Connect Your Data with Pinecone
Copy page
Connect documents to your agents using Pinecone Assistant's MCP server
Pinecone is a vector database, and Pinecone Assistant helps you build production-grade chat and agent applications. Connect your documents and files to your agents using Pinecone Assistant's MCP server for semantic search and retrieval.
Supported data sources
With Pinecone Assistant you can connect:
- Documents: DOCX (.docx), PDF (.pdf), Text (.txt)
- Structured Data: JSON (.json)
- Documentation: Markdown (.md)
Getting started
Step 1: Create a Pinecone account
Step 2: Create an Assistant
- Log in to your Pinecone dashboard
- Navigate to the Assistant tab
- Click "Create an Assistant"
- Give your assistant a name
Step 3: Upload your files
- In your assistant, navigate to the Files tab (located in the top right corner)
- Upload your documents (DOCX, JSON, Markdown, PDF, or Text files)
- Wait for Pinecone to process and index your content
Test your assistant in the Assistant playground. Try uploading an Apple 10-K PDF file from Apple's investor relations page and ask it to summarize the document.
Step 4: Get your MCP server URL
- Navigate to the Settings tab in your assistant
- Copy the MCP URL provided
Step 5: Register the MCP server
Register the Pinecone MCP server as a tool in your agent configuration. Replace <your-mcp-url> with the MCP URL you copied in Step 4.
Using TypeScript SDK:
You can create your credential using keychain, nango, or environment variables, but in this example we use environment variables.
Using Visual Builder:
-
Add a Pinecone credential:
- Go to the Credentials tab in the Visual Builder
- Click "New credential"
- Select "Bearer authentication"
- Enter:
- Name:
Pinecone API Key(or your preferred name) - API key: Your Pinecone API key (found in your Pinecone dashboard)
- Name:
- Click "Create Credential" to save
-
Register the MCP server:
- Go to the MCP Servers tab in the Visual Builder
- Click "New MCP server"
- Select "Custom Server"
- Enter:
- Name:
Pinecone Documents - URL: Your MCP URL from Pinecone Settings tab
- Transport Type:
Streamable HTTP - Credential: Select the Pinecone credential you created
- Name:
- Click "Create" to save the server
-
Add the MCP tool to your sub agent:
- Drag the Pinecone Documents MCP tool onto your agent canvas and connect it to the sub agent
Step 6: Use the Pinecone Assistant MCP server in your agent
Once you have registered your MCP server as a tool and connected it to your agent, your agent can use the Pinecone Assistant tool to search and retrieve relevant content from your uploaded documents.
The Pinecone tool provides a get_context function that retrieves relevant document snippets from your knowledge base. When your agent calls this tool, it will:
Search semantically: Use vector similarity search to find the most relevant content based on the query
Return formatted snippets: Each result includes:
file_name: The name of the file containing the snippetpages: The page numbers where the snippet appears (for PDFs and DOCX files)content: The actual text content of the snippet
Parameters:
query(required): The search query to retrieve context fortop_k(optional): The number of context snippets to retrieve. Defaults to 15.