64391 Model Context Protocol servers — searchable, rated, ready to install.
AI workflow/MCP implementation package planner.
Muse AI Image turns prompts into photoreal pictures and clips with the Muse Image model and Muse
Standing review layer for coding agents: Claude, GPT and Gemini debate, return consensus + dissent.
Live Australian grocery prices from Woolworths, Coles, Aldi and Harris Farm.
Visual website feedback your coding agent applies: pin change requests on the live site over MCP.
Hosted MCP for Kalshi prediction markets: search, odds, order books, settlement rules, and trading.
Statements, invoices, tables, ledgers — every result carries its own arithmetic proof.
Desktop strategy development and testing with a built-in local stdio MCP server.
Compliance-filtered crypto exchange fee comparison and rebate-link routing for AI agents.
Monitor brand visibility, citations, competitors, sentiment, and GEO performance in AI search.
Find 27,000+ outdoor ping pong tables worldwide, with spot details and live playing conditions.
Scholarly search: OpenAlex, Crossref, arXiv, OpenCitations and PubMed in one endpoint.
Extract the people a company publishes on its own team, leadership or about page.
Project-scoped marketing ops for agents: Bearer dpk_/dpa_ or OAuth, read and supervised write.
Free, local MCP server that audits ClickUp, Slack & Teams for work that slipped through.
JPL-referenced Human Design charts for AI agents: bodygraph, transit, composite, Penta, DreamRave.
Peptide and GLP-1 dosing math (dose to syringe units) plus search over Shotlee's articles.
Vedic and Western astrology for AI agents: charts, dasha, matchmaking, panchanga, numerology, tarot.
Советники по бизнес-методикам: подбор эксперта-методики под задачу и консультация.
Local chronological memory banks you control; Claude recalls them via MCP.
One section in, one section out — on Markdown/GEML files, bad writes refused.
MCP server for GitHub: repos, files, issues, PRs, search. Single Go binary.
Measure a program's CPU energy and LLM tokens, then refactor it cheaper. Measure, never estimate.
Run builds, tests, and benchmarks on your own Tailscale compute node.
POST /mcp