Skip to main content
The Nexus MCP server lets any MCP client query your Nexus contexts over Streamable HTTP. It serves three read-only tools: list_contexts, query_context, and get_query.

Prerequisites

  • A Pinecone API key with access to your Nexus project. Create one in the Pinecone console.
  • The MCP endpoint, your deployment’s workspace host with the /mcp path (the base of nexus_default_workspace_data_console_url from the install output).
  • Node.js, so the mcp-remote bridge can run through npx.

Add the server config

Add the config below to your MCP client, replacing YOUR_WORKSPACE_HOST and YOUR_PINECONE_API_KEY with your own values. The server authenticates each request with the key you pass, so every caller queries their own project. The mcp-remote bridge lets clients that only launch local stdio servers reach the remote HTTP endpoint.

Tools

  • list_contexts: List the contexts available to your project (each has a slug). Takes no arguments and returns an array of context objects, each shaped { slug, name, id, description, queryable, is_curating, is_optimizing, last_curated_at, last_optimized_at }. queryable turns true once the context has been optimized, is_curating and is_optimizing flag whether work is running now, and the two timestamps are ISO strings or null.
  • query_context: Submit a question scoped to one context. Args: context (slug), question. Runs in background mode and returns a query_id immediately without waiting for the answer. The return object is { query_id, status, model }. Pass the query_id to get_query to fetch the result.
  • get_query: Poll the result of a submitted query. Args: query_id. Returns { query_id, answer, output_json, citations, model, status, error }. answer is the grounded answer text, or null until it’s ready. output_json holds structured output when the query requested a shape, otherwise null. citations is an array of source references and error is set only when the query failed. Keep polling until status is completed, failed, or cancelled.