- Conduid
- Marketplace
- #tool-use
MCP servers tagged tool-use
210 live MCP servers tagged "tool-use", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with tool-use.
Ronnyx
A flexible AI assistant framework with tool-based orchestration and API interface.
Hpml Assetopsbench Smart Grid MCP
SmartGridBench: a smart-grid transformer-maintenance benchmark for tool-using LLM agents, built on IBM AssetOpsBench with MCP/direct-call tool surfaces.
Lmcp Demo
MCP (Model Context Protocol) server: tool integration, context management & hallucination-safe AI agent pipelines
Evidence Normalizer
men (MCP Evidence Normalizer) — deterministic normalization of MCP tool results into clean, bounded evidence.
Edge Mhs
A Fastly Compute reference for AI agents controlling physical hardware over Anthropic's Model Hardware Standard
Practice AI Agent
A CLI AI agent built stage by stage in TypeScript — tool use, MCP client & server, persistent memory, and a researcher sub-agent, powered by the Claude API.
Open Toolset Protocol
Open Agent Toolset Protocol (OATP) - universal spec for AI agent tool discipline, structural instrumentation, and deterministic execution. Vendor-agnostic interop layer for availa…
Self Improving Agent
Terminal coding agent that executes tools (real think>tool>result loop with confirm + undo, MCP tools in-loop) and rewrites its own system prompt from feedback with metrics + auto…
Chatty
A minimalist, local-first AI assistant for your terminal. Powered by Ollama, it executes Python code to solve problems and interact with tools via the MCP specification.
Project Systemu
An open-source AI agent that builds the tools it's missing, mid-task — under your governance. Pull capabilities at runtime instead of pre-wiring them. Local-first, MIT.
Minion CLI
A terminal-native agentic coding harness built from scratch — streaming ReAct loop with reflection and planning, MCP/A2A protocols, cross-session semantic memory, subagent orchest…
Keep Protocol
🦀 Signed protobuf packets over TCP for AI agent-to-agent communication. ed25519 identity. Claw to claw.
Agentic Patterns Book
История AI-агентов — это история решения ограничений нейросетей. Нет памяти? RAG и context engineering. Не может действовать? Tool Use и MCP. Ошибается? Reflection и CI feedback…
Compliance Watch
Contract and invoice compliance auditor built with Claude API. Hybrid RAG, tool use, MCP server, prompt evaluation, extended thinking. Full pipeline — not a chatbot.
AgentRX
AgentRX diagnoses AI tool-chain failures and prescribes the next best action. Covers skills, MCP servers, plugins, built-in tools, agents, workflows, and hooks. Task-first, not to…
Mochikit
A modern, plugin-driven TypeScript AI Agent framework. 44 core files, strict TS, zero boilerplate.
Agent Accelerator
A flexible framework that helps AI agents to connect seamlessly with real world data and tools using the Model Context Protocol
Thinklys
RAG-based learning platform with a TypeScript agentic layer: custom MCP server exposes user-scoped tools over uploaded documents; a Claude tool-use agent drives them, with prompt…
Spotter
Audit agent for Claude Code that catches missed tool calls — separates spotting from doing. Your Claude answers, Spotter watches.
Secure Gateway
A hardened Model Context Protocol gateway with auth, tool allow-listing, output validation, and audit logging
Tool Output Spoofing Lab
Benchmarking schema-valid false tool observations and defense baselines for tool-using LLM agents.
Rtrace Agent Reliability
R-TRACE: Stateful agent evaluation and release reliability with reproducible Windows GPU evidence.
Toolforge MCP
Cost-disciplined MCP client agent with a deterministic 5-rule tool-selection heuristic and first-class dry-run.
Document MCP Server
A FastMCP-based document server that exposes files as MCP resources and tools for AI-powered document retrieval and search.
Tool Schema
Convert any JSON Schema into a valid tool / function calling schema for OpenAI, Anthropic, Gemini and MCP. Zero dependencies.
Aobench
Role-aware, permission-enforced benchmark for LLM agents that operate HPC systems — SLURM, telemetry, RBAC, docs, facility. A policy violation hard-fails the task. 88 tasks (10 ca…
AdoptViaAI
Claude API CLI demonstrating all 5 CCA-F certification domains — chat, tool use, agents, MCP, and safety guardrails in a single production-pattern tool.
Document Adapter
LLM이 DOCX/PPTX/HWPX 문서를 직접 편집할 수 있게 해주는 통합 어댑터 + MCP 서버. Claude Desktop / Claude Code / Anthropic API Tool Use 호환. pip install document-adapter
Agent Anatomy
Interactive visualization of LLM agent internals — real API message flow (tool_use, tool_result, MCP, Skills). Agent Engineering = Context Engineering.
Agentspace
A local agent runtime & workspace — a tiny agent OS in your shell. Natural-language orchestration, MCP tools, and agents that write their own tools & agents (via PI). Built from s…
Records Demo
A generic MCP server showing safe agent access: typed read/write tools, writes disabled by default, structured errors, and tests. Swap the store for a real API to make it a produc…
LMStudio Windows 11 Controller
This is a smart desktop controller that allows smaller LLM (8B 20B) GGUF to controll the Windows 11 desktop.
Why Research
Recursive research intelligence that gets smarter every time you use it. MCP server + CLI + REST API. Prediction-error learning, surprise detection, persistent brain.
Liteagent
A native, single-user, local-model-first AI agent. Works with any OpenAI-compatible endpoint (Ollama, vLLM, LM Studio) — full tool-calling loop, MCP client, memory, scheduler, and…
LLM Tool Use Patterns
Production-oriented patterns for LLM agents with tool use in Python. Guard rails, state, observability.
Openworkflow
Open-source alternative to Claude Code's hidden multi-agent Workflow tool. Fan out dozens of subagents from one Python script and keep only the final answer in context. Runs stand…
Governed Metrics MCP
An MCP server demonstrating the governed metrics layer pattern: an LLM accesses curated metric definitions as tools instead of writing raw SQL against a database.
Mynd Skill Forge
MYND Skill Forge — Platform for creating and managing AI agent skills. Build, test, and distribute skills for AI agents with MCP tool integration.
Agents Galore
25 runnable agent pattern demos on the Anthropic SDK — from tool-calling to fleet orchestration, safety, and production backends.
Tool Lint
CLI linter for AI tool definitions — validates MCP, OpenAI, and Anthropic schemas
Datalox Gated Runtime
Stateful, resettable, verifiable API worlds for tool-using agents.
Tool Using Agent Builder
Skill Codex xây dựng Tool-Using Agent end-to-end: kiến trúc, security, quality gates, kiểm thử behavioral và operability.
Spendiq Prototype
Conversational AI copilot over procurement, AP, and contract data — grounded answers with citations to specific rows and clauses. Built for the TechTorch AI & Data Engineer challe…
Tool Safety Lab
Public-safe MCP-style tool safety lab with permission gates, approval boundaries, schemas, audit logs, and CI tests.
Pydantic AI Apcore
expose apcore modules as pydantic-ai tools via the `AbstractToolset` interface.
Sael
Sael — a streaming-first protocol for AI agent ↔ tool communication. The successor to MCP. By Unyly.
Blastdoor
Blast radius control for autonomous agents: capability boundaries, dry-run by default, verifiable kill switches, and an audit trail for every mutation.
Guarded Tools
MCP server treating a large tool surface as a governance problem: tool-search discovery, request and token budgets, human-in-the-loop confirmation for writes, and an append-only a…
Servers And Agents
Your integrated AI/Agents/MCP environment: server definitions, tool contracts, prompt routing, and safety guardrails.
Autonomous AI Agents
Deep dive into enterprise-grade AI Agents & Advanced RAG. Implementing MCP architecture, hierarchical indexing, query transformation, ReAct loops from scratch, and multi-agent sta…