TxtAI Assistant MCP
by rmtech1
A Model Context Protocol (MCP) server implementation for semantic search and memory management using txtai. This server provides a robust API for storing, retrieving, and managing text-based memories with semantic search capabilities.
Last updated: N/A
What is TxtAI Assistant MCP?
TxtAI Assistant MCP is a server that extends the capabilities of txtai, an AI-powered search engine, by integrating it with the Model Context Protocol (MCP). It enables AI assistants like Claude and Cline to leverage txtai's powerful semantic search capabilities for memory management and context retrieval.
How to use TxtAI Assistant MCP?
To use TxtAI Assistant MCP, clone the repository, configure the environment variables, and run the start script. Then, configure Claude or Cline AI to use this server as an MCP server by adding the server configuration to their respective settings files. The AI assistants can then use the provided tools (store_memory, retrieve_memory, etc.) to interact with the server.
Key features of TxtAI Assistant MCP
Semantic search across stored memories
Persistent storage with file-based backend
Tag-based memory organization and retrieval
Memory statistics and health monitoring
Use cases of TxtAI Assistant MCP
Enhancing AI assistant capabilities with semantic memory
Providing context to AI models during conversations
Storing and retrieving important information for AI models
Organizing and managing memories with tags
FAQ from TxtAI Assistant MCP
What is txtai?
What is txtai?
txtai is an all-in-one semantic search solution built on neural search with transformers, providing zero-shot text classification, text extraction, embeddings, multi-language support, high performance and scalability.
What is MCP?
What is MCP?
MCP stands for Model Context Protocol. It allows AI models to interact with external tools and services, such as this txtai-assistant-mcp server, to enhance their capabilities.
How do I configure Claude or Cline to use this server?
How do I configure Claude or Cline to use this server?
Add the server configuration to Claude's MCP configuration file (claude_desktop_config.json) or Cline's MCP settings file (cline_mcp_settings.json), specifying the path to the start.sh script.
What are the available MCP tools?
What are the available MCP tools?
The available tools are store_memory, retrieve_memory, search_by_tag, delete_memory, get_stats, and check_health. Each tool has specific arguments as described in the README.
Where are the memories stored?
Where are the memories stored?
Memories and tags are stored in JSON files (memories.json and tags.json) in the data directory.