AI & LLMs

Exposes a unified pool of free LLM chat routes behind one OpenAI-compatible endpoint, letting MCP clients browse available providers and models, check which free tiers are usable right now, and send chat or agent requests with automatic failover. Works without credentials whenever an enabled keyless route is available.

Provides a local-first, governed MCP foundation where QA engineers can check server health and capabilities, read a status resource, use an orientation prompt, and validate non-secret configuration, profiles, and credential references without exposing secrets. External provider integrations, test execution, and release reporting are not yet implemented and remain scaffolded.

Lets an AI agent that is already driving a SolidCraft session export the live or saved design and open it directly in OrcaSlicer, with options for format, body filtering, control port, and export-only mode. It also exposes a diagnostics tool that reports the detected SolidCraft CLI, running control windows, and available slicer commands.

Give any AI agent a shopping brain. LMK.today is an open Model Context Protocol server with curated cross-merchant search, real price history, live demand signals, and editorial gift collections — no account required. More at https://lmk.today/mcp

Enables hands-free voice collaboration with a coding agent: you speak requirements aloud and hear only short, plain-language progress and completion summaries while the agent edits code, runs tests, and fixes bugs in the background. It also handles continuous speech recognition with automatic turn detection, barge-in interruption, and spoken approval prompts before risky operations.

Exposes five prompt-engineering skills as MCP tools, prompts and resources so a connected AI client can itself prepare and execute task, system-prompt, evaluation and rewrite work. It also provides a durable, resumable pipeline that tracks isolated worker dispatches, validates stage output, enforces loop limits and persists run artifacts — locally over stdio or self-hosted on Cloudflare Workers without any model API key.

Enables LLMs to access and analyze ESPN fantasy football leagues through read-only MCP tools, covering rosters, scores, transactions, standings, lineup audits, and league-specific rules.

Provide AI-powered real-time analysis and intelligence on NPM packages, including security, dependencies, performance, and quality metrics. Enable faster and safer package management decisions by integrating with Claude and Anthropic AI. Deliver comprehensive insights such as vulnerability scanning, download trends, and maintenance status to optimize your npm ecosystem.

Enables Claude Code and OpenAI Codex CLI to act as bidirectional partners by letting each ask the other for code review, explanations, planning, performance analysis, and implementation help. It also provides background job tools for starting, observing, waiting on, and cancelling delegated tasks.

IA-QA as an MCP Server Use IA-QA's developer tools to test your llm agents RAG ai tools, directly from Cursor, Claude Desktop, Windsurf, or any AI agent without leaving your IDE. Many classical testing tools too ! Enjoy ! No API key. No signup. Free.

Enables agents and users to route prompts to the cheapest reachable free or paid model across providers, compare costs, list filtered models, and receive fallback chains and cached routing results without calling any LLM API.

Enables any MCP client or OpenAI-compatible application to use Meta Muse through a logged-in Chrome session, with tools for chat, attachments, session management, media retrieval, streaming, and tool-call compatibility.

Enables AI assistants to drive a locally running desktop fire-simulation app through natural language — opening projects, recognizing drawings, building geometry and meshes, running fire/smoke, evacuation, HVAC smoke-control and sprinkler water-spray hydraulics analyses, and reviewing ASET/RSET results. Ships an ontology, rule set, glossaries and step-by-step playbooks so prompts stay accurate and errors are caught before a run.

MCP server for TracePass — the EU Digital Product Passport (DPP) compliance platform for the ESPR and EU Battery Regulation. Lets AI assistants create products, build and audit Digital Product Passports (battery: 91 fields; electronics: 166), set economic-operator parties, and read or capture GS1 EPCIS 2.0 supply-chain events. 6 tools, 2 resources, 5 prompts. Connect to the hosted endpoint (https://ai.tracepass.eu/mcp) with a TracePass tp_ API key, or run locally via npx -y tracepass-mcp-serve...

Enable your LLMs to perform accurate numerical calculations with a simple API. Leverage basic arithmetic and statistical functions to enhance your applications. Simplify complex mathematical tasks effortlessly and improve your model's capabilities.

Drop a single script into a web UI and the page itself exposes DOM inspection, interaction, and diagnostic devtools to coding agents through document.modelContext, with no server, LLM, or chat UI involved. It also lets an app register its own domain-state tools, so agents can reach state that the DOM cannot reveal.

IBAN validation, BIC/SWIFT lookup, Swiss clearing, SEPA compliance and risk indicators for AI agents. 121K+ bank entries from GLEIF, 1,190 Swiss BC-Nummer from SIX BankMaster, 84 countries. Native MCP support with 5 tools, 2 resources, 1 prompt.

Reliable web fetching MCP server with built-in retry logic, circuit breaker patterns, caching, and anti-bot bypass. Fetches URLs as raw HTML or clean markdown optimized for LLM consumption. Includes domain health checks and cache management tools.

Enables AI assistants to query news articles from TheNewsAPI.com through natural-language prompts, exposing search, top stories, headlines, similar articles, article lookup, and source listing as MCP tools.

Enables ChatGPT to control Mobile Safari on a real USB-connected iPhone through an OpenAI Secure MCP Tunnel and Appium MCP, including device selection, WDA preparation, and Safari session automation.

Enables AI agents to score their outgoing responses against groundedness and prompt-injection risks mid-turn, returning allow, warn, or block verdicts before the response reaches the user.

Enables Codex users to delegate engineering, refactoring, auditing, and test execution tasks to Google Antigravity CLI as a persistent autonomous subagent, with tools for managing sessions and running prompts.

Zero-dependency CLI that connects any AI agent to every MCP server: one config, synced to Claude Code, Cursor, Codex, Cline, Windsurf and VS Code. 99.8% token savings on tool discovery through a single MCP gateway (mcptoon serve), Agent Plugins Specification 1.0.0 support, and strict spec validation. pip install mcptoon

Local macOS MCP server for Calendar and Reminders that gives each AI agent its own token and access to only the calendars and reminder lists you choose, per action. Writes can require your approval in a panel that shows every field.