MCP Servers

Auto-route AI requests to 13 models (Claude, GPT, Gemini, Qwen, DeepSeek). 57% cost savings.

Opik MCP Server

Interact with Opik prompts, traces, datasets and metrics through the Model Context Protocol.

A Model Context Protocol server for generating charts using AntV.

Model Context Protocol (MCP) server for Cerebras to make coding faster in AI-first IDEs

Gives LLMs ears. Spectral, harmonic, rhythm, stereo, and structural audio analysis.

Model Context Protocol server for the DocAuto document-generation API.

LLM and GPU rental prices: model price lookup, GPU listings, cheapest-GPU search, price history

MCP server for WHMCS — 73 tools, 10 resources, 8 prompts, simulate mode, rate limiting.

Provable, declarative multi-agent workflows for Claude Code (typed .slang, non-LLM executor).

Query the AI Brand Directory. Audit brand visibility in ChatGPT, Claude, and Gemini.

Search scored onchain agent frameworks, MCPs, wallets, tools, and live agents.

Model Context Protocol server for Gitea (and Forgejo, Codeberg).

Check an email before an AI agent sends it: send / ask a human / block. Detects prompt injection.

A Stockfish MCP server to allow an LLM to play chess against Stockfish

A Model Context Protocol (MCP) server and app for creating Datawrapper charts using AI assistants

A Model Context Protocol server to run other MCP servers

Pre-execution cost estimation for LLM agent workflows with calibration learning

Second opinions in Claude Code and any MCP host from GPT, Gemini, Grok, and 400+ OpenRouter models.

Airtight math for AI agents: 3.68M-doc theorem search + numeric/Lean verification. No LLM, no key.

HiveCompute MCP Server — decentralized inference router for AI agents

Externalises time-of-day, session boundaries, and break prompts for time-blind users.

Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents.

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f

Two independent AI models read a GPR, locate or pipe scan and flag the do-not-core call.