Doctree MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 24 installs a week from npm. Last commit 12 Jun 2026.
BM25 search + tree navigation over markdown docs for AI agents. No embeddings, no LLM calls.
Today is the operative word: we check Doctree MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add doctree-mcp -- npx -y doctree-mcp
{
"mcpServers": {
"doctree-mcp": {
"args": [
"-y",
"doctree-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.doctree-mcp]
command = "npx"
args = ["-y", "doctree-mcp"]
{
"mcpServers": {
"doctree-mcp": {
"args": [
"-y",
"doctree-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"doctree-mcp": {
"args": [
"-y",
"doctree-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
DOCS_ROOT (Path to your markdown repository root), DOCS_GLOB (Glob pattern for finding markdown files (default: **/*.md)), DOCS_ROOTS (Multiple weighted collections: ./docs:1.0,./api:0.8 (alternative to DOCS_ROOT)), GLOSSARY_PATH (Path to glossary.json for query expansion (default: $DOCS_ROOT/glossary.json)).
The author declared them in the registry entry; get the values from the project itself.
Managed Apache Solr for agents: hybrid BM25+kNN search, server-side embeddings, RAG answers
Persistent memory for AI agents — semantic + recency search, ONNX embeddings, Docker Compose.
RAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.
Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.
MCP server for GigaChat — AI chat, embeddings, image generation (Russia)
MCP server for the xAI Grok API — chat, vision, search, and embeddings
35 AI tools for image/video generation, TTS, transcription, OCR & embeddings via deAPI
Semantic code search for AI agents — hybrid BM25+vector, call-graph, 20+ languages.
Answers built from our own checks of this server.