Merkl MCP Server
MCP server providing tools to search, get, and aggregate Merkl opportunities. Enables querying campaign data, APRs, TVL, and more through natural language.
README
Merkl MCP Server
An MCP server exposing Merkl Opportunities endpoints using @modelcontextprotocol/sdk.
Setup
- Node.js 18+ recommended
- Install deps
npm install
Optionally set environment variables:
MERKL_BASE_URL(default: https://api.merkl.xyz)MERKL_API_KEY(Bearer token if you have one; public endpoints work without it)
Run (local)
- Dev server:
npm run dev
- Start once:
npm run build
npm start
- Smoke test (direct HTTP call, not MCP):
npm run smoke
Tools exposed
- opportunities-search
- opportunities-get
- opportunities-campaigns
- opportunities-count
- opportunities-bins-apr
- opportunities-bins-tvl
- opportunities-aggregate
- opportunities-aggregate-max
- opportunities-aggregate-min
Use with an MCP-compatible client
This server uses the stdio transport. Point your MCP client to run the command and read/write on stdio:
- Command:
npx merkl-mcp
- Or locally via repo:
npm start
Set env vars as needed (e.g. MERKL_API_KEY). The server will register tools listed above.
Note: Requires Node 18+. Enable debug logs by setting MERKL_DEBUG=1.
One-line npx startup
After publishing as merkl-mcp to npm (or using npm link), you can start the server with:
npx merkl-mcp
If dist/server.js is missing, the CLI will build automatically on first run.
Connect to Claude Desktop (macOS)
Claude Desktop supports MCP over stdio. Add this server to Claude's config and restart the app.
- Create or edit config file
- Path:
~/Library/Application Support/Claude/claude_desktop_config.json
- Use the published package (one-line npx)
{
"mcpServers": {
"merkl": {
"command": "npx",
"args": ["-y", "merkl-mcp"],
"env": {
"MERKL_API_KEY": "(Optional) YOUR_API_KEY_OR_REMOVE_IF_UNUSED"
}
}
}
}
- Or run from local repo
{
"mcpServers": {
"merkl": {
"command": "node",
"args": ["dist/src/server.js"],
"cwd": "./merkl-mcp",
"env": {
"MERKL_API_KEY": "(Optional) YOUR_API_KEY_OR_REMOVE_IF_UNUSED"
}
}
}
}
- Restart Claude Desktop
- Start a new chat; the tool named
merklshould appear in the Tools list.
Troubleshooting
- Ensure Node.js 18+ is installed and available to Claude's environment.
- Remove
MERKL_API_KEYif you don't have one; public endpoints work without it. - Check Claude logs if tools don't appear; verify the config file path and JSON syntax.
Publish to npm
Set the name in package.json (already set up for you via bin aliases) and publish:
npm login # if not already
npm publish --access public
Then users can run:
npx merkl-mcp
# or the short alias
npx merkl-mcp
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.