logo
Free, unlimited AI code reviews that run on commit
git-lrc git-lrc GitHub Install Now We'd appreciate a star git-lrc - Free, unlimited AI code reviews that run on commit | Product Hunt git-lrc - Free, unlimited AI code reviews that run on commit | Product Hunt

api-market-mcp-gateway

Facilitates agent interaction with an extensive catalog of over 40 distinct APIs and sophisticated AI models, all exposed via OpenAPI definitions. This component bridges communication pathways between intelligent agents and the diverse tool ecosystem hosted on API.market.

Author

api-market-mcp-gateway logo

Noveum

MIT License

Quick Info

GitHub GitHub Stars 3
NPM Weekly Downloads 0
Tools 1
Last Updated 2026-02-19

Tags

apisopenapiapinoveum apiapi marketservices noveum

API-MARKET Unified Service Endpoint (MCP Gateway)

Overview

This implementation serves as a Model Context Protocol (MCP) server, effectively wrapping the diverse endpoints from API.Market into consumable MCP resources. It empowers Large Language Models (LLMs) to seamlessly discover and invoke external services described by their OpenAPI schemas using the standardized MCP framework.

Access to the comprehensive suite of tools located at API.market is granted through this tool. Agents can engage with the substantial collection of over 200 unique APIs available on the platform without restriction, maximizing operational utility. The service itself is provided at no cost for utilization.

Deployment Instructions

It is unnecessary to clone or maintain this repository for operational use. Configuration should be applied directly within your preferred client environment.

Configuring for Claude Desktop

  1. Navigate to or establish the Claude Desktop configuration file, typically found at:
  2. macOS location: ~/Library/Application Support/Claude/claude_desktop_config.json
  3. Integrate the following JSON stanza into the mcpServers block to activate the API-Market gateway:

{ "mcpServers": { "api-market": { "command": "npx", "args": ["-y", "@noveum-ai/mcp-server"], "env": { "API_HEADERS": "x-magicapi-key:your-api-key" } } } }

Configuring for Cursor IDE

  1. Access the settings menu: File -> Preferences -> Cursor Settings.
  2. Navigate to the MCP section.
  3. Select the option to Add new global MCP Server.
  4. Insert the subsequent configuration into the designated mcp.json file:

{ "mcpServers": { "api-market": { "command": "npx", "args": [ "-y", "@noveum-ai/mcp-server", "--headers", "x-magicapi-key:" ] } } }

Alternatively, if adding manually to an existing list, place this object as the initial element within mcpServers:

"api-market": {
  "command": "npx",
  "args": [
    "-y",
    "@noveum-ai/mcp-server",
    "--headers",
    "x-magicapi-key:<your-api-key>"
  ]
},
  1. Legacy Cursor installations may require direct command line input after adding the server: bash npx -y @noveum-ai/mcp-server --headers x-magicapi-key:your-api-key

Key Acquisition from API.market

To secure the necessary authentication token: 1. Authenticate on the API.market portal. 2. Navigate to your user profile section and select 'My API Keys'. 3. Your credentials will be displayed there.

Integrated Services Catalog

  • Routing & Matrix: GET-trueway-matrix-MatrixService-CalculateDrivingMatrix
  • Speech Processing: GET-magicapi-whisper-predictions--request_id, POST-magicapi-whisper-whisper
  • Media Manipulation (FaceSwap): POST-capix-faceswap-upload, POST-capix-faceswap-faceswap-v1-image, POST-capix-faceswap-faceswap-v1-video, POST-capix-faceswap-result
  • Geospatial Services: GET-trueway-geocoding-GeocodingService-Geocode, GET-trueway-geocoding-GeocodingService-ReverseGeocode
  • Network Tools: POST-magicapi-dnschecker-dnschecker, GET-magicapi-whois-whois--domain-, POST-magicapi-domainchecker-check_domains
  • Code Generation/Analysis: GET-magicapi-coder-predictions--request_id, POST-magicapi-coder-coder
  • Content Moderation: POST-bridgeml-nsfw-detection-nsfw_detection
  • Image Deblurring: GET-magicapi-deblurer-predictions--request_id, POST-magicapi-deblurer-deblurer
  • Image Synthesis: POST-bridgeml-text-to-image-text_to_image
  • Temporal Analysis: GET-magicapi-period-predictions--request_id, POST-magicapi-period-period
  • Location Search: GET-trueway-places-PlacesService-FindPlaceByText, GET-trueway-places-PlacesService-FindPlacesNearby
  • Stylistic Modeling (Hair): GET-magicapi-hair-predictions--request_id, POST-magicapi-hair-hair
  • Advanced Code Models: POST-bridgeml-codellama-bridgeml-codellama
  • Information Retrieval (Brave Suite):
    • Video Search: GET-brave-brave-videos-search
    • Web Search: GET-brave-brave-web-search
    • Image Search: GET-brave-brave-images-search
    • News Aggregation: GET-brave-brave-news-search
    • Query Suggestion: GET-brave-brave-suggest-search
    • Spell Check Utility: GET-brave-brave-spellcheck-search
  • Navigation: GET-trueway-routing-DirectionsService-FindDrivingRoute, GET-trueway-routing-DirectionsService-FindDrivingPath
  • Feed Parsing: POST-pipfeed-parse-extract

Operational Examples

Use Case 1: Route Determination

Agents can ascertain travel paths between specified geographical coordinates.

Use Case 2: News Synthesis and Deep Dive

Agents can retrieve topical news summaries and subsequently access linked articles for deeper investigation.

Use Case 3: Domain Availability Inquiry

Facilitates checking the registration status of specified domain names.

Contribution and Development

Integrating Novel Services

The utils directory contains utility scripts essential for managing API definitions, processing OpenAPI schemas, and registering newly supported APIs within the MCP framework.

Step 1: Locate OpenAPI Schema File

Acquire the OpenAPI JSON specification for the target API. Create a subdirectory named json_files in the project root and deposit the OpenAPI JSON specification there.

Step 2: Schema Path Modification

Execute modify_api.py to correctly inject the file reference into the specification structure.

bash python utils/modify_api.py

Step 3: Refining Service Descriptions

After path adjustments, utilize one of the following methods to refine the API summaries:

  • Automated Condensation via LLM:

bash python utils/LLM_summary_shortener.py

  • Manual Description Editing:

bash python utils/manual_summary_shortener.py

Step 4: Compilation and Verification

Recompile the project sources to implement the modifications:

bash npm run build

Validate the new integration using the inspection utility:

bash npm run inspect

Step 5: Submission Protocol

To propose your enhancements to the main repository: - Fork the repository source. - Establish a dedicated feature branch. - Submit a formal Pull Request (PR).

Step 6: MCP Server Publishing (Optional)

For public distribution of your build: - Revise package.json (e.g., increment version number, adjust metadata). - Execute the package publication command: bash npm publish --access public

Development Tooling

Build & Cleanup

  • npm run build: Compiles TypeScript sources.
  • npm run clean: Deletes generated build artifacts.
  • npm run typecheck: Executes static TypeScript type validation.

Interactive Development

  • npm run dev: Monitors source files and triggers incremental rebuilds upon modification.
  • npm run inspect-watch: Initiates the inspector with live reloading functionality.

Code Quality Assurance

  • npm run lint: Runs static analysis via ESLint.
  • npm run typecheck: Confirms TypeScript type correctness.

Command Line Invocation

When running the inspector directly: bash 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"

Local Debugging Cycle

  1. Initiate the local development harness: bash npm run inspect-watch

  2. Apply modifications within the src/ TypeScript source files.

  3. The server automatically recompiles and refreshes.
  4. Utilize the MCP Inspector interface for immediate functional verification.

Local Setup and Execution

To run or debug the gateway locally: 1. Clone the repository and fetch dependencies: bash git clone https://github.com/Noveum/api-market-mcp-server.git cd api-market-mcp-server npm install

  1. Produce the distributable code: bash npm run build

  2. Execute the server for inspection: bash npm run inspect

Contributor Guidelines

  1. Create a fork of the repository.
  2. Checkout a new branch for feature implementation.
  3. Implement necessary changes.
  4. Verify integrity via testing and linting: bash npm run typecheck npm run lint

  5. Submit a formal Pull Request.

Licensing

This software is distributed under the MIT License.

WIKIPEDIA: Cloud computing describes the delivery of computing services—including servers, storage, databases, networking, software, analytics, and intelligence—over the Internet ("the cloud"). Major cloud providers include Amazon Web Services (AWS), Microsoft Azure, and Google Cloud Platform (GCP). Its adoption is predicated on abstracting physical infrastructure management from end-users and organizations.

== NIST Essential Characteristics == In 2011, the U.S. National Institute of Standards and Technology (NIST) established five core attributes defining cloud systems. These are defined as:

On-demand self-service: "A user can provision computational resources, such as processing time or repository space, autonomously and instantly, without requiring service provider personnel intervention." Broad network accessibility: "The capabilities are accessible via network connections using standardized protocols, supporting diverse client platforms (e.g., mobile devices, desktops, workstations)." Resource pooling: "Provider resources are aggregated to serve multiple clients simultaneously via a multi-tenant architecture, dynamically allocating physical and virtual assets based on fluctuating demand." Rapid elasticity: "Services can scale up or down swiftly, potentially automatically, to match usage needs. From the consumer's perspective, available capacity often seems limitless and instantly obtainable in any required volume." Measured service: "Resource consumption (e.g., bandwidth, CPU cycles, storage volume) is automatically tracked and regulated through an abstraction layer, ensuring transparent reporting for both the consumer and the supplier." These definitions have seen subsequent refinement by the International Organization for Standardization (ISO) as of 2023.

== Genesis of the Cloud Concept == The conceptual foundation of cloud infrastructure traces back to the 1960s, particularly with the rise of time-sharing systems facilitated by Remote Job Entry (RJE). This era was dominated by centralized data centers where users submitted tasks to mainframe operators. The primary focus was leveraging expensive, large-scale computing assets more effectively through shared access. The modern 'cloud' visual metaphor for abstracted services was first employed in 1994 by General Magic in documentation for their Telescript environment, signifying the accessible domain for mobile agents. This analogy is credited to communications specialist David Hoffman, drawing from established networking terminology. The term "cloud computing" gained widespread recognition in 1996 following internal business planning by Compaq Computer Corporation, outlining a vision for future internet-centric computing.

See Also

`