├── .editorconfig ├── .env.example ├── .github ├── scripts │ └── before-beta-release.cjs └── workflows │ ├── check.yaml │ ├── pre_release.yaml │ └── release.yaml ├── .gitignore ├── .npmignore ├── CHANGELOG.md ├── LICENSE ├── README.md ├── eslint.config.mjs ├── package-lock.json ├── package.json ├── src ├── example_call_web_browser.ts ├── example_client_stdio.ts ├── index.ts └── server.ts ├── tsconfig.eslint.json └── tsconfig.json /.editorconfig: -------------------------------------------------------------------------------- 1 | root = true 2 | 3 | [*] 4 | indent_style = space 5 | indent_size = 4 6 | charset = utf-8 7 | trim_trailing_whitespace = true 8 | insert_final_newline = true 9 | end_of_line = lf 10 | max_line_length = 120 11 | -------------------------------------------------------------------------------- /.env.example: -------------------------------------------------------------------------------- 1 | APIFY_TOKEN= 2 | -------------------------------------------------------------------------------- /.github/scripts/before-beta-release.cjs: -------------------------------------------------------------------------------- 1 | const { execSync } = require('child_process'); 2 | const fs = require('fs'); 3 | const path = require('path'); 4 | 5 | const PKG_JSON_PATH = path.join(__dirname, '..', '..', 'package.json'); 6 | 7 | const pkgJson = require(PKG_JSON_PATH); // eslint-disable-line import/no-dynamic-require 8 | 9 | const PACKAGE_NAME = pkgJson.name; 10 | const VERSION = pkgJson.version; 11 | 12 | const nextVersion = getNextVersion(VERSION); 13 | console.log(`before-deploy: Setting version to ${nextVersion}`); // eslint-disable-line no-console 14 | pkgJson.version = nextVersion; 15 | 16 | fs.writeFileSync(PKG_JSON_PATH, `${JSON.stringify(pkgJson, null, 2)}\n`); 17 | 18 | function getNextVersion(version) { 19 | const versionString = execSync(`npm show ${PACKAGE_NAME} versions --json`, { encoding: 'utf8' }); 20 | const versions = JSON.parse(versionString); 21 | 22 | if (versions.some((v) => v === VERSION)) { 23 | console.error(`before-deploy: A release with version ${VERSION} already exists. Please increment version accordingly.`); // eslint-disable-line no-console 24 | process.exit(1); 25 | } 26 | 27 | const prereleaseNumbers = versions 28 | .filter((v) => (v.startsWith(VERSION) && v.includes('-'))) 29 | .map((v) => Number(v.match(/\.(\d+)$/)[1])); 30 | const lastPrereleaseNumber = Math.max(-1, ...prereleaseNumbers); 31 | return `${version}-beta.${lastPrereleaseNumber + 1}`; 32 | } 33 | -------------------------------------------------------------------------------- /.github/workflows/check.yaml: -------------------------------------------------------------------------------- 1 | # This workflow runs for every pull request to lint and test the proposed changes. 2 | 3 | name: Check 4 | 5 | on: 6 | pull_request: 7 | 8 | # Push to main will trigger code checks 9 | push: 10 | branches: 11 | - main 12 | tags-ignore: 13 | - "**" # Ignore all tags to prevent duplicate builds when tags are pushed. 14 | 15 | jobs: 16 | lint_and_test: 17 | name: Lint 18 | runs-on: ubuntu-latest 19 | 20 | steps: 21 | - uses: actions/checkout@v4 22 | - name: Use Node.js 22 23 | uses: actions/setup-node@v4 24 | with: 25 | node-version: 22 26 | cache: 'npm' 27 | cache-dependency-path: 'package-lock.json' 28 | - name: Install Dependencies 29 | run: npm ci 30 | 31 | - name: Lint 32 | run: npm run lint 33 | -------------------------------------------------------------------------------- /.github/workflows/pre_release.yaml: -------------------------------------------------------------------------------- 1 | name: Create a pre-release 2 | 3 | on: 4 | # Push to main will deploy a beta version 5 | push: 6 | branches: 7 | - main 8 | tags-ignore: 9 | - "**" # Ignore all tags to prevent duplicate builds when tags are pushed. 10 | 11 | concurrency: 12 | group: release 13 | cancel-in-progress: false 14 | 15 | jobs: 16 | release_metadata: 17 | if: "!startsWith(github.event.head_commit.message, 'docs') && !startsWith(github.event.head_commit.message, 'ci') && startsWith(github.repository, 'apify/')" 18 | name: Prepare release metadata 19 | runs-on: ubuntu-latest 20 | outputs: 21 | version_number: ${{ steps.release_metadata.outputs.version_number }} 22 | changelog: ${{ steps.release_metadata.outputs.changelog }} 23 | steps: 24 | - uses: apify/workflows/git-cliff-release@main 25 | name: Prepare release metadata 26 | id: release_metadata 27 | with: 28 | release_type: prerelease 29 | existing_changelog_path: CHANGELOG.md 30 | 31 | wait_for_checks: 32 | name: Wait for code checks to pass 33 | runs-on: ubuntu-latest 34 | steps: 35 | - uses: lewagon/wait-on-check-action@v1.3.4 36 | with: 37 | ref: ${{ github.ref }} 38 | repo-token: ${{ secrets.GITHUB_TOKEN }} 39 | check-regexp: (Build & Test .*|Lint|Docs build) 40 | wait-interval: 5 41 | 42 | update_changelog: 43 | needs: [ release_metadata, wait_for_checks ] 44 | name: Update changelog 45 | runs-on: ubuntu-latest 46 | outputs: 47 | changelog_commitish: ${{ steps.commit.outputs.commit_long_sha || github.sha }} 48 | 49 | steps: 50 | - name: Checkout repository 51 | uses: actions/checkout@v4 52 | with: 53 | token: ${{ secrets.APIFY_SERVICE_ACCOUNT_GITHUB_TOKEN }} 54 | 55 | - name: Use Node.js 22 56 | uses: actions/setup-node@v4 57 | with: 58 | node-version: 22 59 | 60 | - name: Update package version in package.json 61 | run: npm version --no-git-tag-version --allow-same-version ${{ needs.release_metadata.outputs.version_number }} 62 | 63 | - name: Update CHANGELOG.md 64 | uses: DamianReeves/write-file-action@master 65 | with: 66 | path: CHANGELOG.md 67 | write-mode: overwrite 68 | contents: ${{ needs.release_metadata.outputs.changelog }} 69 | 70 | - name: Commit changes 71 | id: commit 72 | uses: EndBug/add-and-commit@v9 73 | with: 74 | author_name: Apify Release Bot 75 | author_email: noreply@apify.com 76 | message: "chore(release): Update changelog and package version [skip ci]" 77 | 78 | publish_to_npm: 79 | name: Publish to NPM 80 | needs: [ release_metadata, wait_for_checks ] 81 | runs-on: ubuntu-latest 82 | steps: 83 | - uses: actions/checkout@v4 84 | with: 85 | ref: ${{ needs.update_changelog.changelog_commitish }} 86 | - name: Use Node.js 22 87 | uses: actions/setup-node@v4 88 | with: 89 | node-version: 22 90 | cache: 'npm' 91 | cache-dependency-path: 'package-lock.json' 92 | - name: Install dependencies 93 | run: | 94 | echo "access=public" >> .npmrc 95 | echo "//registry.npmjs.org/:_authToken=${NPM_TOKEN}" >> .npmrc 96 | npm ci 97 | - # Check version consistency and increment pre-release version number for beta only. 98 | name: Bump pre-release version 99 | run: node ./.github/scripts/before-beta-release.cjs 100 | - name: Build module 101 | run: npm run build 102 | - name: Publish to NPM 103 | run: npm publish --tag beta 104 | 105 | env: 106 | NODE_AUTH_TOKEN: ${{ secrets.APIFY_SERVICE_ACCOUNT_NPM_TOKEN }} 107 | NPM_TOKEN: ${{ secrets.APIFY_SERVICE_ACCOUNT_NPM_TOKEN }} 108 | -------------------------------------------------------------------------------- /.github/workflows/release.yaml: -------------------------------------------------------------------------------- 1 | name: Create a release 2 | 3 | on: 4 | # Trigger a stable version release via GitHub's UI, with the ability to specify the type of release. 5 | workflow_dispatch: 6 | inputs: 7 | release_type: 8 | description: Release type 9 | required: true 10 | type: choice 11 | default: auto 12 | options: 13 | - auto 14 | - custom 15 | - patch 16 | - minor 17 | - major 18 | custom_version: 19 | description: The custom version to bump to (only for "custom" type) 20 | required: false 21 | type: string 22 | default: "" 23 | 24 | concurrency: 25 | group: release 26 | cancel-in-progress: false 27 | 28 | jobs: 29 | release_metadata: 30 | name: Prepare release metadata 31 | runs-on: ubuntu-latest 32 | outputs: 33 | version_number: ${{ steps.release_metadata.outputs.version_number }} 34 | tag_name: ${{ steps.release_metadata.outputs.tag_name }} 35 | changelog: ${{ steps.release_metadata.outputs.changelog }} 36 | release_notes: ${{ steps.release_metadata.outputs.release_notes }} 37 | steps: 38 | - uses: apify/workflows/git-cliff-release@main 39 | name: Prepare release metadata 40 | id: release_metadata 41 | with: 42 | release_type: ${{ inputs.release_type }} 43 | custom_version: ${{ inputs.custom_version }} 44 | existing_changelog_path: CHANGELOG.md 45 | 46 | update_changelog: 47 | needs: [ release_metadata ] 48 | name: Update changelog 49 | runs-on: ubuntu-latest 50 | outputs: 51 | changelog_commitish: ${{ steps.commit.outputs.commit_long_sha || github.sha }} 52 | 53 | steps: 54 | - name: Checkout repository 55 | uses: actions/checkout@v4 56 | with: 57 | token: ${{ secrets.APIFY_SERVICE_ACCOUNT_GITHUB_TOKEN }} 58 | 59 | - name: Use Node.js 22 60 | uses: actions/setup-node@v4 61 | with: 62 | node-version: 22 63 | 64 | - name: Update package version in package.json 65 | run: npm version --no-git-tag-version --allow-same-version ${{ needs.release_metadata.outputs.version_number }} 66 | 67 | - name: Update CHANGELOG.md 68 | uses: DamianReeves/write-file-action@master 69 | with: 70 | path: CHANGELOG.md 71 | write-mode: overwrite 72 | contents: ${{ needs.release_metadata.outputs.changelog }} 73 | 74 | - name: Commit changes 75 | id: commit 76 | uses: EndBug/add-and-commit@v9 77 | with: 78 | author_name: Apify Release Bot 79 | author_email: noreply@apify.com 80 | message: "chore(release): Update changelog and package version [skip ci]" 81 | 82 | create_github_release: 83 | name: Create github release 84 | needs: [release_metadata, update_changelog] 85 | runs-on: ubuntu-latest 86 | env: 87 | GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} 88 | steps: 89 | - name: Create release 90 | uses: softprops/action-gh-release@v2 91 | with: 92 | tag_name: ${{ needs.release_metadata.outputs.tag_name }} 93 | name: ${{ needs.release_metadata.outputs.version_number }} 94 | target_commitish: ${{ needs.update_changelog.outputs.changelog_commitish }} 95 | body: ${{ needs.release_metadata.outputs.release_notes }} 96 | 97 | publish_to_npm: 98 | name: Publish to NPM 99 | needs: [ update_changelog ] 100 | runs-on: ubuntu-latest 101 | steps: 102 | - uses: actions/checkout@v4 103 | with: 104 | ref: ${{ needs.update_changelog.changelog_commitish }} 105 | - name: Use Node.js 22 106 | uses: actions/setup-node@v4 107 | with: 108 | node-version: 22 109 | cache: 'npm' 110 | cache-dependency-path: 'package-lock.json' 111 | - name: Install dependencies 112 | run: | 113 | echo "access=public" >> .npmrc 114 | echo "//registry.npmjs.org/:_authToken=${NPM_TOKEN}" >> .npmrc 115 | npm ci 116 | - name: Build module 117 | run: npm run build 118 | - name: Publish to NPM 119 | run: npm publish --tag latest 120 | 121 | env: 122 | NODE_AUTH_TOKEN: ${{ secrets.APIFY_SERVICE_ACCOUNT_NPM_TOKEN }} 123 | NPM_TOKEN: ${{ secrets.APIFY_SERVICE_ACCOUNT_NPM_TOKEN }} 124 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # This file tells Git which files shouldn't be added to source control 2 | 3 | .DS_Store 4 | .idea 5 | dist 6 | build 7 | node_modules 8 | apify_storage 9 | storage 10 | 11 | 12 | .env 13 | -------------------------------------------------------------------------------- /.npmignore: -------------------------------------------------------------------------------- 1 | # .npmignore 2 | # Exclude everything by default 3 | * 4 | 5 | # Include specific files and folders 6 | !dist/ 7 | !README.md 8 | !LICENSE 9 | -------------------------------------------------------------------------------- /CHANGELOG.md: -------------------------------------------------------------------------------- 1 | # Changelog 2 | 3 | All notable changes to this project will be documented in this file. 4 | 5 | ## [0.1.3](https://github.com/apify/mcp-server-rag-web-browser/releases/tag/v0.1.3) (2025-03-17) 6 | 7 | ### 🐛 Bug Fixes 8 | 9 | - Changelog, package ([#17](https://github.com/apify/mcp-server-rag-web-browser/pull/17)) ([9067509](https://github.com/apify/mcp-server-rag-web-browser/commit/9067509a12fda837456899b22a3432c8ff172f4f)) by [@jirispilka](https://github.com/jirispilka) 10 | 11 | 12 | ## [0.1.1](https://github.com/apify/mcp-server-rag-web-browser/releases/tag/v0.1.1) (2025-03-17) 13 | 14 | ### 🚀 Features 15 | - Add scraping tool option ([#13](https://github.com/apify/mcp-server-rag-web-browser/pull/13)) ([0dc796c](https://github.com/apify/mcp-server-rag-web-browser/commit/0dc796cea98e02e276fcc03e43514fa156a3018d)) by [@jirispilka](https://github.com/jirispilka) 16 | - Refactor server to simplify it ([#14](https://github.com/apify/mcp-server-rag-web-browser/pull/14)) ([bbd063b](https://github.com/apify/mcp-server-rag-web-browser/commit/bbd063b2b4fc58e1fd25c07908ec1e8355955c59)) by [@jirispilka](https://github.com/jirispilka) 17 | - Change env variable name from APIFY_API_TOKEN to APIFY_TOKEN 18 | - Add extra query parameters 19 | - Remove unnecessary example clients (SSE and chat client) 20 | - Create NPM package @apify/mcp-server-rag-web-browser 21 | - Update readme 22 | 23 | ### 🐛 Bug Fixes 24 | 25 | - Workflow ([#16](https://github.com/apify/mcp-server-rag-web-browser/pull/16)) ([dea430d](https://github.com/apify/mcp-server-rag-web-browser/commit/dea430d793e924821b3eebc99ed4996333af99b8)) by [@jirispilka](https://github.com/jirispilka) 26 | 27 | ## [0.1.0](https://github.com/apify/mcp-server-rag-web-browser/releases/tag/v0.1.0) (2025-03-17) 28 | 29 | ### 🚀 Features 30 | 31 | - Initial release 32 | - Example clients ([#10](https://github.com/apify/mcp-server-rag-web-browser/pull/10)) ([ad31f34](https://github.com/apify/mcp-server-rag-web-browser/commit/ad31f34045e3d5a01b41073af06bae33e89b1f32)) by [@jirispilka](https://github.com/jirispilka), closes [#8](https://github.com/apify/mcp-server-rag-web-browser/issues/8) 33 | 34 | ### 🐛 Bug Fixes 35 | 36 | - Update version ([#15](https://github.com/apify/mcp-server-rag-web-browser/pull/15)) ([1a05865](https://github.com/apify/mcp-server-rag-web-browser/commit/1a05865b4052b080a0dd758ec0e90ea1f7bdd14c)) by [@jirispilka](https://github.com/jirispilka) -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "{}" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright 2023 Apify Technologies s.r.o. 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Model Context Protocol (MCP) Server for the RAG Web Browser Actor 🌐 2 | 3 | Implementation of an MCP server for the [RAG Web Browser Actor](https://apify.com/apify/rag-web-browser). 4 | This Actor serves as a web browser for large language models (LLMs) and RAG pipelines, similar to a web search in ChatGPT. 5 | 6 | mcp-server-rag-web-browser MCP server 7 | 8 | ## 🎯 What does this MCP server do? 9 | 10 | This server is specifically designed to provide fast responses to AI agents and LLMs, allowing them to interact with the web and extract information from web pages. 11 | It runs locally and communicates with the [RAG Web Browser Actor](https://apify.com/apify/rag-web-browser) in [**Standby mode**](https://docs.apify.com/platform/actors/running/standby), 12 | sending search queries and receiving extracted web content in response. 13 | 14 | The RAG Web Browser Actor allows an AI assistant to: 15 | - Perform web search, scrape the top N URLs from the results, and return their cleaned content as Markdown 16 | - Fetch a single URL and return its content as Markdown 17 | 18 | ## 🧱 Components 19 | 20 | ### Tools 21 | 22 | - **search**: Query Google Search, scrape the top N URLs from the results, and returns their cleaned content as Markdown. Arguments: 23 | - `query` (string, required): Search term or URL 24 | - `maxResults` (number, optional): Maximum number of search results to scrape (default: 1) 25 | - `scrapingTool` (string, optional): Select a scraping tool for extracting web pages. Options: 'browser-playwright' or 'raw-http' (default: 'raw-http') 26 | - `outputFormats` (array, optional): Select one or more formats for the output. Options: 'text', 'markdown', 'html' (default: ['markdown']) 27 | - `requestTimeoutSecs` (number, optional): Maximum time in seconds for the request (default: 40) 28 | 29 | ## 🔄 What is the Model Context Protocol? 30 | 31 | The Model Context Protocol (MCP) is a framework that enables AI applications, such as Claude Desktop, to connect seamlessly with external tools and data sources. 32 | For more details, visit the [Model Context Protocol website](https://modelcontextprotocol.org/) or read the blog post [What is MCP and why does it matter?](https://blog.apify.com/what-is-model-context-protocol/). 33 | 34 | ## 🤖 How does the MCP Server integrate with AI Agents? 35 | 36 | The MCP Server empowers AI Agents to perform web searches and browsing using the [RAG Web Browser Actor](https://apify.com/apify/rag-web-browser). 37 | For a comprehensive understanding of AI Agents, check out our blog post: [What are AI Agents?](https://blog.apify.com/what-are-ai-agents/) and explore Apify's [Agents](https://apify.com/store/categories/agents). 38 | 39 | Interested in building and monetizing your own AI agent on Apify? Check out our [step-by-step guide](https://blog.apify.com/how-to-build-an-ai-agent/) for creating, publishing, and monetizing AI agents on the Apify platform. 40 | 41 | ## 🔌 Related MCP servers and clients by Apify 42 | 43 | This server operates over standard input/output (stdio), providing a straightforward connection to AI Agents. Apify offers several other MCP-related tools: 44 | 45 | ### Server Options 46 | - **🖥️ This MCP Server** – A local stdio-based server for direct integration with Claude Desktop 47 | - **🌐 [RAG Web Browser Actor via SSE](https://apify.com/apify/rag-web-browser#anthropic-model-context-protocol-mcp-server)** – Access the RAG Web Browser directly via Server-Sent Events without running a local server 48 | - **🇦 [MCP Server Actor](https://apify.com/apify/actors-mcp-server)** – MCP Server that provides AI agents with access to over 4,000 specialized [Apify Actors](https://apify.com/store) 49 | 50 | ### Client Options 51 | - **💬 [Tester MCP Client](https://apify.com/jiri.spilka/tester-mcp-client)** – A user-friendly UI for interacting with any SSE-based MCP server 52 | 53 | ## 🛠️ Configuration 54 | 55 | ### Prerequisites 56 | 57 | - MacOS or Windows 58 | - The latest version of Claude Desktop must be installed (or another MCP client) 59 | - [Node.js](https://nodejs.org/en) (v18 or higher) 60 | - [Apify API Token](https://docs.apify.com/platform/integrations/api#api-token) (`APIFY_TOKEN`) 61 | 62 | ### Install 63 | 64 | Follow the steps below to set up and run the server on your local machine: 65 | First, clone the repository using the following command: 66 | 67 | ```bash 68 | git clone git@github.com:apify/mcp-server-rag-web-browser.git 69 | ``` 70 | 71 | Navigate to the project directory and install the required dependencies: 72 | 73 | ```bash 74 | cd mcp-server-rag-web-browser 75 | npm install 76 | ``` 77 | 78 | Before running the server, you need to build the project: 79 | 80 | ```bash 81 | npm run build 82 | ``` 83 | 84 | #### Claude Desktop 85 | 86 | Configure Claude Desktop to recognize the MCP server. 87 | 88 | 1. Open your Claude Desktop configuration and edit the following file: 89 | 90 | - On macOS: `~/Library/Application\ Support/Claude/claude_desktop_config.json` 91 | - On Windows: `%APPDATA%/Claude/claude_desktop_config.json` 92 | 93 | ```text 94 | "mcpServers": { 95 | "rag-web-browser": { 96 | "command": "npx", 97 | "args": [ 98 | "@apify/mcp-server-rag-web-browser" 99 | ], 100 | "env": { 101 | "APIFY_TOKEN": "your-apify-api-token" 102 | } 103 | } 104 | } 105 | ``` 106 | 107 | 2. Restart Claude Desktop 108 | 109 | - Fully quit Claude Desktop (ensure it's not just minimized or closed). 110 | - Restart Claude Desktop. 111 | - Look for the 🔌 icon to confirm that the server is connected. 112 | 113 | 3. Examples 114 | 115 | You can ask Claude to perform web searches, such as: 116 | ```text 117 | What is an MCP server and how can it be used? 118 | What is an LLM, and what are the recent news updates? 119 | Find and analyze recent research papers about LLMs. 120 | ``` 121 | 122 | Debug the server using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector) 123 | ```bash 124 | export APIFY_TOKEN=your-apify-api-token 125 | npx @modelcontextprotocol/inspector npx -y @apify/mcp-server-rag-web-browser 126 | ``` 127 | 128 | ## 👷🏼 Development 129 | 130 | ### Local client (stdio) 131 | 132 | To test the server locally, you can use `example_client_stdio.ts`: 133 | 134 | ```bash 135 | export APIFY_TOKEN=your-apify-api-token 136 | node dist/example_client_stdio.js 137 | ``` 138 | 139 | The script will start the MCP server, fetch available tools, and then call the `search` tool with a query. 140 | 141 | ### Direct API Call 142 | 143 | To test calling the RAG Web Browser Actor directly: 144 | 145 | ```bash 146 | export APIFY_TOKEN=your-apify-api-token 147 | node dist/example_call_web_browser.js 148 | ``` 149 | 150 | ### Debugging 151 | 152 | Since MCP servers operate over standard input/output (stdio), debugging can be challenging. 153 | For the best debugging experience, use the [MCP Inspector](https://github.com/modelcontextprotocol/inspector). 154 | 155 | Build the mcp-server-rag-web-browser package: 156 | 157 | ```bash 158 | npm run build 159 | ``` 160 | 161 | You can launch the MCP Inspector via [`npm`](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm) with this command: 162 | 163 | ```bash 164 | export APIFY_TOKEN=your-apify-api-token 165 | npx @modelcontextprotocol/inspector node dist/index.js 166 | ``` 167 | 168 | Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging. 169 | -------------------------------------------------------------------------------- /eslint.config.mjs: -------------------------------------------------------------------------------- 1 | import apifyConfig from '@apify/eslint-config'; 2 | 3 | // eslint-disable-next-line import/no-default-export 4 | export default [ 5 | { ignores: ['**/dist'] }, // Ignores need to happen first 6 | ...(Array.isArray(apifyConfig) ? apifyConfig : [apifyConfig]), 7 | { 8 | languageOptions: { 9 | sourceType: 'module', 10 | 11 | parserOptions: { 12 | project: 'tsconfig.eslint.json', 13 | }, 14 | }, 15 | }, 16 | ]; 17 | -------------------------------------------------------------------------------- /package.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "@apify/mcp-server-rag-web-browser", 3 | "version": "0.1.3", 4 | "type": "module", 5 | "description": "An MCP Server for RAG Web Browser Actor", 6 | "engines": { 7 | "node": ">=18.0.0" 8 | }, 9 | "main": "dist/index.js", 10 | "bin": { 11 | "mcp-rag-web-browser": "./dist/index.js" 12 | }, 13 | "files": [ 14 | "dist", 15 | "LICENSE" 16 | ], 17 | "repository": { 18 | "type": "git", 19 | "url": "https://github.com/apify/mcp-server-rag-web-browser" 20 | }, 21 | "bugs": { 22 | "url": "https://github.com/apify/mcp-server-rag-web-browser/issues" 23 | }, 24 | "homepage": "https://github.com/apify/mcp-server-rag-web-browser", 25 | "keywords": [ 26 | "apify", 27 | "mcp", 28 | "server", 29 | "actors", 30 | "model context protocol", 31 | "rag", 32 | "web browser" 33 | ], 34 | "scripts": { 35 | "start": "npm run start:dev", 36 | "start:prod": "node dist/index.js", 37 | "start:dev": "tsx src/index.ts", 38 | "lint": "eslint .", 39 | "lint:fix": "eslint . --fix", 40 | "build": "tsc", 41 | "watch": "tsc --watch", 42 | "inspector": "npx @modelcontextprotocol/inspector dist/index.js" 43 | }, 44 | "dependencies": { 45 | "@modelcontextprotocol/sdk": "^1.0.4", 46 | "express": "^4.21.2", 47 | "node-fetch": "^3.3.2", 48 | "zod": "^3.24.1", 49 | "zod-to-json-schema": "^3.24.1" 50 | }, 51 | "devDependencies": { 52 | "@apify/eslint-config": "^0.5.0-beta.7", 53 | "@apify/eslint-config-ts": "^0.4.1", 54 | "@apify/tsconfig": "^0.1.0", 55 | "@types/express": "^5.0.0", 56 | "@types/node": "^20.11.24", 57 | "dotenv": "^16.4.7", 58 | "eslint": "^9.22.0", 59 | "tsx": "^4.6.2", 60 | "typescript": "^5.3.3", 61 | "typescript-eslint": "^8.18.2" 62 | } 63 | } 64 | -------------------------------------------------------------------------------- /src/example_call_web_browser.ts: -------------------------------------------------------------------------------- 1 | /** 2 | * @fileoverview Example how to call the RAG Web Browser Actor in a standby mode. 3 | * @module src/example_call_web_browser 4 | */ 5 | 6 | /* eslint-disable no-console */ 7 | import dotenv from 'dotenv'; 8 | import fetch from 'node-fetch'; 9 | 10 | dotenv.config({ path: '../.env' }); 11 | 12 | const QUERY = 'MCP Server for Anthropic'; 13 | const MAX_RESULTS = 1; // Limit the number of results to decrease response size 14 | const ACTOR_BASE_URL = 'https://rag-web-browser.apify.actor/search'; // Base URL from OpenAPI schema 15 | 16 | const { APIFY_TOKEN } = process.env; 17 | 18 | if (!APIFY_TOKEN) { 19 | throw new Error('APIFY_TOKEN environment variable is not set.'); 20 | } 21 | 22 | const queryParams = new URLSearchParams({ 23 | query: QUERY, 24 | maxResults: MAX_RESULTS.toString(), 25 | }); 26 | 27 | const headers = { 28 | Authorization: `Bearer ${APIFY_TOKEN}`, 29 | }; 30 | 31 | // eslint-disable-next-line no-void 32 | void (async () => { 33 | const url = `${ACTOR_BASE_URL}?${queryParams.toString()}`; 34 | console.info(`GET request to ${url}`); 35 | 36 | try { 37 | const response = await fetch(url, { method: 'GET', headers }); 38 | 39 | if (!response.ok) { 40 | console.log(`Error: Failed to fetch data: ${response.statusText}`); 41 | } 42 | 43 | const responseBody = await response.json(); 44 | console.info('Received response from RAG Web Browser:', responseBody); 45 | 46 | // Optional: Further process or display the response 47 | console.log('Response:', responseBody); 48 | } catch (error: any) { // eslint-disable-line @typescript-eslint/no-explicit-any 49 | console.error('Error occurred:', error.message); 50 | } 51 | })(); 52 | -------------------------------------------------------------------------------- /src/example_client_stdio.ts: -------------------------------------------------------------------------------- 1 | /* eslint-disable no-console */ 2 | /** 3 | * Connect to the MCP server using stdio transport and call a tool. 4 | * You need provide a path to MCP server and APIFY_TOKEN in .env file. 5 | */ 6 | 7 | import { Client } from '@modelcontextprotocol/sdk/client/index.js'; 8 | import { StdioClientTransport } from '@modelcontextprotocol/sdk/client/stdio.js'; 9 | import { CallToolResultSchema } from '@modelcontextprotocol/sdk/types.js'; 10 | import dotenv from 'dotenv'; 11 | 12 | dotenv.config({ path: '../.env' }); 13 | 14 | const { APIFY_TOKEN } = process.env; 15 | 16 | if (!APIFY_TOKEN) { 17 | throw new Error('APIFY_TOKEN environment variable is not set.'); 18 | } 19 | 20 | const SERVER_PATH = '../dist/index.js'; 21 | 22 | // Create server parameters for stdio connection 23 | const transport = new StdioClientTransport({ 24 | command: 'node', // Executable 25 | args: [ 26 | SERVER_PATH, 27 | ], 28 | env: { 29 | 'APIFY_TOKEN': APIFY_TOKEN 30 | } 31 | }); 32 | 33 | // Create a new client instance 34 | const client = new Client( 35 | { name: 'example-client', version: '1.0.0' }, 36 | { capabilities: {} }, 37 | ); 38 | 39 | // Main function to run the example client 40 | async function run() { 41 | try { 42 | // Connect to the MCP server 43 | await client.connect(transport); 44 | 45 | // List available tools 46 | const tools = await client.listTools(); 47 | console.log('Available tools:', tools); 48 | 49 | // Call a tool 50 | console.log('Calling rag web browser ...'); 51 | const result = await client.callTool( 52 | { name: 'search', arguments: { query: 'web browser for Anthropic' } }, 53 | CallToolResultSchema, 54 | ); 55 | console.log('Tool result:', JSON.stringify(result)); 56 | } catch (error) { 57 | console.error('Error:', error); 58 | } 59 | } 60 | 61 | // Execute the main function 62 | await run(); 63 | -------------------------------------------------------------------------------- /src/index.ts: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env node 2 | /** 3 | * This script initializes and starts the MCP server for the Apify RAG Web Browser using the Stdio transport. 4 | * 5 | * Usage: 6 | * node 7 | * 8 | * Example: 9 | * node index.js 10 | */ 11 | import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js'; 12 | 13 | import { RagWebBrowserServer } from './server.js'; 14 | 15 | async function main() { 16 | const server = new RagWebBrowserServer(); 17 | const transport = new StdioServerTransport(); 18 | await server.connect(transport); 19 | } 20 | 21 | main().catch((error) => { 22 | console.error('Server error:', error); // eslint-disable-line no-console 23 | process.exit(1); 24 | }); 25 | -------------------------------------------------------------------------------- /src/server.ts: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env node 2 | 3 | /** 4 | * MCP server that allows to call the RAG Web Browser Actor 5 | */ 6 | 7 | import { Server } from '@modelcontextprotocol/sdk/server/index.js'; 8 | import type { Transport } from '@modelcontextprotocol/sdk/shared/transport.js'; 9 | import { 10 | CallToolRequestSchema, 11 | ListToolsRequestSchema, 12 | } from '@modelcontextprotocol/sdk/types.js'; 13 | import { z } from 'zod'; 14 | import { zodToJsonSchema } from 'zod-to-json-schema'; 15 | 16 | 17 | const { APIFY_TOKEN } = process.env; 18 | 19 | const MAX_RESULTS = 1; 20 | const TOOL_SEARCH = 'search'; 21 | const ACTOR_BASE_URL = 'https://rag-web-browser.apify.actor/search'; 22 | 23 | const WebBrowserArgsSchema = z.object({ 24 | query: z.string() 25 | .describe('Enter Google Search keywords or a URL of a specific web page. The keywords might include the' 26 | + 'advanced search operators. Examples: "san francisco weather", "https://www.cnn.com", ' 27 | + '"function calling site:openai.com"') 28 | .regex(/[^\s]+/, { message: "Search term or URL cannot be empty" }), 29 | maxResults: z.number().int().positive().min(1).max(100).default(MAX_RESULTS) 30 | .describe( 31 | 'The maximum number of top organic Google Search results whose web pages will be extracted. ' 32 | + 'If query is a URL, then this field is ignored and the Actor only fetches the specific web page.', 33 | ), 34 | scrapingTool: z.enum(['browser-playwright', 'raw-http']) 35 | .describe('Select a scraping tool for extracting the target web pages. ' 36 | + 'The Browser tool is more powerful and can handle JavaScript heavy websites, while the ' 37 | + 'Plain HTML tool can not handle JavaScript but is about two times faster.') 38 | .default('raw-http'), 39 | outputFormats: z.array(z.enum(['text', 'markdown', 'html'])) 40 | .describe('Select one or more formats to which the target web pages will be extracted.') 41 | .default(['markdown']), 42 | requestTimeoutSecs: z.number().int().min(1).max(300).default(40) 43 | .describe('The maximum time in seconds available for the request, including querying Google Search ' 44 | + 'and scraping the target web pages.'), 45 | }); 46 | 47 | /** 48 | * Create an MCP server with a tool to call RAG Web Browser Actor 49 | */ 50 | export class RagWebBrowserServer { 51 | private server: Server; 52 | 53 | constructor() { 54 | this.server = new Server( 55 | { 56 | name: 'mcp-server-rag-web-browser', 57 | version: '0.1.0', 58 | }, 59 | { 60 | capabilities: { 61 | tools: {}, 62 | }, 63 | }, 64 | ); 65 | this.setupErrorHandling(); 66 | this.setupToolHandlers(); 67 | } 68 | 69 | private async callRagWebBrowser(args: z.infer): Promise { 70 | if (!APIFY_TOKEN) { 71 | throw new Error('APIFY_TOKEN is required but not set. ' 72 | + 'Please set it in your environment variables or pass it as a command-line argument.'); 73 | } 74 | 75 | const queryParams = new URLSearchParams({ 76 | query: args.query, 77 | maxResults: args.maxResults.toString(), 78 | scrapingTool: args.scrapingTool, 79 | }); 80 | 81 | // Add all other parameters if provided 82 | if (args.outputFormats) { 83 | args.outputFormats.forEach((format) => { 84 | queryParams.append('outputFormats', format); 85 | }); 86 | } 87 | 88 | const url = `${ACTOR_BASE_URL}?${queryParams.toString()}`; 89 | const response = await fetch(url, { 90 | method: 'GET', 91 | headers: { 92 | Authorization: `Bearer ${APIFY_TOKEN}`, 93 | }, 94 | }); 95 | 96 | if (!response.ok) { 97 | throw new Error(`Failed to call RAG Web Browser: ${response.statusText}`); 98 | } 99 | 100 | const responseBody = await response.json(); 101 | return JSON.stringify(responseBody); 102 | } 103 | 104 | private setupErrorHandling(): void { 105 | this.server.onerror = (error) => { 106 | console.error('[MCP Error]', error); // eslint-disable-line no-console 107 | }; 108 | process.on('SIGINT', async () => { 109 | await this.server.close(); 110 | process.exit(0); 111 | }); 112 | } 113 | 114 | private setupToolHandlers(): void { 115 | this.server.setRequestHandler(ListToolsRequestSchema, async () => { 116 | return { 117 | tools: [ 118 | { 119 | name: TOOL_SEARCH, 120 | description: 'Search phrase or a URL at Google and return crawled web pages as text or Markdown. ' 121 | + 'Prefer HTTP raw client for speed and browser-playwright for reliability.', 122 | inputSchema: zodToJsonSchema(WebBrowserArgsSchema), 123 | }, 124 | ], 125 | }; 126 | }); 127 | this.server.setRequestHandler(CallToolRequestSchema, async (request) => { 128 | const { name, arguments: args } = request.params; 129 | switch (name) { 130 | case TOOL_SEARCH: { 131 | try { 132 | const parsed = WebBrowserArgsSchema.parse(args); 133 | const content = await this.callRagWebBrowser(parsed); 134 | return { 135 | content: [{ type: 'text', text: content }], 136 | }; 137 | } catch (error) { 138 | console.error('[MCP Error]', error); 139 | throw new Error(`Failed to call RAG Web Browser: ${error}`); 140 | } 141 | } 142 | default: { 143 | throw new Error(`Unknown tool: ${name}`); 144 | } 145 | } 146 | }); 147 | } 148 | 149 | async connect(transport: Transport): Promise { 150 | await this.server.connect(transport); 151 | } 152 | } 153 | -------------------------------------------------------------------------------- /tsconfig.eslint.json: -------------------------------------------------------------------------------- 1 | { 2 | "extends": "./tsconfig.json", 3 | "include": [ 4 | "src/**/*.ts", 5 | "tests/**/*.ts", 6 | "*.ts", 7 | "*.js", 8 | ".eslintrc.js" 9 | ], 10 | "exclude": [ 11 | "node_modules", 12 | "dist" 13 | ] 14 | } 15 | -------------------------------------------------------------------------------- /tsconfig.json: -------------------------------------------------------------------------------- 1 | { 2 | "extends": "@apify/tsconfig", 3 | "compilerOptions": { 4 | "module": "ESNext", 5 | "target": "ESNext", 6 | "outDir": "dist", 7 | "moduleResolution": "node", 8 | "noUnusedLocals": false, 9 | "lib": ["ES2022"], 10 | "skipLibCheck": true, 11 | "typeRoots": ["./types", "./node_modules/@types"], 12 | "strict": true 13 | }, 14 | "include": ["./src/**/*"], 15 | "exclude": ["node_modules"] 16 | } 17 | --------------------------------------------------------------------------------