An MCP server implementation for retrieving information from Pinecone Assistant. - Retrieves information from Pinecone Assistant - Supports multiple results retrieval with a configurable number of results - Docker installed on your system - Pinecone API key - obtain from the Pinecone Console - Pinecone Assistant API host - after creating an Assistant (e.g. in Pinecone Console), you can find the ho
Add this skill
npx mdskills install pinecone-io/assistant-mcpWell-documented MCP server with clear setup instructions for both Docker and source builds
An MCP server implementation for retrieving information from Pinecone Assistant.
To build the Docker image:
docker build -t pinecone/assistant-mcp .
Run the server with your Pinecone API key:
docker run -i --rm \
-e PINECONE_API_KEY= \
-e PINECONE_ASSISTANT_HOST= \
pinecone/assistant-mcp
PINECONE_API_KEY (required): Your Pinecone API keyPINECONE_ASSISTANT_HOST (optional): Pinecone Assistant API host (default: https://prod-1-data.ke.pinecone.io)LOG_LEVEL (optional): Logging level (default: info)Add this to your claude_desktop_config.json:
{
"mcpServers": {
"pinecone-assistant": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"PINECONE_API_KEY",
"-e",
"PINECONE_ASSISTANT_HOST",
"pinecone/assistant-mcp"
],
"env": {
"PINECONE_API_KEY": "",
"PINECONE_ASSISTANT_HOST": ""
}
}
}
}
If you prefer to build from source without Docker:
cargo build --releasetarget/release/assistant-mcpexport PINECONE_API_KEY=
export PINECONE_ASSISTANT_HOST=
# Run the inspector alone
npx @modelcontextprotocol/inspector cargo run
# Or run with Docker directly through the inspector
npx @modelcontextprotocol/inspector -- docker run -i --rm -e PINECONE_API_KEY -e PINECONE_ASSISTANT_HOST pinecone/assistant-mcp
This project is licensed under the terms specified in the LICENSE file.
Install via CLI
npx mdskills install pinecone-io/assistant-mcpPinecone Assistant MCP Server is a free, open-source AI agent skill. An MCP server implementation for retrieving information from Pinecone Assistant. - Retrieves information from Pinecone Assistant - Supports multiple results retrieval with a configurable number of results - Docker installed on your system - Pinecone API key - obtain from the Pinecone Console - Pinecone Assistant API host - after creating an Assistant (e.g. in Pinecone Console), you can find the ho
Install Pinecone Assistant MCP Server with a single command:
npx mdskills install pinecone-io/assistant-mcpThis downloads the skill files into your project and your AI agent picks them up automatically.
Pinecone Assistant MCP Server works with Claude Code, Claude Desktop, Cursor, Vscode Copilot, Windsurf, Continue Dev, Gemini Cli, Amp, Roo Code, Goose. Skills use the open SKILL.md format which is compatible with any AI coding agent that reads markdown instructions.