Doctree MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 42 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.
Nothing serious here today
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.
Connect this server
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 -e 'DOCS_ROOT=<DOCS_ROOT>' -- npx -y doctree-mcp{
"mcpServers": {
"doctree-mcp": {
"command": "npx",
"args": [
"-y",
"doctree-mcp"
],
"env": {
"DOCS_ROOT": "<DOCS_ROOT>"
}
}
}
}[mcp_servers.doctree-mcp]
command = "npx"
args = ["-y", "doctree-mcp"]
env = { DOCS_ROOT = "<DOCS_ROOT>" }{
"mcpServers": {
"doctree-mcp": {
"command": "npx",
"args": [
"-y",
"doctree-mcp"
],
"env": {
"DOCS_ROOT": "<DOCS_ROOT>"
}
}
}
}{
"servers": {
"doctree-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"doctree-mcp"
],
"env": {
"DOCS_ROOT": "<DOCS_ROOT>"
}
}
}
}Put your own value in place of
<DOCS_ROOT> (Path to your markdown repository root).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
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)).
Alternatives to Doctree MCP
same job, measured the same wayLocal Markdown search, navigation and editing via MCP, with optional vector embeddings.
25 tools: LLM chat, summaries, translation, embeddings, speech, images. 25 free calls.
Everyday tools for AI agents, paid per call with x402: images, markdown, speech-to-text, embeddings.
Markdown-first long-term memory for AI agents. Hybrid BM25 + vector search, runs locally.
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.
Doctree MCP — questions
Answers built from our own checks of this server.