plug.directory
Add my server

Model and agent tools MCP servers

8,819 servers

Call other models, run sub-agents, manage prompts and evaluate outputs.

Filter and sort these servers

Start from the first servers

  1. JevLint-LE io.github.nolindnaidoo/jevlint-le

    Lint questions for TypeSafe's Jev and OpenAI's Luna offline, or ask the model itself with your key.

    Version check not run yet

    Developer tools Official MCP Registry Local

  2. IRL Gateway io.github.norve-labs/irl-gateway

    An AI agent's trading mandate it can't break: checked before every order, reasoning sealed in IRL.

    Version check not run yet

    Model and agent tools Official MCP Registry Local

  3. pepe io.github.omarmhaimdat/pepe

    Load-test a URL, ping it by phase, ramp to find the capacity, compare runs: JSON reports, guardrails

    Version check not run yet

    Utilities Official MCP Registry Local

  4. Perforce Agentic Gateway io.github.perforce/perforce-agentic-gateway

    Local MCP gateway that proxies AI clients to many MCP servers with a token-efficient code mode

    Version check not run yet

    Model and agent tools Official MCP Registry Local

  5. TokenSqueezer LLM Token Compressor io.github.pgalyen1987/tokensqueezer

    x402-gated LLM token compressor: strip filler, collapse JSON, densify prose. Paid in USDC.

    Version check not run yet

    Model and agent tools Official MCP Registry Local

  6. Aria io.github.pkotecha-eng/aria-mcp-server

    Search 35M+ PubMed, 400K+ ClinicalTrials.gov & ISRCTN trials. Prompts included. No API key.

    Version check not run yet

    Model and agent tools Official MCP Registry · PyPI Local

  7. thread-keeper io.github.po4erk91/thread-keeper

    Multi-agent shared brain across Claude, Codex, Antigravity, Gemini, Copilot, and VS Code.

    Version check not run yet

    Model and agent tools Official MCP Registry Local

  8. Vibedonate io.github.pooriaarab/vibedonate

    BitTorrent-style mesh for AI inference across agentic CLIs. Local-first.

    Version check not run yet

    Model and agent tools Official MCP Registry Local

  9. Llmstxt Doc Search io.github.praveenc/llmstxt-doc-search

    BM25 search over llms.txt doc indexes (Strands, Kiro, AWS); sources addable at runtime.

    Version check not run yet

    Cloud platforms Official MCP Registry Local

  10. ProvenTools io.github.proventools/proventools

    Read-only ProvenTools business ideas, evidence, build prompts, and validation reports.

    Version check not run yet

    Model and agent tools Official MCP Registry Local

  11. Local Coding Agent io.github.pvnc228/local-coding-agent

    Delegate small coding tasks to local Ollama/llama.cpp models; patches gated by real test runs.

    Version check not run yet

    Coding agent tools Official MCP Registry Local

  12. Qsp Client io.github.qso-graph/qsp-client

    QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)

    Version check not run yet

    Model and agent tools Official MCP Registry Local

  13. Graqle io.github.quantamixsol/graqle

    Graph-powered codebase reasoning, impact analysis, and governance tools over MCP.

    Version check not run yet

    Developer tools Official MCP Registry Local

  14. Llm Kosh io.github.rastogivaibhav/llm-kosh

    Local-first AI memory cartridge with persistent MCP memory for Claude via SQLite FTS5.

    Version check not run yet

    Model and agent tools Official MCP Registry Local

  15. Baton io.github.ribato22/baton

    Multi-model AI orchestration: plan a task DAG, route each task to the best capable model.

    Version check not run yet

    Project management Official MCP Registry Local

  16. devmcp io.github.rudranaresh0201/devmcp

    Git/CI MCP server with the full protocol surface (tools, resources, prompts, roots, sampling).

    Version check not run yet

    Model and agent tools Official MCP Registry · PyPI Local

  17. verimcp io.github.rudranaresh0201/verimcp

    Transparent MCP proxy that independently re-verifies tool-call claims before the Host trusts them.

    Version check not run yet

    Model and agent tools Official MCP Registry · PyPI Local

  18. Modelcostsaver io.github.sachinuppal/modelcostsaver

    Offline MCP: predict LLM call cost and pick the cheapest capable model. No keys, no network.

    Version check not run yet

    Model and agent tools Official MCP Registry Local

  19. Almanac io.github.savecharlie/almanac

    Verified ephemeris & WMM2025 geomagnetic compute: the physical numbers LLMs hallucinate, done right.

    Version check not run yet

    Model and agent tools Official MCP Registry Local

  20. Deus Witness io.github.sipkigroup/witness

    MCP proxy: holds risky tool calls for passkey approval; signed receipts you can check offline.

    Version check not run yet

    Model and agent tools Official MCP Registry Local

  21. Magg io.github.sitbon/magg

    Aggregates and proxies other MCP servers, letting LLMs discover, add, and manage tools at runtime.

    Version check not run yet

    Model and agent tools Official MCP Registry Local

  22. LLMVerify io.github.subodhkc/llmverify

    Local-first MCP server for LLM output verification — risk signals, injection and PII checks.

    Version check not run yet

    Security Official MCP Registry Local

  23. agent-custody io.github.svayatta/agent-custody

    MCP gateway that checks each agent tool call against a signed grant and policy, and signs a receipt

    Version check not run yet

    Model and agent tools Official MCP Registry Local

  24. Synapbus io.github.synapbus/synapbus

    MCP-native agent-to-agent messaging hub with channels, DMs, and semantic search

    Not checked yet

    Communication and chat Official MCP Registry · Go modules

  25. Overllm io.github.theadamdanielsson/overllm

    Find the LLM/AI calls you didn't need — where plain code or a regex does the job. No model.

    Version check not run yet

    Developer tools Official MCP Registry Local

  26. EvalForge Lite io.github.thejaredchapman/evalforge-lite

    Compare text LLMs across OpenRouter, Bedrock, Vertex AI and Foundry with automated grading.

    Version check not run yet

    Model and agent tools Official MCP Registry Local

  27. Agentrisk io.github.trycoin-ai/agentrisk

    Risk guardrails for AI trading agents. Your agent proposes; your policy decides.

    Version check not run yet

    Model and agent tools Official MCP Registry Local

  28. Mem io.github.turbyho/mem-context

    Temporal memory MCP server with LanceDB vector search, weight-decay scoring, and LLM consolidation

    Version check not run yet

    Search and retrieval (RAG) Official MCP Registry Local

  29. unerr io.github.unerr-ai/unerr

    Operational memory for AI agents: code graph, session memory & guardrails. No context rot.

    Version check not run yet

    Memory and context Official MCP Registry Local

  30. MCP-Bastion io.github.vaquarkhan/mcp-bastion

    Security middleware for MCP. Blocks prompt injection, PII leakage, and resource exhaustion.

    Version check not run yet

    Security Official MCP Registry · PyPI Local

  31. Vizier Guard io.github.vassiliylakhonin/vizier-guard

    Deterministic authorization and security guard for AI agent actions with signed receipts.

    Version check not run yet

    Security Official MCP Registry Local

  32. VMware Pilot io.github.vmware-skills/vmware-pilot

    Multi-step workflow orchestration for VMware MCP skills with approval gates and rollback.

    Version check not run yet

    Model and agent tools Official MCP Registry Local

  33. LLM Sandbox io.github.vndee/llm-sandbox

    Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.

    Version check not run yet

    Model and agent tools Official MCP Registry · PyPI Local

  34. Vouch io.github.vouchdev/vouch

    Git-native, review-gated knowledge base for LLM agents. Cited retrieval, audited writes.

    Version check not run yet

    Git and code hosting Official MCP Registry Local

  35. NovAI - Chinese AI Models Gateway io.github.vvvvking/novai-python

    Chinese frontier AI models as MCP tools via one OpenAI-compatible endpoint, zero platform fee.

    Version check not run yet

    Model and agent tools Official MCP Registry Local

  36. Data Cleaner Agent io.github.wesseltl/data-cleaner-agent

    Clean messy CSVs: an LLM picks the steps, tested code does the work. Data untouched by the model.

    Version check not run yet

    Office documents and spreadsheets Official MCP Registry Local

  37. Polis Protocol io.github.yehudalevy-collab/polis-protocol

    Local-first control plane for coding agents: routing, reservations, and guardrails.

    Version check not run yet

    Coding agent tools Official MCP Registry Local

  38. Agent Foundry io.github.youcisla/agent-foundry

    Skill orchestrator: plan, execute, verify skills over MCP stdio.

    Version check not run yet

    Model and agent tools Official MCP Registry Local

  39. VMware Pilot io.github.zw008/vmware-pilot

    Multi-step workflow orchestration for VMware MCP skills with approval gates and rollback.

    Version check not run yet

    Model and agent tools Official MCP Registry Local

  40. Usage Planner io.github.ItsOdeLeo/usage-planner

    Plan OpenAI Codex usage from local quota, banked resets and extra-reset forecasts.

    Version check not run yet

    Model and agent tools Official MCP Registry · npm Local MIT

  41. dsh-baton io.github.JialaoLiu/dsh-baton

    Hand tasks from Claude Code, Codex or any MCP client to a local DeepSeek Harness.

    Version check not run yet

    Project management Official MCP Registry · npm Local MIT

  42. Localize io.github.JoblessJoe/localize

    Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.

    Version check not run yet

    Files and storage Official MCP Registry · npm Local MIT

  43. Conector io.github.Secra-Solutions/conector

    Self-hosted MCP gateway: connect 1,178 apps once and use them from any AI agent.

    Version check not run yet

    Model and agent tools Official MCP Registry · npm Local MIT

  44. AI Stupid Level io.github.StudioPlatforms/aistupidlevel

    LLM benchmark rankings, drift status, incidents and Smart Router previews from AI Stupid Level.

    Version check not run yet

    Monitoring and observability Official MCP Registry · npm Local MIT

  45. AgentGate io.github.agentgate-builder/agentgate

    Check if an AI agent is registered, Active and Verified in the Concordium Agent Registry (CIS-8004).

    100% up · 30 days

    DevOps and infrastructure Official MCP Registry · npm Remote MIT

  46. InjectScan io.github.agentgate-builder/x402-prompt-injection-scan

    Prompt-injection scanner for agents: risk score, categories and spans for text, pages, MCP tools

    100% up · 30 days

    Model and agent tools Official MCP Registry · npm Remote MIT

  47. Buildagents io.github.aurimasAPG/buildagents

    Design AI agent teams for a business problem and generate ready-to-paste Claude Code prompts.

    100% up · 30 days

    Model and agent tools Official MCP Registry · npm Local Remote MIT

  48. seekfetch io.github.esticklack/seekfetch

    Unofficial MCP server for the DeepSeek Search & Fetch API: web search and page-to-Markdown.

    Version check not run yet

    Web search and scraping Official MCP Registry · npm Local MIT