3818 Model Context Protocol servers — searchable, rated, ready to install.
Traced LLM Proxy
Agent-native parametric 3D CAD: model machines, validate them and emit shop drawings
Fan a goal out to cheap parallel LLM workers on your own key or a free local Ollama. Keep your mind.
Acquisition.gov FAR Overhaul model parts, agency deviations, PDFs, and guidance. 5 tools.
Hosted MCP memory: save sessions/decisions once, search from Claude, Cursor, ChatGPT. EU-hosted FTS.
Pay-per-call NLP & embeddings APIs on Base via x402. No keys/signup; agents pay per call in USDC.
Search and invoke real AI capabilities on modelmarket.dev. Free trial, then a prepaid key.
Practice questions for the four Claude certifications. The assistant never sees the key.
Pre-checks a model change before GPU time or traffic: memory, layout, serving config, pins.
Trust verdicts on repos, models, VS Code and Docker Desktop extensions and agent skills.
Large files and secrets between people and agents, never through the chat or the model.
Reports real token usage and cost from Claude Code and OpenCode data. Nothing leaves your machine.
Ship models, build logs, tutorials, galleries, content search, and rigging calculators.
Closed-source remote MCP: model benchmarks, costs, HN signals, tech registry.
Claude, ChatGPT, Grok and other AIs on one job list. The board asks for proof before a job closes.
Track and query EzStat metrics from Claude, Cursor, or any MCP agent. StatHat-compatible.
AI voices from many models talk to each other. Read free; write with a token that stays out of chat.
Local-first, zero-knowledge AI memory across Claude, Cursor, and every MCP client. 0 RTT reads.
Shared memory for a team in Claude Code: what one person records, everyone has.
AI integrity standards, benchmarks, and EU AI Act-aligned Tier 0 model certification
Model Context Protocol server for Forgejo, Codeberg and Gitea, in Rust
Benchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.
Audited tarot, I Ching, Xiao Liu Ren, Bazi (Four Pillars). Model never invents results.
Consult other LLMs as tools — ask them, compare their answers, synthesize a conclusion.
POST /mcp