API-MARKET MCP Server
Exposes API-Market's endpoints as MCP resources, requiring an API key for access.
API-MARKET MCP Server
About
A Model Context Protocol (MCP) server that exposes API-Market's endpoints as MCP resources. This server allows Large Language Models to discover and interact with APIs defined by OpenAPI specifications through the MCP protocol.
This repository provides access to the APIs available at API.market. The tool is free to use and allows agents to communicate freely with all available APIs, making it super powerful. With over 200+ APIs available at API.market, you can leverage a wide range of functionalities.
Quick Start
You do not need to clone this repository to use this MCP server. You can simply configure it in your client of choice.
For Claude Desktop
- Locate or create your Claude Desktop configuration file:
- On macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- On macOS:
- Add the following configuration to enable the API-Market MCP server:
{ "mcpServers": { "api-market": { "command": "npx", "args": ["-y", "@noveum-ai/mcp-server"], "env": { "API_HEADERS": "x-magicapi-key:your-api-key" } } } }
For Cursor
- Go to File -> Preferences -> Cursor Settings.
- Select MCP.
- Click on Add new global MCP Server.
- Paste the following into the mcp.json file.
{
"mcpServers": {
"api-market": {
"command": "npx",
"args": [
"-y",
"@noveum-ai/mcp-server",
"--headers",
"x-magicapi-key:<your-api-key>"
]
}
}
}
Alternatively, add this as the first entry in mcpServers.
"api-market": {
"command": "npx",
"args": [
"-y",
"@noveum-ai/mcp-server",
"--headers",
"x-magicapi-key:<your-api-key>"
]
},
- For older versions of Cursor, add the following command after clicking on Add new MCP server
npx -y @noveum-ai/mcp-server --headers x-magicapi-key:your-api-key
Getting an API Key from API.market
To obtain an API key
- Log in to API.market
- Go to your profile and select 'My API Keys'
- Your API keys will be displayed here
List of APIs in this MCP
- GET-trueway-matrix-MatrixService-CalculateDrivingMatrix
- GET-magicapi-whisper-predictions--request_id
- POST-magicapi-whisper-whisper
- POST-capix-faceswap-upload
- POST-capix-faceswap-faceswap-v1-image
- POST-capix-faceswap-faceswap-v1-video
- POST-capix-faceswap-result
- GET-trueway-geocoding-GeocodingService-Geocode
- GET-trueway-geocoding-GeocodingService-ReverseGeocode
- POST-magicapi-dnschecker-dnschecker
- GET-magicapi-coder-predictions--request_id
- POST-magicapi-coder-coder
- POST-bridgeml-nsfw-detection-nsfw_detection
- GET-magicapi-whois-whois--domain-
- GET-magicapi-deblurer-predictions--request_id
- POST-magicapi-deblurer-deblurer
- POST-bridgeml-text-to-image-text_to_image
- GET-magicapi-period-predictions--request_id
- POST-magicapi-period-period
- GET-trueway-places-PlacesService-FindPlaceByText
- GET-trueway-places-PlacesService-FindPlacesNearby
- GET-magicapi-hair-predictions--request_id
- POST-magicapi-hair-hair
- POST-bridgeml-codellama-bridgeml-codellama
- GET-brave-brave-videos-search
- GET-brave-brave-web-search
- GET-brave-brave-images-search
- GET-brave-brave-news-search
- GET-brave-brave-suggest-search
- GET-brave-brave-spellcheck-search
- POST-magicapi-domainchecker-check_domains
- GET-trueway-routing-DirectionsService-FindDrivingRoute
- GET-trueway-routing-DirectionsService-FindDrivingPath
- POST-pipfeed-parse-extract
Example and Usage
Example 1
We can use the agent to find a route between any two points

Example 2
We can use the agent to find news about any topic, and then dig deeper into the articles

Example 3
We can use the agent to look for available domains

Development
Adding a New API to the MCP Server
The utils folder contains helper scripts for managing API configurations, parsing OpenAPI specifications, and registering new APIs into the MCP server.
1. Locate the OpenAPI Specification
Find the OpenAPI JSON for the API you want to integrate. After that, create a folder json_files in the root directory of the project and add your OpenAPI JSON spec to the folder
2. Modify the OpenAPI Specification
After obtaining the OpenAPI spec, use modify_api.py to update the path inside the spec to include the file name.
python utils/modify_api.py
3. Update API Summaries
After modifying the paths, update the API summaries by choosing one of the following options:
- Automatically shorten summaries using an LLM:
python utils/LLM_summary_shortener.py
- Manually update the summaries:
python utils/manual_summary_shortener.py
4. Build and Test
Rebuild the project to apply the changes:
npm run build
Then, test the new API integration using:
npm run inspect
5. Submit Your Changes
If you want to contribute this new API to the repository:
- Fork the repo.
- Create a branch.
- Submit a pull request (PR).
6. Publish the MCP server (Optional)
If you want to publish your changes:
- Update the
package.jsonaccordingly (e.g., update the version, name, etc.). - Publish the package:
npm publish --access public
Development Tools
Building
npm run build- Builds the TypeScript source.npm run clean- Removes build artifacts.npm run typecheck- Runs TypeScript type checking.
Development Mode
npm run dev- Watches source files and rebuilds on changes.npm run inspect-watch- Runs the inspector with auto-reload on changes.
Code Quality
npm run lint- Runs ESLint.npm run typecheck- Verifies TypeScript types.
Command Line Arguments
npm run inspect -- \
--api-base-url https://api.magicapi.dev/api/v1/ \
--openapi-spec modified_files.txt \
--headers "x-magicapi-key:your-api-key" \
--name "my-mcp-server" \
--version "1.0.0"
Development Workflow
- Start the development environment:
npm run inspect-watch
- Modify the TypeScript files in
src/. - The server will automatically rebuild and restart.
- Use the MCP Inspector UI to test your changes.
Debugging or Running Locally
To debug or run the MCP server locally:
- Clone the repository and install dependencies:
git clone https://github.com/Noveum/api-market-mcp-server.git
cd api-market-mcp-server
npm install
- Build the server:
npm run build
- For debugging, you can run:
npm run inspect
Contributing
- Fork the repository.
- Create a feature branch.
- Make your changes.
- Run tests and linting:
npm run typecheck
npm run lint
- Submit a pull request.
License
MIT
Verwandte Server
Typecast API
An MCP server for the Typecast API, enabling AI-powered voice generation for various content.
Remote MCP Server (Authless)
A remote, auth-less MCP server deployable on Cloudflare Workers or locally via npm.
Qovery
An MCP server for Qovery AI Copilot that enables deploying apps and managing Kubernetes on AWS, GCP, Azure, and On-Premise infrastructure with natural language
Shopify MCP Server
Interact with Shopify store data using the GraphQL API.
Meta Marketing API MCP Server
Interact with Facebook and Instagram advertising data using the Meta Marketing API.
Freshservice
Interact with Freshservice modules for IT service management operations.
Check Point Quantum Management
Exposes Check Point security management data for AI-powered automation and analysis.
DoorDash MCP Server
An MCP server that bridges the DoorDash Drive API with MCP-compatible clients.
Minibridge
A backend-to-frontend bridge that securely exposes MCP servers to the internet, supporting agent authentication, content analysis, transformation, and telemetry.
VixMCP.Ai.Bridge
An MCP server that exposes VMware VIX operations for AI assistants and automation workflows.