"The concept of thinking or introspection" matching MCP servers:

A Node.js server that enables LLMs to inspect GraphQL schemas and retrieve information about queries, mutations, and types via MCP.

Provides comprehensive GraphQL introspection, filtering, and query/mutation execution with safety controls. Enables AI agents to explore and interact with GraphQL APIs through natural language.

MCP server for the Clash of Clans API. Can get player, clan information, analyze ongoing wars, as well as war logs (provided they are public).

An MCP server that automates importing products from AliExpress, Alibaba, and Accio into DSers and pushing them to Shopify or Wix stores, with features like bulk import, pricing rules, and title cleanup.

Enables AI agents to create webhook URLs, wait for incoming deliveries, inspect payloads, and replay or send signed webhook events to a local handler.

Enables users to search, compare, and retrieve detailed information about World of Warships ships using the official Wargaming.net API. Supports filtering by nation, type, and tier with multi-language support and intelligent caching.

Enables agents to grade and repair the Bazaar discovery metadata of x402 services through native tools, itemizing defects or returning a validator-passed discovery package inferred from one real sample output. Calls are paid in USDC on Base via the x402 protocol, with no accounts or API keys required.

A local stdio server that lets coding agents build and verify a merchant payment integration against a sandbox, creating and cancelling invoices, simulating payment outcomes, checking invoice status, and validating webhook signatures. It also serves embedded docs as resources and refuses live or payout keys, keeping all work out of production paths.

Enables AI agents to connect to any GraphQL endpoint, introspect schemas, and execute queries or mutations through auto-generated tools.

Optimizes REST API calls for AI agents by returning compact schemas instead of full responses, allowing agents to fetch only needed fields via jq masks, reducing token consumption by up to 50x.

Turns an existing Express, Hono, Fastify, or Next.js API into a Streamable HTTP MCP endpoint, exposing one tool per OpenAPI operation that runs in-process through the app's existing routes, auth, validation, and handlers. It also serves discovery documents and readiness guidance so models can better understand and call the API.

Lets an AI assistant learn the CloudCart Storefront GraphQL API, look up types, queries and mutations by name, and validate GraphQL snippets against schema and common real-world mistakes. It runs entirely locally with no store, token, or network access, so no live data is ever touched.

Enables MCP-capable agents to search the curated gold-402 directory of x402 services, probe any endpoint for valid 402 payment terms, and optionally purchase a human editorial verdict for a resource.

A TypeScript-based MCP server that enables testing of REST APIs through Cline. This tool allows you to test and interact with any REST API endpoints directly from your development environment.

A stdio MCP server that audits other MCP servers over the live protocol. It connects to any MCP target (stdio or HTTP), lints every tool's schema for agent-usability, then actually calls the tools with deliberately broken inputs to see how the server handles them, and returns a 0–100 conformance score with a per-dimension breakdown rendered as Markdown.

Validates OpenAPI specs from files, inline content, or URLs, and generates prompts for agent developers based on the API analysis.

Enables precise measurement of live HTTP and WebSocket services while maintaining an append-only, evidence-based ledger of claims that agents can query with explicit timestamps, staleness indicators, and instructions for re-verification.

ozon-mcp is a knowledge-rich MCP server that turns the entire Ozon seller toolkit into 15 high-leverage tools. AI agents (Claude, Cursor, Cline, Continue, Goose, Zed, …) can search the API in Russian or English, drill into any of 466 methods with a fully-resolved JSON Schema, and execute calls with built-in safety guards. Subscription- aware, automatic pagination over all 4 cursor styles, retry/ba

MCP server for Mockzilla. Lets coding agents like Claude Code, Claude Desktop, Cursor and Gemini CLI install the Mockzilla CLI and run API mocks from an OpenAPI spec or a single endpoint. Log in from the agent to deploy hosted mocks on mockzilla.org

An MCP server for Tern that enables the generation, verification, and management of webhook handlers across over 16 platforms and various frameworks. It provides tools to create verified endpoints, debug signature failures, and manage failed event replays via dead letter queues.

Enables MCP hosts to list, look up, and describe a static catalog of OpenAPI operations, and to inspect a governing contract and explicit deny-list that define what the server refuses to do.

Enables AI assistants to interact with Fastly's CDN API through the Model Context Protocol, allowing secure management of CDN services, caching, security settings, and performance monitoring without exposing API keys.

An MCP server that generates MCP servers. Give it an API definition - OpenAPI 3.0/3.1 or a Postman collection or extend an existing server - and it scaffolds a complete, runnable, ownable TypeScript or Python MCP server for that collection of APIs.

Local, stateful twins of the Jobber, Housecall Pro, and QuickBooks Online APIs. Its MCP tools let a coding agent reset, rewind, advance time, inject faults, and load scenarios while it builds and tests integrations, with no real accounts.

Enables testing and validation of APIs for AI agent compatibility, providing scores, grades, and actionable recommendations.

A small native HTTP client whose MCP server (plunger mcp) lets an AI agent send requests safely: undefined variables are refused, secrets are filled in by name and masked in results, and every request is recorded in a history you can see in the window. MIT licensed, for Windows, with a Linux build of the CLI and MCP server.

Point Claude at any API. JitAPI figures out which endpoints to call and in what order — automatically. Register any OpenAPI spec, search endpoints in plain English, and orchestrate multi-step workflows across multiple APIs. No API keys required — works out of the box with local embeddings.

Enables local analysis of OpenAPI 3 and Swagger 2 JSON/YAML spec files on disk, with no remote fetching of specs or credentials. It groups endpoints by tag, flags operations that appear to lack security, lists deprecated operations, and produces short markdown cheat sheets for agents.

API client for coding agents. Sends saved HTTP, GraphQL and gRPC requests, runs collections with their checks, and creates or edits requests over stdio or loopback HTTP, with secret values redacted and calls limited to an allowlist of hosts.

Enables AI assistants to help developers build on the monday.com GraphQL API by validating queries, explaining errors, providing column value formats, introspecting the live schema, executing queries, and scaffolding boilerplate code.