e2e-mcp-test
An end-to-end test MCP server built with FastMCP that exposes a REST API as a set of tools for AI agents. It enables LLMs to perform CRUD operations on an upstream API by mapping HTTP methods to MCP tools.
README
e2e-mcp-test
E2E test MCP server
Overview
This is a FastMCP server that exposes a REST API as a set of MCP (Model Context Protocol) tools. AI agents and LLMs can invoke these tools to interact with the upstream API.
Local Development
Prerequisites
- Python 3.11+
- The upstream API running at
http://localhost:8080
Setup
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
Run
python3 mcp_server.py
The server starts on http://0.0.0.0:8000/mcp using the
streamable HTTP transport.
Container Build
docker build -t e2e-mcp-test .
docker run -p 8000:8000 e2e-mcp-test
CI/CD with Pipelines as Code (Tekton)
This project uses Pipelines as Code (PAC) for fully automated CI/CD on
OpenShift. No manual setup is required -- every push to main automatically
builds the container image and deploys to OpenShift.
The pipeline definition lives in .tekton/push.yaml and performs:
- Clone -- fetches the repository source
- Build -- builds the container image with buildah and pushes to the OpenShift internal registry
- Deploy -- applies the deployment manifests and rolls out the new version
How It Works
A GitHub webhook (created automatically by the RHDH template) sends push events
to the Pipelines as Code controller on OpenShift. PAC reads .tekton/push.yaml
from the repo and creates a PipelineRun automatically.
Manual Deployment (without pipeline)
Apply the included manifests directly:
oc apply -f deploy/deployment.yaml
This creates a Deployment, Service, and Route in the mcp-servers
namespace. The Route provides a TLS-terminated public endpoint.
Customization
Edit mcp_server.py to replace the placeholder tools (list_items,
get_item, create_item) with tools that match your actual API endpoints.
Each @mcp.tool function maps to one REST endpoint:
| HTTP Method | MCP Tool Pattern |
|---|---|
| GET (list) | Tool that returns a list of resources |
| GET (by id) | Tool that returns a single resource |
| POST | Tool that creates a resource |
| PATCH / PUT | Tool that updates a resource |
| DELETE | Tool that removes a resource |
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.