OpenAPI Slice

Created By
vvarp10 months ago
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.
Overview

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

uvx openapi-slice-mcp

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

Project Info
Created At
10 months ago
Updated At
10 months ago
Author Name
vvarp
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago