Model and agent tools MCP servers
8,814 servers
Call other models, run sub-agents, manage prompts and evaluate outputs.
- Toolmesh
io.github.DunkelCloud/toolmeshSelf-hosted MCP gateway. Turn any REST API into MCP tools via YAML (DADL). Authz, audit, policies.
Address set by you
Model and agent tools Official MCP Registry · Go modules Remote
- AVEL
io.github.Ensi81/avelIdentity/reputation verification for agent-to-agent payments across x402, AP2, MPP, checkout.
Version check not run yet
Model and agent tools Official MCP Registry Local
- Eyebrowse
io.github.Evil-Bane/eyebrowseStealthy, LLM-drivable browser engine — a Python library + 85-tool MCP server on stealth Chromium.
Version check not run yet
Browser automation Official MCP Registry Local
- rekey
io.github.Ezra-Black/rekeyRotate API keys across AWS, GitLab, Cloudflare, OpenAI & more. Secrets never reach the model.
Version check not run yet
Cloud platforms Official MCP Registry Local
- dyslex.ia
io.github.Firou91/dyslex-iaAccessibility MCP server and Agent Skills for AI agents. Requires Superpowers.
Version check not run yet
Developer tools Official MCP Registry Local
- Dep Scope
io.github.FlorianBruniaux/dep-scopeSymbol-level npm dependency analysis: scan verdicts, native alternatives, migration prompts.
Version check not run yet
Model and agent tools Official MCP Registry Local
- Dev953
io.github.GRU-953/dev953dev953 method companion: exposes its multi-agent coding method as callable MCP tools.
Version check not run yet
Model and agent tools Official MCP Registry Local
- Gru953 Crew
io.github.GRU-953/gru953-crewGRU953 Crew's autonomous multi-agent coding method, exposed as callable MCP tools.
Version check not run yet
Model and agent tools Official MCP Registry Local
- stipend.sh
io.github.Graphiker-Australia/stipendNon-custodial USDC wallet on Base with spending limits enforced in code, not in a prompt.
Version check not run yet
Model and agent tools Official MCP Registry Local
- RAGScore
io.github.HZYAI/ragscoreGenerate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.
Version check not run yet
Science and research Official MCP Registry Local
- Bestie Check
io.github.HireBestie/bestie-checkDocument reasoning checks: a helicopter view of claims and assumptions before handoff.
89.97% up · 30 days
Office documents and spreadsheets Official MCP Registry Local Remote
- Memograph
io.github.Indhar01/memographGraph-based memory system for LLMs with knowledge graphs and semantic search.
Version check not run yet
Memory and context Official MCP Registry Local
- Codex4ever
io.github.ItsOdeLeo/codex4everPlan OpenAI Codex usage from local quota, banked resets and extra-reset forecasts.
Version check not run yet
Model and agent tools Official MCP Registry Local
- Lethe
io.github.JesusGarcia9009/letheContext GC for LLM agents: offload large tool outputs and recall them to save tokens.
Version check not run yet
Memory and context Official MCP Registry Local
- Local Llm Worker
io.github.JoblessJoe/local-llm-workerLocal LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.
Version check not run yet
Model and agent tools Official MCP Registry Local
- Llmxray
io.github.LogneBudo/llmxrayWhat went wrong with your own Ollama calls, in sentences with the fix. Local, read-only.
Version check not run yet
Model and agent tools Official MCP Registry Local
- Context Guardian
io.github.LuminariSoftwares/context-guardianCompacting proxy for OpenAI-compatible backends, with MCP tools to search the archived history.
Version check not run yet
Model and agent tools Official MCP Registry Local
- Stack Guardian
io.github.LuminariSoftwares/stack-guardianHealth doctor for a home AI stack: Ollama nodes, GPUs and tailnet, with graded confidence.
Version check not run yet
Model and agent tools Official MCP Registry Local
- Ollama Handoff
io.github.Michael-WhiteCapData/ollama-handoffOffload cheap work from your AI agent to a local Ollama model, at zero cloud cost.
Version check not run yet
Model and agent tools Official MCP Registry Local
- cogvault
io.github.NBibikov/cogvaultLocal hybrid-search memory for AI agents over plain Markdown. Multi-tenant, offline, no LLM.
Version check not run yet
Office documents and spreadsheets Official MCP Registry Local
- Genome
io.github.NORTHTEKDevs/genomeFully local memory for AI agents: zero-LLM ingest, semantic recall, air-gapped, auditable.
Version check not run yet
Memory and context Official MCP Registry Local
- Codigest
io.github.NaNIsaac/codigestTerminal output, project snapshots and semantic diffs as LLM-ready context
Version check not run yet
Model and agent tools Official MCP Registry Local
- Osmp
io.github.Octid-io/osmpAgentic AI instruction encoding. 86.8% vs JSON. Inference-free decode. Any channel.
Version check not run yet
Utilities Official MCP Registry · PyPI Local
- Search Registry
io.github.OnticX/search-mcp-registrySearch and discover MCP servers from the MCP Registry.
Version check not run yet
Model and agent tools Official MCP Registry · PyPI Local
- DAiL Marketplace
io.github.Rizzzo21/dail-marketplaceMCP adapter for the DAiL agent-to-agent marketplace: escrow-protected trade via stdio.
Version check not run yet
Model and agent tools Official MCP Registry Local
- Agent Eval
io.github.RudrenduPaul/agent-evalStatistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.
Version check not run yet
Model and agent tools Official MCP Registry Local
- Inferbench
io.github.RudrenduPaul/inferbenchBenchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.
Version check not run yet
Model and agent tools Official MCP Registry Local
- Slop Eval
io.github.RudrenduPaul/slop-evalWraps the slop-eval CLI as a single generic MCP tool for genericness scoring of AI UI output.
Version check not run yet
Model and agent tools Official MCP Registry Local
- Swarm Rd Orchestrator
io.github.RudrenduPaul/swarm-rd-orchestratorAppend-only event log for cross-agent context/memory sharing via 3 MCP tools.
Version check not run yet
Model and agent tools Official MCP Registry Local
- Taskswarm
io.github.RudrenduPaul/taskswarmWraps the taskswarm CLI as a single generic MCP tool for multi-agent task coordination.
Version check not run yet
Project management Official MCP Registry Local
- Workloadtruth
io.github.RudrenduPaul/workloadtruthClassifies GPU workloads as inference or training from telemetry alone via MCP tools.
Version check not run yet
Model and agent tools Official MCP Registry Local
- ChimeraForge
io.github.Sahil170595/chimeraforgeLocal-first LLM deployment planner: GPU/VRAM sizing, cost and latency, with provenance
Version check not run yet
DevOps and infrastructure Official MCP Registry Local
- Agent Intern
io.github.SinanTufekci/agent-internDelegate from Claude Code to Gemini, Codex, Copilot, Cursor and opencode CLIs as sub-agents.
Version check not run yet
Model and agent tools Official MCP Registry Local
- Elite Reasoning
io.github.Snehgabani/elite-reasoning-mcpEvidence-gated verification, selection, and measurement MCP for coding agents.
Version check not run yet
Coding agent tools Official MCP Registry Local
- Being Human
io.github.Syedomershah99/being-humanLearns your writing voice from your own prompt history, then makes the model write like that.
Version check not run yet
Design and media Official MCP Registry Local
- Ai Consensus
io.github.TheStevenJohnstone/ai-consensusStanding review layer for coding agents: Claude, GPT and Gemini debate, return consensus + dissent.
Version check not run yet
Model and agent tools Official MCP Registry Local
- Fuuga minion
io.github.Thorium/fuugaOffline local-LLM helper: delegate simple errands to a local model, with sandboxed file tools.
Version check not run yet
Files and storage Official MCP Registry Local
- Engram
io.github.TushaeBXN/engramLocal, private long-term memory for AI: verbatim, searchable, correctable. No LLM or API key.
Version check not run yet
Memory and context Official MCP Registry Local
- Attestix
io.github.VibeTensor/attestixAI agent identity, signed credentials, delegated authority and governance evidence.
Version check not run yet
Model and agent tools Official MCP Registry Local
- Humane Proxy
io.github.Vishisht16/humane-proxyAI safety middleware — detects self-harm and criminal intent in LLM prompts.
Version check not run yet
Model and agent tools Official MCP Registry Local
- Benchwarmers
io.github.WendellResearch-AI/benchwarmersAsk a collection of LLMs at once through your Benchwarmers server; verdicts pick the next panel.
Version check not run yet
Model and agent tools Official MCP Registry Local
- Forgejudge
io.github.ahmedEid1/forgejudgeOpen eval leaderboard + CI gate for autonomous coding agents (solve, score, trace).
Version check not run yet
Coding agent tools Official MCP Registry Local
- defluff
io.github.ahmedak/defluffDeterministic prose linter for LLM text — flags AI slop, filler, buzzwords, hedges, clichés.
Version check not run yet
Developer tools Official MCP Registry Local
- Arcus Agent Gateway
io.github.alekskram/arcus-agent-gatewayRead-only MCP gateway to 194 tokenized US equities on Robinhood Chain: quotes, holders, whale moves.
Version check not run yet
Model and agent tools Official MCP Registry Local
- Aster Agent Gateway
io.github.alekskram/aster-agent-gatewayRead-only MCP gateway to Aster DEX: 24/7 gold, oil and equity perps, funding with real intervals.
Version check not run yet
Model and agent tools Official MCP Registry Local
- dYdX Agent Gateway
io.github.alekskram/dydx-agent-gatewayAnalytics-only MCP gateway to dYdX v4: auditable trader PnL, funding and OI detectors. No keys.
Version check not run yet
Data warehouses and analytics Official MCP Registry Local
- datoon
io.github.andrii-su/datoonSmart structured-data to TOON gateway: converts to TOON only when it saves LLM tokens.
Version check not run yet
Model and agent tools Official MCP Registry Local
- SYNAPSE CHANNEL
io.github.anulum/synapse-channelLocal-first multi-agent coordination for messages, leases, shared plans, status, and resources.
Version check not run yet
Model and agent tools Official MCP Registry Local