"Automating HTTP API Wrapping into MCPT Tool" matching MCP servers:

Enables fetching HTTP resources through the MCP protocol.

MCP router that fronts your other MCP servers behind a few small generic tools, so their tool definitions stay out of the context window and are discovered on demand.

Stateful interactive HTTP REPL and Agentic MCP engine for API navigation and testing.

Enables MCP clients to connect over HTTP/SSE, call simple echo, arithmetic, uppercasing, and time tools, and run asynchronous tasks with approval elicitations via the Tasks extension.

Audits MCP tool descriptions for quality and reliability, scoring them 0-100, detecting smells, and providing rewritten versions for better agent accuracy.

Graph-based tool retrieval for LLM agents. Builds a tool graph from OpenAPI/MCP specs and retrieves multi-step workflows via hybrid search (BM25 + graph traversal + embedding), recovering accuracy from 12% to 82% with 79% fewer tokens. Also works as an MCP Proxy to aggregate multiple servers behind 3 meta-tools.

Enables AI assistants to query live football data, including fixtures, live scores, standings, statistics, betting odds, and full odds movement history for corner and card lines.

Amazon MCP server and Amazon product data API for AI agents. Lets Claude, Cursor, ChatGPT and other MCP clients search Amazon, get real-time prices, reviews, product details, sellers, deals and best seller ranks, or look up any ASIN. One API key, 100 free requests a month.

Enables AI agents to validate AI infrastructure claims, check endpoint availability, solve CAPTCHA challenges, convert web pages to Markdown, search the web, extract structured JSON, and fetch bot-protected HTML through native tool calls.

Protects AI agents from bad tool outputs, schema mismatches, and tool poisoning by validating, sanitizing, and scoring reliability of tool responses.

MCP server that detects and guards against tool poisoning and prompt injection attacks in tool descriptions and schemas. It provides risk scoring, pattern detection, safe rewriting, and audit reports with zero external API cost.

Provides pre-fetch routing intelligence for AI agents by recommending the cheapest reliable route (HTTP, browser, machine endpoint, or avoid) before visiting a URL.

Self-contained SearXNG MCP server in Docker. Aggregates 200+ search engines across 30+ categories with multi-page fanout, autocomplete, and engine discovery. Dual transport (HTTP + stdio), API key auth, and built-in Web UI reverse proxy.

Enables scoring the WHO-5 Well-Being Index from five answers, returning a 0–100 score and a low, reduced, or normal band without providing a diagnosis.

Enables an MCP client to read and write a personal Garmin Connect account: activities with per-set strength detail, daily health metrics (sleep, HRV, stress, steps, readiness), planned and completed workouts, and weigh-ins with body composition. It also logs finished strength sessions and body-composition readings as FIT files so they appear in Garmin Connect like natively recorded ones.

It gives AI agents one tool to access the Omega-API judge, which evaluates conversational turns and returns a decision and gate action (release, clarify, suppress, or none) to guide the agent's response.

The LinkedIn API and MCP server for AI agents: search, connect, message and enrich on accounts you own, with limits enforced on our server. 20,000+ LinkedIn accounts run on this stack, and under 1% of them have ever been restricted.

An MCP server for Canvas LMS that provides 15 curated tools for everyday student work and a gateway to reach every endpoint your Canvas instance exposes.

Eight crypto and DeFi data tools for AI agents: prices, gas, one ParaSwap route quote, GoPlus token security and top-holder samples, DefiLlama yields, Hyperliquid/dYdX funding, and observed wallet balances. Inspect prices free; pay 0.001–0.008 USDC per call on Base through x402. No API key or subscription.

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.

Enables AI assistants to access sports betting odds data from 265+ bookmakers across 34 sports, including events, odds, historical data, arbitrage, and value bets.

Every other colour API tells you what goes together. Colour Memory tells you what it means, where the evidence ends, and what it must not claim. 47,515 hand-researched records, graded A–E, every result cited. 91 specialist tools built for agents that need precision, not guesses. Direct MCP: https://api.colourmemory.com/mcp — no signup, no key for the free tools (10 calls).

Turns an OpenAPI spec into a ready-to-run test harness with local LLM agents: WireMock stubs, contract tests, robustness probes, and chaos scenarios you can switch on and off in a running WireMock.

Enables AI agents to call real API endpoints and verify responses against OpenAPI specs, supporting contract testing, auth presets, spec diffing, and health checks.

Stop letting your agent guess at APIs. Ask the code you actually installed. installed-api is a Claude Code plugin (an MCP server, Python standard library only) that answers "what's the signature of X?", "does Y take that argument?" and "which version do we have?" from the packages installed in this project: your .venv, your node_modules.

Local OpenAPI contract checks and breaking-change detection between spec versions for AI coding agents.

Enables searching and browsing internet radio stations from the Radio Browser directory, retrieving live now-playing track information from station streams via ICY/Shoutcast metadata, and interacting with directory data through MCP tools without requiring API keys.

Signed, offline-verifiable authorization for API-contract changes. Before a contract change (OpenAPI, GraphQL, Protobuf, AsyncAPI, MCP manifests) merges or deploys, the agent calls preflight_change_set; the decision is deterministic, signed, and verifiable without calling CodeRifts. Three tools: preflight_change_set, verify_receipt, get_decision_details. Only a granted change can proceed.

MCP server and agent skill for the pline.ai API: scrape, crawl, batch-scrape, map, and search the web from Claude, Cursor, Codex, and any MCP client.

Provides LinkedIn automation via a real browser session using your own cookie, enabling profile, company, job, and post search and reading, plus sending messages and connection requests with rate limiting.

Enables search and lookup of SolidWorks API documentation, including methods, interfaces, enums, and examples, via natural language queries.

Live normalized remote-job data across 5 boards — one keyless endpoint, one schema, skill fit-score. No API key required. Tools: search jobs by skills + salary floor, live market stats, and computed salary bands.

Enables agents to invoke any REST or SOAP service by sending a normalized payload, with support for API key, Basic, Bearer, and OAuth2 auth. Connectors can be registered once and reused by name.

MCP server for decoding and inspecting x402 payment headers and requests. Remote endpoint: https://lumenworks-x402-decoder.onrender.com/mcp

Lets a human review what an AI agent is about to post to a chat tool (Slack first) before it is sent. Renders the draft, destination and warnings (@here/@channel, unresolved mentions, format issues) in a neutral local HTML preview; never sends anything.

Analyzes multi-step AI agent tool chains to compute success probability, identify bottlenecks, and suggest better execution orders, enabling more reliable agents via local pure-math computation.

Lets AI agents and developers list a catalog of troubleshooting datasets, preview up to three records per product for free, and get Lightning payment instructions to unlock full structured datasets.

Per-customer API usage analytics and billing exports for small B2B APIs. Agents can sign up, get ingest snippets and read usage by customer, endpoint and plan.

Provides a deterministic failure-decision API for MCP clients, returning one of six actions (RETRY_NOW, WAIT, REPAIR_REQUEST, VERIFY_FIRST, ESCALATE, ABORT) based on failure context to guide safe next steps.

MCP server for inspecting email domains and addresses, providing objective domain-level email infrastructure answers such as MX, SPF, DMARC, MTA-STS, and disposable-domain evidence.