Vectara

What is Vectara-MCP?

Vectara-MCP is an open-source server that enables AI systems to interact seamlessly with Vectara's RAG-as-a-service platform via the Model Context Protocol (MCP). It provides fast, reliable RAG (Retrieval Augmented Generation) with reduced hallucination, leveraging Vectara's trusted RAG capabilities.

How to use Vectara-MCP?

To use Vectara-MCP, you first need to install it via pip:

pip install vectara-mcp

After installation, you can configure it with MCP clients like Claude Desktop by adding a specific JSON configuration to your claude_desktop_config.json file. Once configured and the Claude Desktop app is restarted, the Vectara-MCP server will be accessible, indicated by a hammer icon.

Key Features of Vectara-MCP

ask_vectara tool: Allows running RAG queries using Vectara, returning search results with a generated response. It supports various arguments like query, corpus_keys, api_key, and optional parameters for context and generation.
search_vectara tool: Enables running semantic search queries using Vectara without generation, returning only the matching search results.
MCP Compatibility: Fully compatible with any MCP client, including Claude Desktop, facilitating secure, two-way connections with AI systems.
Reduced Hallucination: Leverages Vectara's Trusted RAG platform to provide more accurate and reliable responses.

Use Cases of Vectara-MCP

Integrating RAG into AI Agents: Developers can easily integrate powerful RAG capabilities into their AI applications and agents.
Enhanced Question Answering: Provides a robust solution for answering complex questions by retrieving relevant information and generating concise responses.
Semantic Search: Enables precise semantic searches across various data sources powered by Vectara.
Building Custom AI Applications: Serves as a foundation for building custom AI applications that require reliable information retrieval and generation.

FAQ from Vectara-MCP

What is MCP? The Model Context Protocol (MCP) is an open standard that enables AI systems to interact seamlessly with various data sources and tools, facilitating secure, two-way connections.
What information do I need to provide to use Vectara-MCP? When you first use the tools, Claude (or your MCP client) will ask for your Vectara API key and corpus key(s).
Can I use multiple corpora? Yes, you can provide multiple corpus keys to search across different datasets.
Is Vectara-MCP compatible with other MCP clients? Yes, it is compatible with any MCP client.

Vectara MCP Server

PyPI version License

🔌 Compatible with Claude Desktop, and any other MCP Client!

Vectara MCP is also compatible with any MCP client

The Model Context Protocol (MCP) is an open standard that enables AI systems to interact seamlessly with various data sources and tools, facilitating secure, two-way connections.

Vectara-MCP provides any agentic application with access to fast, reliable RAG with reduced hallucination, powered by Vectara's Trusted RAG platform, through the MCP protocol.

Installation

You can install the package directly from PyPI:

pip install vectara-mcp

Available Tools

ask_vectara: Run a RAG query using Vectara, returning search results with a generated response.

Args:
- query: str, The user query to run - required.
- corpus_keys: list[str], List of Vectara corpus keys to use for the search - required. Please ask the user to provide one or more corpus keys.
- api_key: str, The Vectara API key - required.
- n_sentences_before: int, Number of sentences before the answer to include in the context - optional, default is 2.
- n_sentences_after: int, Number of sentences after the answer to include in the context - optional, default is 2.
- lexical_interpolation: float, The amount of lexical interpolation to use - optional, default is 0.005.
- max_used_search_results: int, The maximum number of search results to use - optional, default is 10.
- generation_preset_name: str, The name of the generation preset to use - optional, default is "vectara-summary-table-md-query-ext-jan-2025-gpt-4o".
- response_language: str, The language of the response - optional, default is "eng".
Returns:
- The response from Vectara, including the generated answer and the search results.
search_vectara: Run a semantic search query using Vectara, without generation.

Args:
- query: str, The user query to run - required.
- corpus_keys: list[str], List of Vectara corpus keys to use for the search - required. Please ask the user to provide one or more corpus keys.
- api_key: str, The Vectara API key - required.
- n_sentences_before: int, Number of sentences before the answer to include in the context - optional, default is 2.
- n_sentences_after: int, Number of sentences after the answer to include in the context - optional, default is 2.
- lexical_interpolation: float, The amount of lexical interpolation to use - optional, default is 0.005.
Returns:
- The response from Vectara, including the matching search results.

Configuration with Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "Vectara": {
      "command": "uv",
      "args": [
        "tool",
        "run",
        "vectara-mcp"
      ]
    }
  }
}

Usage in Claude Desktop App

Once the installation is complete, and the Claude desktop app is configured, you must completely close and re-open the Claude desktop app to see the Vectara-mcp server. You should see a hammer icon in the bottom left of the app, indicating available MCP tools, you can click on the hammer icon to see more detial on the Vectara-search and Vectara-extract tools.

Now claude will have complete access to the Vectara-mcp server, including the ask-vectara and search-vectara tools. When you issue the tools for the first time, Claude will ask you for your Vectara api key and corpus key (or keys if you want to use multiple corpora). After you set those, you will be ready to go. Here are some examples you can try (with the Vectara corpus that includes information from our website:

Vectara RAG Examples

Querying Vectara corpus:

ask-vectara Who is Amr Awadallah?

Searching Vectara corpus:

search-vectara events in NYC?

Acknowledgments ✨

Model Context Protocol for the MCP specification
Anthropic for Claude Desktop

Vectara Overview