{"id":26570838,"url":"https://github.com/sirmews/mcp-pinecone","last_synced_at":"2025-12-14T14:28:55.322Z","repository":{"id":267109677,"uuid":"900184645","full_name":"sirmews/mcp-pinecone","owner":"sirmews","description":"Model Context Protocol server to allow for reading and writing from Pinecone. Rudimentary RAG","archived":false,"fork":false,"pushed_at":"2025-01-31T08:20:22.000Z","size":115,"stargazers_count":28,"open_issues_count":1,"forks_count":8,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-01T18:20:10.683Z","etag":null,"topics":["claude","model-context-protocol","pinecone","rag"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sirmews.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-12-08T04:53:27.000Z","updated_at":"2025-02-26T23:16:17.000Z","dependencies_parsed_at":"2025-01-05T10:33:07.400Z","dependency_job_id":null,"html_url":"https://github.com/sirmews/mcp-pinecone","commit_stats":null,"previous_names":["sirmews/mcp-pinecone"],"tags_count":9,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sirmews%2Fmcp-pinecone","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sirmews%2Fmcp-pinecone/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sirmews%2Fmcp-pinecone/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sirmews%2Fmcp-pinecone/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sirmews","download_url":"https://codeload.github.com/sirmews/mcp-pinecone/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245026583,"owners_count":20549166,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["claude","model-context-protocol","pinecone","rag"],"created_at":"2025-03-22T22:19:17.918Z","updated_at":"2025-12-14T14:28:50.266Z","avatar_url":"https://github.com/sirmews.png","language":"Python","funding_links":[],"categories":["Database \u0026 Messaging MCP Servers","Community Servers","🤖 AI/ML","MCP 服务器精选列表","پیاده‌سازی‌های سرور","Legend","MCP Servers","Knowledge \u0026 Memory","APIs and HTTP Requests","Databases","Table of Contents","🗂️ Extensions by Category","Uncategorized","Server Implementations"],"sub_categories":["🗄️ 数据库交互","🗄️ \u003ca name=\"databases\"\u003e\u003c/a\u003eپایگاه‌های داده","🗄️ \u003ca name=\"databases\"\u003e\u003c/a\u003eDatabases","🗄️ Databases","How to Submit","AI Services","Uncategorized"],"readme":"# Pinecone Model Context Protocol Server for Claude Desktop.\n\n[![smithery badge](https://smithery.ai/badge/mcp-pinecone)](https://smithery.ai/server/mcp-pinecone)\n\n[![PyPI - Downloads](https://img.shields.io/pypi/dd/mcp-pinecone?style=flat)](https://pypi.org/project/mcp-pinecone/)\n\nRead and write to a Pinecone index.\n\n\n## Components\n\n```mermaid\nflowchart TB\n    subgraph Client[\"MCP Client (e.g., Claude Desktop)\"]\n        UI[User Interface]\n    end\n\n    subgraph MCPServer[\"MCP Server (pinecone-mcp)\"]\n        Server[Server Class]\n        \n        subgraph Handlers[\"Request Handlers\"]\n            ListRes[list_resources]\n            ReadRes[read_resource]\n            ListTools[list_tools]\n            CallTool[call_tool]\n            GetPrompt[get_prompt]\n            ListPrompts[list_prompts]\n        end\n        \n        subgraph Tools[\"Implemented Tools\"]\n            SemSearch[semantic-search]\n            ReadDoc[read-document]\n            ListDocs[list-documents]\n            PineconeStats[pinecone-stats]\n            ProcessDoc[process-document]\n        end\n    end\n\n    subgraph PineconeService[\"Pinecone Service\"]\n        PC[Pinecone Client]\n        subgraph PineconeFunctions[\"Pinecone Operations\"]\n            Search[search_records]\n            Upsert[upsert_records]\n            Fetch[fetch_records]\n            List[list_records]\n            Embed[generate_embeddings]\n        end\n        Index[(Pinecone Index)]\n    end\n\n    %% Connections\n    UI --\u003e Server\n    Server --\u003e Handlers\n    \n    ListTools --\u003e Tools\n    CallTool --\u003e Tools\n    \n    Tools --\u003e PC\n    PC --\u003e PineconeFunctions\n    PineconeFunctions --\u003e Index\n    \n    %% Data flow for semantic search\n    SemSearch --\u003e Search\n    Search --\u003e Embed\n    Embed --\u003e Index\n    \n    %% Data flow for document operations\n    UpsertDoc --\u003e Upsert\n    ReadDoc --\u003e Fetch\n    ListRes --\u003e List\n\n    classDef primary fill:#2563eb,stroke:#1d4ed8,color:white\n    classDef secondary fill:#4b5563,stroke:#374151,color:white\n    classDef storage fill:#059669,stroke:#047857,color:white\n    \n    class Server,PC primary\n    class Tools,Handlers secondary\n    class Index storage\n```\n\n### Resources\n\nThe server implements the ability to read and write to a Pinecone index.\n\n### Tools\n\n- `semantic-search`: Search for records in the Pinecone index.\n- `read-document`: Read a document from the Pinecone index.\n- `list-documents`: List all documents in the Pinecone index.\n- `pinecone-stats`: Get stats about the Pinecone index, including the number of records, dimensions, and namespaces.\n- `process-document`: Process a document into chunks and upsert them into the Pinecone index. This performs the overall steps of chunking, embedding, and upserting.\n\nNote: embeddings are generated via Pinecone's inference API and chunking is done with a token-based chunker. Written by copying a lot from langchain and debugging with Claude.\n## Quickstart\n\n### Installing via Smithery\n\nTo install Pinecone MCP Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/mcp-pinecone):\n\n```bash\nnpx -y @smithery/cli install mcp-pinecone --client claude\n```\n\n### Install the server\n\nRecommend using [uv](https://docs.astral.sh/uv/getting-started/installation/) to install the server locally for Claude.\n\n```\nuvx install mcp-pinecone\n```\nOR\n```\nuv pip install mcp-pinecone\n```\n\nAdd your config as described below.\n\n#### Claude Desktop\n\nOn MacOS: `~/Library/Application\\ Support/Claude/claude_desktop_config.json`\nOn Windows: `%APPDATA%/Claude/claude_desktop_config.json`\n\nNote: You might need to use the direct path to `uv`. Use `which uv` to find the path.\n\n\n__Development/Unpublished Servers Configuration__\n  \n```json\n\"mcpServers\": {\n  \"mcp-pinecone\": {\n    \"command\": \"uv\",\n    \"args\": [\n      \"--directory\",\n      \"{project_dir}\",\n      \"run\",\n      \"mcp-pinecone\"\n    ]\n  }\n}\n```\n\n\n__Published Servers Configuration__\n  \n```json\n\"mcpServers\": {\n  \"mcp-pinecone\": {\n    \"command\": \"uvx\",\n    \"args\": [\n      \"--index-name\",\n      \"{your-index-name}\",\n      \"--api-key\",\n      \"{your-secret-api-key}\",\n      \"mcp-pinecone\"\n    ]\n  }\n}\n```\n\n#### Sign up to Pinecone\n\nYou can sign up for a Pinecone account [here](https://www.pinecone.io/).\n\n#### Get an API key\n\nCreate a new index in Pinecone, replacing `{your-index-name}` and get an API key from the Pinecone dashboard, replacing `{your-secret-api-key}` in the config.\n\n## Development\n\n### Building and Publishing\n\nTo prepare the package for distribution:\n\n1. Sync dependencies and update lockfile:\n```bash\nuv sync\n```\n\n2. Build package distributions:\n```bash\nuv build\n```\n\nThis will create source and wheel distributions in the `dist/` directory.\n\n3. Publish to PyPI:\n```bash\nuv publish\n```\n\nNote: You'll need to set PyPI credentials via environment variables or command flags:\n- Token: `--token` or `UV_PUBLISH_TOKEN`\n- Or username/password: `--username`/`UV_PUBLISH_USERNAME` and `--password`/`UV_PUBLISH_PASSWORD`\n\n### Debugging\n\nSince MCP servers run over stdio, debugging can be challenging. For the best debugging\nexperience, we strongly recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector).\n\n\nYou can launch the MCP Inspector via [`npm`](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm) with this command:\n\n```bash\nnpx @modelcontextprotocol/inspector uv --directory {project_dir} run mcp-pinecone\n```\n\n\nUpon launching, the Inspector will display a URL that you can access in your browser to begin debugging.\n\n## License\n\nThis project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.\n\n## Source Code\n\nThe source code is available on [GitHub](https://github.com/sirmews/mcp-pinecone).\n\n## Contributing\n\nSend your ideas and feedback to me on [Bluesky](https://bsky.app/profile/perfectlycromulent.bsky.social) or by opening an issue.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsirmews%2Fmcp-pinecone","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsirmews%2Fmcp-pinecone","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsirmews%2Fmcp-pinecone/lists"}