- Conduid
- Marketplace
- #ai-agents
MCP servers tagged ai-agents
15K live MCP servers tagged "ai-agents", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with ai-agents.
Skinki
Local-first memory engine for AI agents — on-device, 0 network, embeddable anywhere via a stable C-ABI + MCP. Honest benchmarks, including the parts that failed.
AnB MCP
MCP server front-end for AnB — let AI agents use secrets without ever seeing the plaintext. Go + official MCP go-sdk; security logic delegated to alice (redaction, exec allowlist,…
Rss Feeder
TypeScript-native RSS and JSON feed reader with a built-in MCP server for AI-agent workflows.
Freigent Plugin
Claude plugin for the Freigent back office — triage your AI work queue, look up loads & carrier authority, and approve/reject tasks with money-movement guardrails.
Fleet Mode
A measured doctrine for orchestrating AI agents — and knowing when not to. Runs as a live Claude Code skill.
Accelerate Site
Self-hosted CRM and AI operations for service businesses. Agents propose, humans approve, everything traces. Open over MCP.
Agent 3md
🗃️ Your whole agent in one file. A 3md document where plane 0 is the agent and every other plane is a skill, loaded on demand.
Manas
Modular agent infrastructure in Rust — memory, perception, coordination, planning, code intelligence for LLM workflows
Mnemo Plugin
Universal memory plugin for OpenCode and Claude Code - bridges to mnemo-mcp via MCP protocol
Claude Castor
Offloads large-context work like file exploration, indexing, summarization, deep research — to Google’s free Antigravity CLI (agy), the terminal coding agent powered by Gemini mod…
Umb
MCP gateway: one Rust binary fronts every MCP server, cutting tool context ~99% via a 3-tool API. Source-available.
Agent Tool Intel
The quality standard for AI agent tools. 39,752+ MCP servers scored. Semantic search, trust engine, execution analytics. Built for agents, transparent for builders.
FlyupMem
Local-first memory layer for AI agents: YAML source of truth, rebuildable SQLite search cache, CLI, MCP, OpenClaw, and Hermes.
AI Hands
Multi-layer desktop automation for AI agents — browser CDP, Windows UIA, vision/OCR. Successor to AIWander/hands.
Llmlang
A high-performance, token-efficient language designed for LLMs as coders. Features a Rust/LLVM JIT compiler, native SoA memory layout, SIMD auto-vectorization, stack-aware paralle…
AutoDS Copilot
A no code AI data science copilot. Point it at a spreadsheet and it runs the whole machine learning workflow, then explains the result in plain language. Built with scikit learn,…
AgenticRelay
Coordination layer on MCP for teams running AI coding agents on the same repo: shared awareness and reviewable memory across developers, machines, and agent vendors.
Reli
On-ramp to East Africa's MCP coordination stack — install, wire, verify, and demo 30+ Kenya-domain MCP servers in one command.
Anthropic RAG
Self-hosted, always-fresh RAG pipeline over the Anthropic GitHub org — grounded, cited Q&A over docs + issues/PRs/comments, refreshed hourly and served to AI agents over an MCP se…
Praxa
Open-source TypeScript SDK, CLI, and MCP contracts for governed AI agents and the Praxa agentic harness.
XfeaturesAthenaeumMCP
Model Context Protocol integration for Xfeatures Athenaeum: connection guide, auth configuration and client examples. The MCP server itself lives in the Athenaeum core repository.
Dataaihub Cookbook
Runnable reference implementations for AI engineering — RAG, AI agents, MCP, and RDF/Knowledge Graphs.
Sessionbridge
Human-in-the-loop browser sessions for MCP clients using Playwright and Chrome DevTools Protocol.
Unified MCP Core Starter
An Java framework that turns your Spring Boot application into a fully compliant Model Context Protocol server for seamless LLM integration.
Py Agent Framework
Stateful LLM agent framework on pydantic-ai: session persistence, context-window management, and a lifecycle extension system for tools and skills.
Claude Code Shared Memory
Persistent cross-project memory for Claude Code — no Obsidian, no vector DB, no external app to keep running. remember plugin + shared fact files + MCP knowledge graph.
Guardbench
Check your MCP servers for tool poisoning and rug pulls, and benchmark MCP security tools under verifiable conditions.
CatalogLock
Security gate and deterministic lockfile for Agentic Resource Discovery (ARD) catalogs. Protect AI agents from SSRF, authority drift, poisoned discovery metadata and agentic suppl…
Dcc MCP Renderdoc
RenderDoc capture and replay automation for the DCC Model Context Protocol ecosystem
Upwork MCP CLI
A CLI + Python wrapper for the Upwork MCP server — search jobs, competitor bids & client history, score gigs, draft AI proposals, and automate Upwork (n8n, cron, Slack, and more).
Cognition
A Discord system where behavior lives in a live registry and can be managed through MCP.
Ciphergate
Self-hosted secrets manager with REST, CLI and MCP surfaces. Encrypted at rest, per-consumer scoping, and a proxy that gives AI agents credentials without letting them hold one.
Verglas
Rule-bound vaults for AI agents on Avalanche - spend inside hard on-chain rules, prove compliance with a ZK proof, carry the ERC-8004 attestation to any L1 over ICM. Console, SDK…
Agent Scale
Connect AI coding agents to remote test machines for commands, file transfer, private services, and MCP—over authenticated iroh P2P.
Ethogram
Open-source behavioral contract testing for AI agents. Define critical behavior, run the real agent, and catch regressions.
Autocad Mechanical Harness
Safety-first deterministic 2D mechanical CAD automation for AutoCAD over MCP, with preview, approval, and readback.
LNSAT
Open-source, pre-release source for policy-governed AI-agent authorization, scoped human approval, audit evidence, and read-only MCP adapters.
IBM MQ MCP Server
Production-oriented MCP server for safely inspecting and operating multiple IBM MQ environments with per-profile least-privilege capabilities.
Mooting
Claude Code, Codex and Copilot in one shared council — CLI coding agents debate over MCP, and a human rules every decision. Terminal UI, no API keys.
Fa Workspace
AI-ready developer workspace for FastAPI microservices—shared architecture, agent instructions, Dev Containers, MCP/Headroom, and secure cross-platform tooling for Codex, Claude C…
Supermem
Personal super-memory graph — a shared execution layer for agents and people. MCP-first, Turso/libSQL backend, local free embeddings, hybrid graph+vector+keyword recall.
Style DNA Ghostwriter
Learn a codebase's unwritten conventions (Python, React, Next.js, TypeScript, Tailwind) and condition AI coding agents (Claude Code, Cursor, Google Antigravity, Windsurf, Copilot,…
Switchboard MCP
Let your Claude Code (CLI) agents talk to each other — a local hub that connects independent agents in tmux via MCP, with a web dashboard. Windows + WSL.
Qedra
A runtime gate for coding agents: an MCP server that blocks the tool calls that wreck a repo (force-push main, rm -rf, secret exfil, CI wipe) and lets real work through. Machine-c…
Claude Gtm Skills
How one founder runs a B2B GTM function on Claude Code: 14 skills, 4 MCP servers, 14 scheduled agents. The architecture, the memory layer and the cron layer, sanitized.
Mascotlab MCP
Generate your app's mascot from Claude Code, Cursor and other MCP clients. Hosted MCP server at mascotlab.io
Easyquotes
Market data API, Python SDK & MCP for A/HK/US stocks — ETF holdings, fund portfolios & institutional positions. A股/港股/美股行情 API、Python SDK 与 MCP，支持 ETF 持仓、基金组合和机构持仓。
Claude Kimi Relay
Claude Code plugin that delegates code review, adversarial design critique, and isolated implementation to Kimi Code over the Agent Client Protocol (ACP). Security-first: Kimi wor…
Chilecule
Agentic drug discovery workflows on fully open-source tooling: RDKit, AutoDock Vina/smina, fpocket, ChEMBL. MCP tool servers + Claude agents, with a retrospective validation harne…
D2 MCP Rs
Rust MCP server for safe D2 diagram rendering from AI agents