2449 Model Context Protocol servers — searchable, rated, ready to install.
Model Context Protocol server for the Exogram Authority Runtime.
Model Context Protocol server for Parseable. Lets LLMs discover and query Parseable.
Control real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
Deterministic security scanning, no model or API key, plus offline-verifiable proof a fix worked.
Local-first LLM orchestration: memory, knowledge, state, routing, swarm, API discovery, plugins.
Run Google, Meta, Microsoft, TikTok and LinkedIn Ads from Claude or ChatGPT. Writes need approval.
Amazon Seller Central and Ads inside Claude or ChatGPT. Real fees from your own settlements.
Rewrites Claude-English into plain English, preserving meaning, code and structure.
Self-hosted MCP server exposing Claude Code as an agentic AI tool over streamable HTTP.
Generate images, video, music, voice and 3D through one API. 30 tools, 200+ models.
Norsk regnskap i Claude: bokføring, MVA, lønn og Altinn — spør på vanlig norsk.
Standing review layer for coding agents: Claude, GPT and Gemini debate, return consensus + dissent.
Read-only OpenIM search for institutional buy-side investment models and architecture.
Connect LLM tools to your Algolia account with user-scoped access for internal workflows.
One workspace of tools for Claude and ChatGPT: connect 600+ apps, generate media, build tools.
Render PyTorch architecture diagrams and animated GIF reveals from trusted model source.
Measure a program's CPU energy and LLM tokens, then refactor it cheaper. Measure, never estimate.
Connect Claude to a self-hosted Total CMS site: search content, read docs, manage with an API key.
Search, read, and write your Apple Notes from ChatGPT/Claude via a local Mac agent + MCP relay.
Free OpenAI-compatible inference with signed provenance receipts and 3 focused MCP tools.
Delegate heavy tasks from Claude Code to the Antigravity CLI (Gemini) with quota-aware failover.
Session memory for coding agents: local-first recall, drift detection, on-device inference.
Search AO3 and have fics read by a secondary model before they're recommended
Test whether 3D assets survive Apple Quick Look and Safari <model>, then fix what fails
POST /mcp