Doclea MCP
A local MCP server providing persistent memory for AI coding assistants by storing and searching architectural decisions, patterns, and solutions. It also includes tools for git automation and mapping codebase expertise based on project history.
README
@doclea/mcp
Local MCP server for Doclea - persistent memory for AI coding assistants.
Installation
Prerequisites
Step 1: Clone and Build
git clone https://github.com/your-org/doclea.git
cd doclea/packages/doclea-mcp
# Install dependencies
bun install
# Download embedding model (first time only, ~130MB)
./scripts/setup-models.sh
# Build
bun run build
Step 2: Start Services
# Start Qdrant + Embeddings
bun run docker:up
# Verify services
curl http://localhost:6333/readyz # Should return "ok"
curl http://localhost:8080/health # Should return "ok"
Step 3: Add to Claude Code
Option A: Claude Code CLI (~/.claude.json or project .claude.json):
{
"mcpServers": {
"doclea": {
"command": "bun",
"args": ["run", "/absolute/path/to/doclea/packages/doclea-mcp/dist/index.js"]
}
}
}
Option B: Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"doclea": {
"command": "bun",
"args": ["run", "/absolute/path/to/doclea/packages/doclea-mcp/dist/index.js"]
}
}
}
Option C: For development (uses source directly):
{
"mcpServers": {
"doclea": {
"command": "bun",
"args": ["run", "/absolute/path/to/doclea/packages/doclea-mcp/src/index.ts"]
}
}
}
Step 4: Restart Claude Code
After updating config, restart Claude Code to load the MCP server.
Step 5: Initialize Your Project
In Claude Code, navigate to your project and ask:
Initialize doclea for this project
This scans your codebase, git history, and documentation to bootstrap memories.
Usage
Once installed, Claude Code automatically has access to these tools:
Store a Decision
Store this as a decision: We're using PostgreSQL because we need ACID
compliance for financial transactions. Tag it with "database" and "infrastructure".
Search for Context
Search memories for authentication patterns
Generate Commit Message
Generate a commit message for my staged changes
Generate PR Description
Create a PR description for this branch
Find Code Experts
Who should review changes to src/auth/?
Generate Changelog
Generate a changelog from v1.0.0 to HEAD for users
Configuration
Create .doclea/config.json in your project root (optional - uses defaults):
{
"embedding": {
"provider": "local",
"endpoint": "http://localhost:8080"
},
"qdrant": {
"url": "http://localhost:6333",
"collectionName": "doclea_memories"
},
"storage": {
"dbPath": ".doclea/local.db"
}
}
Embedding Providers
| Provider | Config |
|---|---|
| local (default) | { "provider": "local", "endpoint": "http://localhost:8080" } |
| openai | { "provider": "openai", "apiKey": "sk-...", "model": "text-embedding-3-small" } |
| nomic | { "provider": "nomic", "apiKey": "...", "model": "nomic-embed-text-v1.5" } |
| voyage | { "provider": "voyage", "apiKey": "...", "model": "voyage-3" } |
| ollama | { "provider": "ollama", "endpoint": "http://localhost:11434", "model": "nomic-embed-text" } |
MCP Tools Reference
Memory Tools
| Tool | Description |
|---|---|
doclea_store |
Store a memory (decision, solution, pattern, architecture, note) |
doclea_search |
Semantic search across memories |
doclea_get |
Get memory by ID |
doclea_update |
Update existing memory |
doclea_delete |
Delete memory |
Git Tools
| Tool | Description |
|---|---|
doclea_commit_message |
Generate conventional commit from staged changes |
doclea_pr_description |
Generate PR description with context |
doclea_changelog |
Generate changelog between refs (markdown/json, developers/users) |
Expertise Tools
| Tool | Description |
|---|---|
doclea_expertise |
Map codebase expertise, identify bus factor risks |
doclea_suggest_reviewers |
Suggest PR reviewers based on file ownership |
Bootstrap Tools
| Tool | Description |
|---|---|
doclea_init |
Initialize project, scan git history, docs, and code |
doclea_import |
Import from markdown files or ADRs |
Memory Types
- decision - Architectural decisions, technology choices
- solution - Bug fixes, problem resolutions
- pattern - Code patterns, conventions
- architecture - System design notes
- note - General documentation
Troubleshooting
Docker services not starting
# Check logs
docker compose -f docker-compose.test.yml logs
# Restart
bun run docker:down
bun run docker:up
First startup is slow
The embeddings service downloads the model (~130MB) on first run. After that, it's cached.
Port conflicts
Default ports: Qdrant (6333), Embeddings (8080). Edit docker-compose.test.yml to change.
MCP server not appearing in Claude
- Verify the path in config is absolute
- Check that
bun run buildcompleted successfully - Restart Claude Code completely
Development
# Run in development mode (hot reload)
bun run dev
# Run all tests
bun test
# Run unit tests only
bun run test:unit
# Run integration tests (requires Docker services)
bun run test:integration
# Type check
bun run typecheck
# Build for production
bun run build
Architecture
┌─────────────────────────────────────────────────────────┐
│ Claude Code │
│ ↓ MCP │
├─────────────────────────────────────────────────────────┤
│ Doclea MCP Server │
│ ┌─────────┐ ┌─────────┐ ┌──────────┐ ┌───────────┐ │
│ │ Memory │ │ Git │ │Expertise │ │ Bootstrap │ │
│ │ Tools │ │ Tools │ │ Tools │ │ Tools │ │
│ └────┬────┘ └────┬────┘ └────┬─────┘ └─────┬─────┘ │
│ └───────────┴───────────┴─────────────┘ │
│ ↓ │
│ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ │
│ │ SQLite │ │ Qdrant │ │ Embeddings │ │
│ │ (metadata) │ │ (vectors) │ │ (local/API) │ │
│ └──────────────┘ └──────────────┘ └──────────────┘ │
└─────────────────────────────────────────────────────────┘
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.