OpenZeppelin Docs MCP Server
Provides offline search and retrieval of OpenZeppelin Contracts documentation with fast full-text search. Enables querying contract APIs, functions, events, and guides for both v4.x and v5.x versions with NatSpec documentation extracted from Solidity source files.
README
OpenZeppelin Docs MCP Server
An MCP (Model Context Protocol) server that provides offline search and retrieval of OpenZeppelin Contracts documentation. Pre-indexes documentation at build time using SQLite with FTS5 for fast full-text search.
Features
- Offline capable - Works without internet after initial setup
- Fast lookups - Pre-built SQLite index with FTS5 full-text search
- Contract-aware - Understands Solidity structure (functions, events, modifiers, errors)
- Version aware - Supports OpenZeppelin Contracts v4.x and v5.x
- NatSpec extraction - Parses documentation directly from Solidity source files
Installation
Quick Install (GitHub)
claude mcp add --transport stdio openzeppelin-docs -- npx -y github:pbuda/openzeppelin-docs-mcp
The index will be built automatically on first run (~2-3 minutes).
Install from npm
claude mcp add --transport stdio openzeppelin-docs -- npx -y openzeppelin-docs-mcp
Verify Installation
# List configured servers
claude mcp list
# Check server status (inside Claude Code)
/mcp
Building from Source
If you want to build and run locally:
# Clone the repository
git clone https://github.com/pbuda/openzeppelin-docs-mcp.git
cd openzeppelin-docs-mcp
# Install dependencies
npm install
# Build the documentation index (fetches repos, ~2-3 min)
npm run build:index
# Build TypeScript
npm run build
Add Local Build to Claude Code
claude mcp add --transport stdio openzeppelin-docs -- node /absolute/path/to/openzeppelin-docs-mcp/dist/index.js
Or manually add to ~/.claude.json:
{
"mcpServers": {
"openzeppelin-docs": {
"command": "node",
"args": ["/absolute/path/to/openzeppelin-docs-mcp/dist/index.js"]
}
}
}
Testing with MCP Inspector
npx @modelcontextprotocol/inspector node dist/index.js
Available Tools
search_oz_docs
Search OpenZeppelin Contracts documentation for guides, API references, and code examples.
{
"query": "reentrancy guard",
"version": "5.x",
"category": "all",
"limit": 5
}
Parameters:
query(required) - Search query (e.g., "ERC20 approve", "access control roles")version-"4.x","5.x", or"all"(default:"5.x")category-"access","token","utils","governance","proxy","finance","metatx", or"all"limit- Max results (default: 5)
get_oz_contract
Get detailed API reference for a specific contract or library.
{
"name": "ERC20",
"version": "5.x"
}
Parameters:
name(required) - Contract or library name (e.g., "Ownable", "ECDSA", "SafeERC20")version-"4.x"or"5.x"(default:"5.x")
Returns: Contract metadata, inheritance chain, all functions/events/errors with signatures and NatSpec.
get_oz_function
Get detailed information about a specific function.
{
"function_name": "ECDSA.recover",
"version": "5.x"
}
Parameters:
function_name(required) - Function name, optionally with contract (e.g., "transfer", "ERC20.transferFrom")version-"4.x"or"5.x"(default:"5.x")
Returns: Function signature, parameters with types and descriptions, return values, NatSpec documentation.
list_oz_modules
List all available contracts and libraries, optionally filtered by category.
{
"category": "utils",
"version": "5.x"
}
Parameters:
category- Filter by category or"all"(default:"all")version-"4.x"or"5.x"(default:"5.x")
Returns: Organized list of all contracts/libraries grouped by category.
Development
# Run in development mode (with hot reload)
npm run dev
# Rebuild the index (skip fetching if repos exist)
npx tsx scripts/build-index.ts --skip-fetch
# Force re-clone repositories
npx tsx scripts/build-index.ts --force
Data Sources
The indexer fetches and parses:
- OpenZeppelin Docs - MDX documentation from github.com/OpenZeppelin/docs
- OpenZeppelin Contracts v5.3.0 - Solidity source with NatSpec comments
- OpenZeppelin Contracts v4.9.6 - Solidity source with NatSpec comments
Database Statistics
After indexing:
- ~927 documentation chunks from MDX files
- ~357 contracts (191 v5.x, 166 v4.x)
- ~3,067 members (functions, events, modifiers)
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.