{"id":28769558,"url":"https://github.com/pinecone-io/pinecone-mcp","last_synced_at":"2025-08-13T02:07:41.971Z","repository":{"id":288682625,"uuid":"963450460","full_name":"pinecone-io/pinecone-mcp","owner":"pinecone-io","description":"Connect your Pinecone projects to Cursor, Claude, and other AI assistants","archived":false,"fork":false,"pushed_at":"2025-06-24T17:20:02.000Z","size":21288,"stargazers_count":28,"open_issues_count":3,"forks_count":8,"subscribers_count":10,"default_branch":"main","last_synced_at":"2025-07-26T16:24:08.804Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/pinecone-io.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","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,"zenodo":null}},"created_at":"2025-04-09T17:45:16.000Z","updated_at":"2025-07-18T05:42:59.000Z","dependencies_parsed_at":"2025-04-20T13:03:04.333Z","dependency_job_id":null,"html_url":"https://github.com/pinecone-io/pinecone-mcp","commit_stats":null,"previous_names":["pinecone-io/pinecone-mcp"],"tags_count":11,"template":false,"template_full_name":null,"purl":"pkg:github/pinecone-io/pinecone-mcp","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pinecone-io%2Fpinecone-mcp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pinecone-io%2Fpinecone-mcp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pinecone-io%2Fpinecone-mcp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pinecone-io%2Fpinecone-mcp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pinecone-io","download_url":"https://codeload.github.com/pinecone-io/pinecone-mcp/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pinecone-io%2Fpinecone-mcp/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":270166108,"owners_count":24538445,"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","status":"online","status_checked_at":"2025-08-13T02:00:09.904Z","response_time":66,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":[],"created_at":"2025-06-17T13:04:01.965Z","updated_at":"2025-08-13T02:07:41.951Z","avatar_url":"https://github.com/pinecone-io.png","language":"TypeScript","funding_links":[],"categories":["Databases","Wissen und Gedächtnis","Production-Ready Servers","官方 MCP 服务器列表","Servers","Cloud Services","Databases and Data","🌐 Web Development","Tools"],"sub_categories":["Vector Databases","Claude API","Dieselbe Konfiguration, CLI und IDE","Data \u0026 Databases","How to Submit","Development"],"readme":"# Pinecone Developer MCP Server\n\nThe [Model Context Protocol](https://modelcontextprotocol.io/introduction) (MCP) is a standard that allows coding assistants and other AI tools to interact with platforms like Pinecone. The Pinecone Developer MCP Server allows you to connect these tools with Pinecone projects and documentation.\n\nOnce connected, AI tools can:\n* Search [Pinecone documentation](https://docs.pinecone.io) to answer questions accurately.\n* Help you configure indexes based on your application's needs.\n* Generate code informed by your index configuration and data, as well as Pinecone documentation and examples.\n* Upsert and search for data in indexes, allowing you to test queries and evaluate results within your dev environment.\n\nSee the [docs](https://docs.pinecone.io/guides/operations/mcp-server) for more detailed information.\n\nThis MCP server is focused on improving the experience of developers working with Pinecone as part of their technology stack. It is intended for use with coding assistants. Pinecone also offers the [Assistant MCP](https://github.com/pinecone-io/assistant-mcp), which is designed to provide AI assistants with relevant context sourced from your knowledge base.\n\n## Setup\n\nTo configure the MCP server to access your Pinecone project, you will need to generate an API key using the [console](https://app.pinecone.io). Without an API key, your AI tool will still be able to search documentation. However, it will not be able to manage or query your indexes.\n\nThe MCP server requires [Node.js](https://nodejs.org). Ensure that `node` and `npx` are available in your `PATH`.\n\nNext, you will need to configure your AI assistant to use the MCP server.\n\n### Configure Cursor\n\nTo add the Pinecone MCP server to a project, create a `.cursor/mcp.json` file in the project root (if it doesn't already exist) and add the following configuration:\n\n```\n{\n  \"mcpServers\": {\n    \"pinecone\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\", \"@pinecone-database/mcp\"\n      ],\n      \"env\": {\n        \"PINECONE_API_KEY\": \"\u003cyour pinecone api key\u003e\"\n      }\n    }\n  }\n}\n```\n\nYou can check the status of the server in **Cursor Settings \u003e MCP**.\n\nTo enable the server globally, add the configuration to the `.cursor/mcp.json` in your home directory instead.\n\nIt is recommended to use rules to instruct Cursor on proper usage of the MCP server. Check out the [docs](https://docs.pinecone.io/guides/operations/mcp-server#configure-cursor) for some suggestions.\n\n### Configure Claude desktop\n\nUse Claude desktop to locate the `claude_desktop_config.json` file by navigating to **Settings \u003e Developer \u003e Edit Config**. Add the following configuration:\n\n```\n{\n  \"mcpServers\": {\n    \"pinecone\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\", \"@pinecone-database/mcp\"\n      ],\n      \"env\": {\n        \"PINECONE_API_KEY\": \"\u003cyour pinecone api key\u003e\"\n      }\n    }\n  }\n}\n```\n\nRestart Claude desktop. On the new chat screen, you should see a hammer (MCP) icon appear with the new MCP tools available.\n\n## Usage\nOnce configured, your AI tool will automatically make use of the MCP to interact with Pinecone. You may be prompted for permission before a tool can be used. Try asking your AI assistant to set up an example index, upload sample data, or search for you!\n\n### Tools\nPinecone Developer MCP Server provides the following tools for AI assistants to use:\n- `search-docs`: Search the official Pinecone documentation.\n- `list-indexes`: Lists all Pinecone indexes.\n- `describe-index`: Describes the configuration of an index.\n- `describe-index-stats`: Provides statistics about the data in the index, including the  number of records and available namespaces.\n- `create-index-for-model`: Creates a new index that uses an integrated inference model to embed text as vectors.\n- `upsert-records`: Inserts or updates records in an index with integrated inference.\n- `search-records`: Searches for records in an index based on a text query, using integrated inference for embedding. Has options for metadata filtering and reranking.\n- `cascading-search`: Searches for records across multiple indexes, deduplicating and reranking the results.\n- `rerank-documents`: Reranks a collection of records or text documents using a specialized reranking model.\n\n### Limitations\nOnly indexes with integrated inference are supported. Assistants, indexes without integrated inference, standalone embeddings, and vector search are not supported.\n\n## Contributing\nWe welcome your collaboration in improving the developer MCP experience. Please submit issues in the [GitHub issue tracker](https://github.com/pinecone-io/pinecone-mcp/issues). Information about contributing can be found in [CONTRIBUTING.md](CONTRIBUTING.md).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpinecone-io%2Fpinecone-mcp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpinecone-io%2Fpinecone-mcp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpinecone-io%2Fpinecone-mcp/lists"}