1. Conduid
  2. RAG
  3. Docent MCP
MCP server · RAG

Docent MCP

· github.com/cuzfrog/docent-mcp

Semantic + BM25 Document + Git history search MCP server

Unclaimed aibm25decision-recordsembedding-modelsgit-historyhybrid-searchindexinglocal-aimcpmcp-serversearch-engine
InstallView source
34Low

Scored 5 months ago · breakdown

About Docent MCP

Docent MCP is an MCP server in the RAG category: semantic + BM25 Document + Git history search MCP server.

Install

From source
git clone https://github.com/cuzfrog/docent-mcp

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Docent MCP

Powered by Claude · Grounded in docs

I know everything about Docent MCP. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ✓README presentThe repository ships documentation.

5 checks have not been run yet.

README

docent

SafeSkill 92/100 Semantic + BM25 Document & Git history search for Design Decision Records — an MCP server that indexes documents and git history, letting agents query why code looks the way it does.

  files/git ──▼── index ──▶  MCP server  ◀──── query
                 (cache)        (HTTP)

Quick Start

docent init              # generate docent.toml config
docent index [path]      # index .md files + git history
docent serve             # start MCP server on port 7878

Open http://localhost:7878 for the built-in Web UI.

Usage

Command Description
docent init Generate a docent.toml config file
docent index [dir] Index both file and git sources (default: current dir)
docent index-file <path> Index specific files/directories
docent index-git <repo> Index git history from a repository
docent serve Start the MCP server (streamable HTTP)
docent list-models List supported embedding models

Flags: --config <path> (default ./docent.toml), --rebuild (full re-index), --verbose.

How It Works

  1. Sources — Reads markdown files and git commit history
  2. Section-aware chunking — Splits documents into chunks, preserving heading structure
  3. Embedding — Converts chunks to vectors via fastembed (configurable model)
  4. Index cache — Persists vectors and metadata to disk
  5. Semantic + BM25 search — Hybrid scoring with configurable algorithm
  6. MCP server — Exposes search_ddr tool over streamable HTTP

Install

TBC

Or build from source — see Development.

Documentation

README copy captured when this server was indexed; it may lag the repository. The original is authoritative.

Questions

About Docent MCP

How do I install Docent MCP?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Docent MCP safe to use with an AI agent?

Its trust score is 34 out of 100 (low). It passes 1 of the 1 static security checks run so far. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Docent MCP still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.