KosmoKrator

database

Pinecone MCP Integration for Claude Agent SDK

Connect Pinecone to Claude Agent SDK through the local KosmoKrator MCP gateway with scoped tools, credentials, and write policy.

7 functions 5 read 2 write Bearer token auth
Submit Pinecone feedback View package source

Connect Pinecone to Claude Agent SDK

Give Claude Agent SDK workflows access to KosmoKrator integrations through a local MCP server.

Add a KosmoKrator stdio MCP server to the Claude Agent SDK options. The gateway is local, scoped to this integration, and starts with --write=deny so Claude Agent SDK can inspect read-capable tools without receiving write access by default.

Pinecone MCP Config for Claude Agent SDK

Use a narrow integration list so the agent does not load unrelated tools.

{
  "mcpServers": {
    "kosmokrator-pinecone": {
      "type": "stdio",
      "command": "kosmo",
      "args": [
        "mcp:serve",
        "--integration=pinecone",
        "--write=deny"
      ]
    }
  }
}

Run the Gateway Manually

kosmokrator mcp:serve --integration=pinecone --write=deny

Why Use KosmoKrator Here

Scoped tools

Expose only Pinecone instead of a broad multi-service tool list.

Local credentials

Reuse credentials already configured for the KosmoKrator CLI and Lua runtime.

Write policy

Start read-only, then opt into ask or allow for trusted workspaces.

Pinecone Tools Visible to Claude Agent SDK

Claude Agent SDK sees stable MCP tool names generated from the Pinecone integration catalog.

MCP toolSource functionTypeDescription
integration__pinecone__pinecone_list_indexes pinecone.pinecone_list_indexes Read List all vector indexes in your Pinecone project. Returns index names, dimensions, metrics, and status.
integration__pinecone__pinecone_get_index pinecone.pinecone_get_index Read Get detailed information about a specific Pinecone vector index, including its dimension, metric, host URL, and status.
integration__pinecone__pinecone_create_index pinecone.pinecone_create_index Write Create a new serverless vector index in Pinecone. Specify the index name, vector dimension, and similarity metric (cosine, euclidean, or dotproduct).
integration__pinecone__pinecone_upsert_vectors pinecone.pinecone_upsert_vectors Write Upsert vectors into a Pinecone index using an index host URL.
integration__pinecone__pinecone_query_vectors pinecone.pinecone_query_vectors Read Search for similar vectors in a Pinecone index using a query embedding.
integration__pinecone__pinecone_list_collections pinecone.pinecone_list_collections Read List all collections in your Pinecone project. Collections are static snapshots of indexes used for backups or creating new indexes.
integration__pinecone__pinecone_get_current_user pinecone.pinecone_get_current_user Read Get information about the currently authenticated Pinecone user, including email, name, and project details.

Related Pinecone Pages

Pinecone CLIUse direct JSON commands instead of MCP discovery. Pinecone MCPFull gateway reference and MCP tool names. KosmoKrator for Claude Agent SDKClient-level gateway setup.