A Model Context Protocol (MCP) server implementation powered by txtai, providing semantic search, knowledge graph capabilities, and AI-driven text
A Model Context Protocol (MCP) server implementation powered by txtai, providing semantic search, knowledge graph capabilities, and AI-driven text processing
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"kb-server": {
"command": "uvx",
"args": [
"kb-mcp-server@0.2.6",
"--embeddings", "/path/to/knowledge_base",
"--host", "localhost",
"--port", "8000"
],
"cwd": "/path/to/working/directory"
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| TXTAI_EMBEDDINGS | Configuration value read at startup. | Optional |
| MCP_SSE_HOST | Endpoint or connection string the server talks to. | Optional |
| MCP_SSE_PORT | Configuration value read at startup. | Optional |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Deterministic contract checks — defined terms, cross-references, drafting issues — inside your AI chat.
Event-sourced knowledge graph memory for AI coding agents with semantic search
A MCP server that uses Logseq API to extract and interact with Logseq notes.
A persistent, human‑like memory system for AI companions