Overview

The MCP Txtai Server enables AI models to interact with Txtai, an AI-powered search engine that builds vector indexes (also known as embeddings) to perform similarity searches. Txtai is widely used for semantic search, retrieval-augmented generation (RAG), and building intelligent applications.

Community Server:

Developed and maintained by rmtech1

Key Features

⚡

Semantic Search

Perform semantic search across stored memories

🔑

Persistent Storage

Persistent storage with file-based backend

⏰

Tag-based Memory

Tag-based memory organization and retrieval

💾

Claude and Cline AI Integration

Integration with Claude and Cline AI

Available Tools

Quick Reference

Tool	Purpose	Category
`store_memory`	Store new memory content	Write
`retrieve_memory`	Retrieve memories based on semantic search	Read
`search_by_tag`	Search memories by tags	Read
`delete_memory`	Delete a specific memory	Write
`get_stats`	Get database statistics	Discovery
`check_health`	Check database and embedding model health	Discovery

Detailed Usage

store_memory▶

Store new memory content with metadata and tags.

use_mcp_tool({
  server_name: "txtai-assistant",
  tool_name: "store_memory",
  arguments: {
    content: "Important information to remember",
    tags: ["important"]
  }
});

Returns a confirmation message.

retrieve_memory▶

Retrieve memories based on semantic search.

use_mcp_tool({
  server_name: "txtai-assistant",
  tool_name: "retrieve_memory",
  arguments: {
    query: "what was the important information?",
    n_results": 5
  }
});

Returns a list of matching memories.

search_by_tag▶

Search memories by tags.

use_mcp_tool({
  server_name: "txtai-assistant",
  tool_name: "search_by_tag",
  arguments: {
    tags: ["important", "context"]
  }
});

Returns a list of matching memories.

delete_memory▶

Delete a specific memory by content hash.

use_mcp_tool({
  server_name: "txtai-assistant",
  tool_name: "delete_memory",
  arguments: {
    content_hash: "hash_value"
  }
});

Returns a confirmation message.

get_stats▶

Get database statistics.

use_mcp_tool({
  server_name: "txtai-assistant",
  tool_name: "get_stats",
  arguments: {}
});

Returns database statistics.

check_health▶

Check database and embedding model health.

use_mcp_tool({
  server_name: "txtai-assistant",
  tool_name: "check_health",
  arguments: {}
});

Returns the health status of the server.

Installation

{
  "mcpServers": {
    "txtai-assistant": {
      "command": "path/to/txtai-assistant-mcp/scripts/start.sh",
      "env": {}
    }
  }
}

Custom Connection:

The server can be configured using environment variables in the .env file.

Common Use Cases

1. Store and retrieve memories

Store and retrieve memories based on semantic search:

// Store a memory
use_mcp_tool({
  server_name: "txtai-assistant",
  tool_name: "store_memory",
  arguments: {
    content: "Important information to remember",
    tags: ["important"]
  }
});

// Retrieve memories
use_mcp_tool({
  server_name: "txtai-assistant",
  tool_name: "retrieve_memory",
  arguments: {
    query: "what was the important information?",
    n_results": 5
  }
});

2. Search by tags

Search memories by tags:

use_mcp_tool({
  server_name: "txtai-assistant",
  tool_name: "search_by_tag",
  arguments: {
    tags: ["important", "context"]
  }
});

Sources

Confluence MCP Server

Confluence MCP servers provide interfaces for LLMs to interact with Atlassian Confluence workspaces. These servers enable AI models to manage documentation, collaborate on content, and automate knowledge management tasks.

Ollama Deep Researcher: AI Model for Web Search & LLM Synthesis

Ollama Deep Researcher MCP servers enable AI models to perform advanced topic research using web search and LLM synthesis, powered by a local MCP server.

Salesforce DX MCP Server

Salesforce DX MCP servers enable AI models to interact with Salesforce instances, providing capabilities for managing orgs, metadata, data, and users.

Txtai MCP Server