AI & ML MCP Servers
LLM providers, agents, models, embeddings, inference, and machine learning workflows.
Vaultfire Trust Protocol
io.github.Ghostkey316
On-chain trust verification and Street Cred for AI agents. ERC-8004, multi-chain.
Haki
io.github.GetHaki
Gives an assistant a persistent, dated memory of facts about a subject, with contradiction handling and traceable recall.
Cacheoverflow
io.github.GetCacheOverflow
MCP server for cache.overflow - AI agents sharing knowledge with AI agents
Concord MCP
io.github.Get-Concord-AI
Cross-harness communication and shared work-state for AI coding agents.
Easel
io.github.Gemberkoekje
A headless painting engine for AI agents: brushes, paint load, wet blending, canvas texture.
Lynxprompt Mcp
io.github.GeiserX
MCP server for LynxPrompt — browse, search, and manage AI configuration blueprints
Geepers Mcp
io.github.Geepers4242
Resolve Geepers physical handles to exact coordinates + navigation for AI agents.
Mcp Server
io.github.Garl-Protocol
18 trust tools for AI agents — verify, score, route, compare, and delegate with confidence.
Agent Trust
io.github.Garl-Protocol
Tamper-evident action receipts, trust scoring & capability tokens for AI agents. 29 MCP tools.
Agent Services Mcp
io.github.Gareth1953
MCP server: x402-paid & free tools for AI agents — provenance, quality scoring, action audit.
Clawwork
io.github.Gammell53
AI agent project management — task boards, progress tracking, and cost reporting.
Cartridge Cafe
io.github.GalenGoodwick
Your AI builds live WebGPU game worlds on cartridge.cafe — guest door, no account needed.
NotifyHub — Unified Notification MCP Server
io.github.GabrielBBaldez
Send notifications across 23 channels with 36 AI-ready tools. One API, zero boilerplate.
RECOVER — Decide Safely After a Failed Machine Action
io.github.GSterlingPress
A remote decision service that tells an assistant the safest next action after a failed API, tool, or agent action.
POSTFACT — Resolve Ambiguous Side Effects Before Retry
io.github.GSterlingPress
Lets an assistant check whether an uncertain side-effecting action actually completed before it retries the action.
Gru953 Crew
io.github.GRU-953
GRU953 Crew's autonomous multi-agent coding method, exposed as callable MCP tools.
Dev953
io.github.GRU-953
dev953 method companion: exposes its multi-agent coding method as callable MCP tools.
Humanizer
io.github.GPTHuman-ai
Rewrites AI-generated text into more natural, human-sounding prose through GPTHuman's API, returning detector and credit metadata.
Gctrl
io.github.GCTRL-TECH
Governed graph-native agent memory: knowledge extraction, fusion, hybrid RAG, scoped access tokens.
Epiphany
io.github.GATSV-tech
One private, local memory your AI tools share. Cross-model, on-device, never lose a session.
Fimemory
io.github.FutureAiIndustries
Local-first shared memory for AI tools. Your files, encrypted at rest by default; budgeted reads.
brokre
io.github.Furowu
AI-safe credential broker for MCP — run saved SSH/MySQL/psql aliases; passwords never reach AI.
Closeread Verify
io.github.FreeGuy-AI
A verified dependency-audit verdict any AI agent can call over MCP, not a raw scan.
Citeguard
io.github.Franksterino
Verifies citations in AI-generated text by fetching each cited source and returning a verdict with a verbatim evidence quote.