
Lens Protocol MCP Server
Enables AI tools to interact with the Lens Protocol decentralized social network ecosystem. Supports fetching profiles, posts, followers, searching content, and accessing social graph data through standardized MCP interfaces.
README
Lens Protocol MCP Server
A Model Context Protocol (MCP) server that provides access to Lens Protocol data and functionality. This server enables AI tools to interact with the Lens Protocol ecosystem through standardized MCP interfaces.
Features
Tools (Actions)
- fetch_account - Fetch Lens Protocol account/profile by address
- fetch_posts - Fetch posts with optional filters (by author, pagination)
- fetch_followers - Get followers of a specific account
- fetch_following - Get accounts that a specific account follows
- search_accounts - Search for profiles (limited in public mode)
- search_posts - Search for posts (limited in public mode)
- fetch_apps - Fetch Lens Protocol applications
- fetch_groups - Fetch groups from the protocol
- fetch_usernames - Fetch username information
Resources (Data Access)
- lens://account/{address} - Account/profile information
- lens://post/{id} - Post/publication data
- lens://app/{address} - Application information
- lens://group/{address} - Group information
Installation
bun install
Usage
Starting the Server
Local (stdio) Mode
bun start
Remote HTTP Mode
bun start:http
# Or with custom port
PORT=8080 bun start:http
The server supports both stdio (for local use) and HTTP (for remote access) transports.
Configuration
Set environment variables:
LENS_ENVIRONMENT
: Set to "testnet" for testnet, defaults to mainnetPORT
: HTTP server port (default: 3000)
Example MCP Tool Calls
Fetch Account
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "fetch_account",
"arguments": {
"address": "0x1234567890123456789012345678901234567890"
}
}
}
Fetch Posts
{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/call",
"params": {
"name": "fetch_posts",
"arguments": {
"pageSize": 5,
"author": "0x1234567890123456789012345678901234567890"
}
}
}
Fetch Followers
{
"jsonrpc": "2.0",
"id": 3,
"method": "tools/call",
"params": {
"name": "fetch_followers",
"arguments": {
"account": "0x1234567890123456789012345678901234567890",
"pageSize": 10
}
}
}
MCP Client Configuration
Local Server Configuration
Add this server to your MCP client configuration:
{
"mcpServers": {
"lens-protocol": {
"command": "bun",
"args": ["index.ts"],
"cwd": "/path/to/lens-mcp"
}
}
}
Remote Server Configuration
For remote HTTP access:
{
"mcpServers": {
"lens-protocol-remote": {
"transport": {
"type": "http",
"url": "https://lens-mcp.lenscan.io/mcp"
}
}
}
}
Development
Running in Development Mode
# Stdio mode
bun dev
# HTTP mode
bun dev:http
Testing
# Run unit tests
bun test
# Run integration tests
bun test:integration
# Run all tests
bun test:all
Docker Deployment
# Build and run with Docker
docker build -f docker/Dockerfile -t lens-mcp .
docker run -p 3000:3000 lens-mcp
# Or use docker-compose
docker-compose -f docker/docker-compose.yml up
Architecture
The server is built using:
- @lens-protocol/client@canary - Official Lens Protocol TypeScript SDK
- @modelcontextprotocol/sdk - MCP server implementation
- Bun - Fast JavaScript runtime and package manager
Limitations
- Search functionality is limited in public client mode (requires authenticated session)
- Some advanced features require authentication which is not implemented in this server
- Rate limiting depends on Lens Protocol API limits
Contributing
- Fork the repository
- Create a feature branch
- Make changes
- Test with
bun test.ts
- Submit a pull request
License
MIT License
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.