mock-mcp
A minimal local HTTP MCP mock server for development and testing, providing predictable tool responses with OAuth token support and zero dependencies.
README
mock-mcp-local
Minimal local HTTP MCP mock server for development integration.
Why this exists
- fast local connector testing
- zero dependencies and setup
- deterministic tool responses for dev and demos
Requirements
- Node.js 18+
Run
npm start
Defaults:
- host:
0.0.0.0 - port:
8787 - MCP endpoint:
http://localhost:8787/mcp - OAuth token endpoint:
http://localhost:8787/oauth/token
Optional overrides:
HOST=0.0.0.0 PORT=8787 npm start
Code structure
server.mjs: HTTP bootstrap and route wiringsrc/config.mjs: environment-driven config and client loadingsrc/http.mjs: shared HTTP/response/body parsing helperssrc/auth.mjs: token issuing + Bearer validationsrc/tools.mjs: mock tool catalog + implementationssrc/rpc.mjs: MCP JSON-RPC dispatcher + cancellation handling
Health check
GET /health
Example:
curl http://127.0.0.1:8787/health
MCP methods supported
initializenotifications/initializedtools/listtools/call$/cancelRequestnotifications/cancelledresources/list(returns empty)prompts/list(returns empty)
Auth flow
POST /mcp requires Authorization: Bearer <access_token>.
Get token first (client credentials):
curl -X POST http://localhost:8787/oauth/token ^
-H "Content-Type: application/x-www-form-urlencoded" ^
-d "grant_type=client_credentials&client_id=demo-client&client_secret=demo-secret&scope=crm.read%20crm.write%20crm.enrich"
Tools exposed
crm.search_contacts- input:
{ "query": "alice" }
- input:
crm.create_deal- input:
{ "title": "Pilot", "amount": 25000, "contactId": "c_1001" }
- input:
Quick test payloads
Initialize:
curl -X POST http://127.0.0.1:8787/mcp ^
-H "Authorization: Bearer <access_token>" ^
-H "Content-Type: application/json" ^
-d "{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"initialize\",\"params\":{}}"
List tools:
curl -X POST http://127.0.0.1:8787/mcp ^
-H "Authorization: Bearer <access_token>" ^
-H "Content-Type: application/json" ^
-d "{\"jsonrpc\":\"2.0\",\"id\":2,\"method\":\"tools/list\",\"params\":{}}"
Call crm.search_contacts:
curl -X POST http://127.0.0.1:8787/mcp ^
-H "Authorization: Bearer <access_token>" ^
-H "Content-Type: application/json" ^
-d "{\"jsonrpc\":\"2.0\",\"id\":3,\"method\":\"tools/call\",\"params\":{\"name\":\"crm.search_contacts\",\"arguments\":{\"query\":\"alice\"}}}"
Cancel a running request:
curl -X POST http://127.0.0.1:8787/mcp ^
-H "Authorization: Bearer <access_token>" ^
-H "Content-Type: application/json" ^
-d "{\"jsonrpc\":\"2.0\",\"id\":99,\"method\":\"$/cancelRequest\",\"params\":{\"requestId\":3,\"reason\":\"user aborted\"}}"
Connector UI values (tfGPT Desktop)
- type:
mcp - transport:
http - server_url:
http://127.0.0.1:8787/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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.