What is Vectra Mcp

Vectra MCP is a Model Context Protocol server designed for interacting with a Vectra knowledge base. It is built using TypeScript and provides tools for managing and querying Vectra instances, facilitating integration with MCP-compatible clients.

Use cases

Use cases for Vectra MCP include creating a centralized knowledge repository, embedding research papers and documents for easy retrieval, querying specific information from collections, and managing large datasets effectively.

How to use

To use Vectra MCP, you can interact with its various tools through API calls. These tools allow you to create collections, embed texts and files, query collections, and manage files within the Vectra knowledge base.

Key features

Key features of Vectra MCP include the ability to create and list collections, embed texts and files in batch, query collections with hybrid search capabilities, and manage files within specific collections.

Where to use

Vectra MCP can be used in fields that require knowledge management, data integration, and information retrieval, such as research institutions, educational organizations, and enterprises that utilize knowledge bases.

Vectra MCP Server

A Model Context Protocol (MCP) server for interacting with a Vectra knowledge base.

This TypeScript-based MCP server provides tools to manage and query a Vectra instance, enabling integration with MCP-compatible clients. It interacts with a backend Vectra API (presumably running separately).

Features

Tools

This server exposes the following tools for interacting with Vectra:

• create_collection: Create a new Vectra collection.
  • Input: name (string, required), description (string, optional)
• list_collections: List existing Vectra collections.
  • Input: None
• embed_texts: Embeds multiple text items in batch into Vectra.
  • Input: items (array of objects with text (required) and optional metadata), collectionId (string, optional)
• embed_files: Reads multiple local files and embeds their content into Vectra.
  • Input: sources (array of local file paths, required), collectionId (string, optional), metadata (object, optional - applies to all items)
• add_file_to_collection: Add an already embedded file (referenced by its ID) to a specific Vectra collection.
  • Input: collectionId (string, required), fileId (string, required)
• list_files_in_collection: List files within a specific Vectra collection.
  • Input: collectionId (string, required)
• query_collection: Query the knowledge base within a specific Vectra collection.
  • Note: This tool always uses hybrid search (vector + keyword) and enables graph search enhancement by default.
  • Input: collectionId (string, required), queryText (string, required), limit (number, optional), maxDistance (number, optional), graphDepth (number, optional), graphRelationshipTypes (array of strings, optional), includeMetadataFilters (array of objects, optional), excludeMetadataFilters (array of objects, optional)
• delete_file: Delete a file and its associated embeddings from Vectra.
  • Input: fileId (string, required)
• get_arangodb_node: Fetch a specific node directly from the underlying ArangoDB database by its key.
  • Input: nodeKey (string, required - e.g., chunk_xyz or doc_abc)

(Refer to src/tools.ts for detailed input schemas)

Development

Install dependencies:

npm install

Build the server:

npm run build

Run the server (listens on stdio):

node build/index.js

For development with auto-rebuild:

npm run watch