OpenAPI Schema Explorer

Created By
kadykova year ago
MCP server providing token-efficient access to OpenAPI/Swagger specs via MCP Resources for client-side exploration.
Overview

What is OpenAPI Schema Explorer?

OpenAPI Schema Explorer is a server designed to provide token-efficient access to OpenAPI (v3.0) and Swagger (v2.0) specifications through MCP Resources, allowing clients to explore large API specifications without loading the entire file into memory.

How to use OpenAPI Schema Explorer?

To use the OpenAPI Schema Explorer, configure your MCP client (like Claude Desktop) to run the server using methods such as npx, Docker, or local installation. You can specify the path or URL of the OpenAPI specification you want to explore.

Key features of OpenAPI Schema Explorer?

  • Token-efficient access to OpenAPI specs via MCP Resources.
  • Supports both OpenAPI v3.0 and Swagger v2.0, with automatic conversion.
  • Allows loading specifications from local files or remote URLs.
  • Provides multiple output formats (JSON, YAML, minified JSON).
  • Dynamic server name based on the loaded spec's title.

Use cases of OpenAPI Schema Explorer?

  1. Exploring API paths and operations without loading entire specifications.
  2. Facilitating API documentation and testing for developers.
  3. Integrating with MCP clients for enhanced API interaction.

FAQ from OpenAPI Schema Explorer?

  • Can I use OpenAPI Schema Explorer with any MCP client?

Yes! It is designed to work with various MCP clients like Claude Desktop and Cline.

  • Is there a need for separate installation?

No, the recommended usage methods (npx and Docker) do not require separate installation steps.

  • What formats can I get the output in?

You can receive output in JSON, YAML, or minified JSON formats.

Server Config

{
  "mcpServers": {
    "My API Spec (npx)": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-openapi-schema-explorer@latest",
        "https://petstore3.swagger.io/api/v3/openapi.json",
        "--output-format",
        "yaml"
      ],
      "env": {}
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
kadykov
Star
-
Language
-
License
-
Category

Recommend Servers

View All
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