Google tells you what exists. Faceabot tells you what holds up.
Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.
Package npm :local-llm-worker · website · measurements and detailsLet a planning agent hand bounded language work to a local Ollama model.
Package npm :@sezzlee/llm-mcp · website · measurements and detailsCloudflare Workers MCP server: llm-output-quality-monitor
MCP endpoint :https://api.lazy-mac.com/llm-output-quality-monitor/mcp · website · measurements and detailsFan a goal out to cheap parallel LLM workers on your own key or a free local Ollama. Keep your mind.
Package pypi :algernon-mcp · website · measurements and detailsLocal, cross-provider preflight checks for LLM integration changes.
Package pypi :llm-preflight · website · measurements and detailsAll Azure MCP tools to create a seamless connection between AI agents and Azure services.
Package nuget :Azure.Mcp · website · measurements and detailsLocal-first, multi-provider tool that captures LLM API spend and exposes it to coding agents via MCP
Package pypi :llm-usage-mcp · website · measurements and detailsCompare, estimate, and deploy cloud infrastructure across AWS, GCP, and Azure for AI agents.
MCP endpoint :https://api.synlake.ai/mcp · website · measurements and detailsDelegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota.
Package pypi :local-delegate-mcp · website · measurements and detailsMCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
MCP endpoint :https://api.artificialwit.com/mcp · measurements and detailsCloud cost + FinOps knowledge for AI agents: AWS/Azure/GCP optimisation, AI spend, waste playbooks.
MCP endpoint :https://mcp.optimnow.io/mcp · website · measurements and detailsPay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.
MCP endpoint :https://eval.zuluworksai.com/mcp · website · measurements and detailsThe agent-native cloud: database, functions, AI, storage, computers. 51 tools, one API key.
MCP endpoint :https://api.scalix.world/v1/mcp · website · measurements and detailsDelegate complete coding tasks to the local OMP default model and inspect the result.
Package npm :omp-worker-mcp · website · measurements and detailsA host-agnostic MCP worker runtime for supervising local Pi coding-agent processes.
Package npm :@zguiyang/pi-worker-mcp · website · measurements and detailsYour own cloud computer run by an AI agent: signed-in browser, its own email, files, long jobs.
MCP endpoint :https://www.myclawn.com/mcp/desktop · website · measurements and detailsCloud region data for AWS, Azure, GCP, OCI & more. Query by location, compliance, GPU.
Package npm :mcp-server-cloud-regions · website · measurements and details檢查網站 llms.txt 與 AI 爬蟲 robots.txt 設定,並自動產生 llms.txt。
MCP endpoint :https://llms-check.panda198271.workers.dev/mcp · website · measurements and detailsLocal-first persistent memory for AI coding agents - 96.0% R@5 on LongMemEval, zero LLM calls.
Package npm :@awareness.market/local · website · measurements and detailsSix checks: llms.txt, llms-full.txt, .md twins, Accept: text/markdown, sitemap.md, alt link. Free.
MCP endpoint :https://www.pathwren.workers.dev/c/mcp-registry-official/mcp/markdown · website · measurements and detailsAI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt
Best tool by topic · Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Reliability data · Faceabot app · Faceabot → AI assistants · What AI agents cannot find yet · Add Faceabot to your AI · Badge for tool publishers · Help · Privacy · Terms