mcpField
O
OpenAPI Slice

OpenAPI Slice

Local
github.com/vvarpDeveloper Tools2Updated 53w ago
Repository

About OpenAPI Slice

OpenAPI Slice is an MCP server for developers and agents working with large OpenAPI specifications. It extracts an endpoint and its referenced components, avoiding the need to load the full specification.

Key features

  1. 01Extract endpoint-specific spec slices
  2. 02Resolve referenced components recursively
  3. 03Output YAML or JSON
  4. 04Load local files or remote URLs
  5. 05Discover available endpoints

Use cases

  1. 01Provide an agent only the spec for a target endpoint
  2. 02Inspect endpoints in a large API definition
  3. 03Load a spec from a file or URL

MCP support

Exposes tools to MCP clients for loading OpenAPI specifications, listing endpoints, extracting endpoint slices, and checking server status.

#openapi

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "openapi-slice": {
      "command": "uvx",
      "args": [
        "openapi-slice-mcp"
      ]
    }
  }
}
Run commanduvx openapi-slice-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiopenapi-slice-mcp

Tools

5

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
file_pathstringYes

Details

From the project README

OpenAPI Slice MCP Server

An MCP (Model Context Protocol) server that helps you work with large OpenAPI specifications by extracting only the relevant portions for specific endpoints. This is particularly useful when working with LLMs that have context limitations - instead of loading an entire large OpenAPI spec, you can extract just the parts you need for a specific endpoint.

Features

  • Endpoint-specific extraction: Get minimal OpenAPI specs containing only the requested endpoint and its dependencies
  • Automatic dependency resolution: Recursively finds and includes all referenced components (schemas, parameters, etc.)
  • Multiple formats: Output in YAML or JSON format
  • File support: Load OpenAPI specs from local YAML or JSON files
  • Remote support: Fetch OpenAPI specs directly from URLs (HTTP/HTTPS)
  • Discovery tools: List all available endpoints in a loaded specification

Tools

The server provides the following MCP tools:

  • load_openapi_spec(file_path: str) - Load an OpenAPI specification from a local YAML or JSON file
  • load_openapi_spec_from_url(url: str, timeout: int = 30) - Load an OpenAPI specification from a remote URL
  • list_endpoints() - List all available endpoints in the currently loaded specification
  • extract_endpoint_slice(path: str, method: str, output_format: str = "yaml") - Extract a minimal spec slice for a specific endpoint
  • get_server_status() - Get the current status of the server

Usage

Running the Server
Stdio Mode (Default)

For local development and Claude Desktop integration:

uvx openapi-slice-mcp

The server runs using the STDIO transport and can be integrated with any MCP client.

HTTP Mode

For Smithery deployment or remote access:

# Using the dedicated HTTP entry point (runs on port 8000 by default)
uvx openapi-slice-mcp-http

# Or using the main entry point with --transport flag
uvx openapi-slice-mcp --transport http --host 0.0.0.0 --port 8000

The HTTP server exposes the MCP protocol at http://host:port/mcp.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.