vectara-mcp
Vectara's MCP server for RAG-powered AI interactions. vectara-mcp is a Model Context Protocol (MCP) server maintained by vectara. It connects to MCP-compatible clients such as Claude Desktop, Cursor, Cline, and other agents that speak the protocol. It exposes 2 tools, including ask_vectara and search_vectara, that an agent can call directly. It is categorized under AI/RAG, Tool/Server and AI/Integration.
What is this MCP
Vectara-MCP is a server implementation of the Model Context Protocol (MCP) that provides AI systems with secure access to Vectara's Trusted RAG platform for reduced-hallucination retrieval-augmented generation.
How to use this MCP
Configure the MCP server in Claude Desktop by adding it to claude_desktop_config.json, then use tools likeask-vectara and search-vectara with required parameters (API key, corpus keys) for RAG queries.
What this MCP can be used for
Enabling AI agents to perform reliable semantic search and RAG queries against Vectara corpora, with features like answer generation, context window control, and multilingual support.
AIMCP authority
DR and traffic signal for the AIMCP public domain.
Frequently asked questions
What is the vectara-mcp MCP server?
vectara-mcp is a Model Context Protocol server from vectara. It lets MCP-compatible AI clients call its tools over a standard interface, so agents like Claude, Cursor, and Cline can use it without custom integration.
How do I connect vectara-mcp to my AI client?
Add vectara-mcp to your client's MCP configuration using the stdio or SSE connection shown in the usage examples on this page, then restart the client to load the server.
What tools does vectara-mcp provide?
vectara-mcp provides 2 tools: ask_vectara and search_vectara.
Is vectara-mcp free to use?
vectara-mcp is listed on AIMCP for free. Any API keys or accounts required by the underlying service are set by its provider.
Vernclaw Plugins for OpenClaw
Ready-to-use connectors for SEO data, social reading & content generation. Pay-as-you-go credits with audit logs.