- 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.
Excel Sovereign MCP
Local Excel MCP. The server chooses openpyxl or Excel COM, then screenshots the write. 本地 Excel MCP，服务端选择 openpyxl 或 Excel COM，写入后截图核对。
Next Skill Router
Cost-aware, local-first skill routing for AI agents. MCP server + CLI + Claude Code hook. Tested on 141 real skills.
Dendrite Admin MCP
Agent-installable MCP server for administering a Dendrite Matrix homeserver — manage users, rooms, registration tokens, server notices, and full-text search from any MCP-capable A…
Awesome AI Agent Tool Registry
Top AI Agent Tool Registry (Opensource) 🌟 Star if you like it! 🌟
Tato Runtime
The hands of an AI agent.
On Page Seo MCP
On-Page.ai SEO MCP server for search engine optimization work with Codex and Claude Code. Public docs, examples, and directory metadata for the hosted server.
Crewchat
A group chat for your AI coding agents and you: an MCP server with a live chat page. One Python file, no dependencies.
Payforapi
Saymon RU Data API — Russian-language data endpoints for AI agents: EGRUL/INN company check, Cyrillic search, research, Russian Post tracking. Pay-per-call via x402 in USDC (Base)…
Canli Research MCP
MCP server for an open quant research record: every paper, killed candidate and trial count, the live paper record and the chain that shows it was not rewritten. On npm and hosted…
Awesome AI Seo Agents
AI SEO agents 2026: which ones you can actually drive from code. Every MCP server and API checked against the vendor's own repo, with dates.
Acqpath Distribution
Check declared content rights before RAG, AI input, summarization, training or indexing. Signed RSL evidence via HTTP x402; no legal clearance.
Canli Validation MCP
MCP server that checks a backtest before you trust it: deflated Sharpe, backtest-overfitting (CSCV), paper-evidence and breadth, with recomputable receipts. npm, MCP Registry, and…
Markdown Memory
MCP server that hands coding agents the one Markdown section that answers the question, not the whole file. Local hybrid search: BM25 keywords + ONNX embeddings in SQLite. No API…
Jev Codex Router
Experimental TypeSafe Jev model routing for Codex Desktop: per-task model and reasoning selection, complex-task planning, subagent dispatch, and fallback.
Vigia
What breaks when you upgrade npm packages — verified, dated facts for AI agents: breaking changes between versions, per-version vulnerabilities, compatible versions. REST + MCP se…
CityScope
Evidence-grounded geospatial intelligence for London cycling, powered by Gemini, MCP, and Google Cloud.
Allbrain MCP
AllBrain MCP runtime, governance, and event-driven multi-agent orchestration core.
Behavry Proxy
Inline MCP governance proxy — OPA/Rego policy enforcement, DLP scanning and prompt-injection detection on every tool call, before it executes.
Vnc MCP Server
MCP server for VNC integration. Allows AI agents to capture screen frames, send keyboard/mouse events, and manage remote desktop sessions through a standardized interface.
Monica
Keep tabs on the browsers your AI agents drive — watch every session live and take over any tab. One desktop app, every pane a CDP target.
Claude AWS Architect
Claude Code plugin for AWS Well-Architected SDLC — multi-agent system design grounded against AWS docs via MCP. 5 agents, 6 MCP servers, 15 skills, 34 validation gates.
Verifiable Memory
Verifiable memory for AI agents — 0% hallucination, cited answers or honest abstention, provable forgetting, deterministic. MCP server. CPU-only, no GPU.
Essaim
Spawn N coordinated Claude Code agents — orchestrator + behavior catalog. Pairs with @swoofer/promptweave + mcp-coordinator.
CSA Obsidian
Python browser automation with Camoufox, session persistence and a 17-tool MCP server. CLI and Python API for authorized QA, accessibility and agent evaluation.
Desktop Assistant Agent
A modular Python AI agent runtime with routing, planning, skill selection, tool execution, approval-aware safety controls, recovery, replanning, MCP integration, deterministic eva…
Rldyour Claudecode
rldyour AI CLI configuration for Claude Code: plugin marketplace, MCP/LSP, Serena memory, security review, browser/design workflows, and reviewer agents.
Gcf Kotlin
GCF Kotlin implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.
Dsh Codebase Memory MCP
Codebase Memory MCP bridge plugin for DeepSeek Harness: knowledge-graph code search, AST snippets, architecture analysis, call-graph tracing, auto-started graph UI, bundled skill,…
Espeon
MIT-licensed experimental Windows workbench for AI-assisted cTrader trading research (MCP, Open API, FIX).
Fomo MCP API
FOMO social-trading data for AI agents: hosted StalkChain MCP and REST API guides for tracked wallets, token research and live flow.
Qianyuan Protocol
QianYuan Protocol — trust & result-reuse layer for AI agents (MCP).
Dcc MCP Sketchup
SketchUp MCP adapter for AI agents to inspect and edit models, manage materials, Tags and scenes, validate geometry, and export assets through the DCC-MCP gateway.
Tmux Agents
MCP server that lets one AI agent launch, watch and steer coding agents (Claude Code, Codex, Hermes, aider) in tmux panes
Hecate Public
Security scanner and runtime guard for MCP servers and AI agents. Runs entirely on your machine.
Corescout
Local-first Rust service that watches how your machine and your AI coding agent work together, tests what it notices with randomized trials, and serves the verified lessons back t…
Repro Gate
Action-bound authorization and verifiable evidence contracts for MCP tool execution
Petty Memory
One memory for you and every AI you use. Local-first links, notes, files and decisions, shared with Claude, Codex and any MCP client.
Mrcp Engine
Deterministic AST code-intelligence engine for AI agents — MCP server + REST API for architecture analysis, security audits, and doc generation.
ApexGraphSwarm
Local-first graph intelligence and multi-agent orchestration workbench with GraphRAG integrations, specialist swarm design, evaluation, and cost-aware delegation.
NexusWallet
Spending-policy wallet for AI agents on Solana: agents propose payments over MCP, an owner-set policy signs, escalates or denies; multi-step tasks use an on-chain Anchor capabilit…
Nyquist
A crypto wallet for autonomous agents. Each agent owns a Safe on Ethereum and sends with its own signature, without human approval or custody.
Agent Authority Check
FOXIFY deterministic authority preflight for MCP servers and AI agents: bind authority, inspect consequence, preserve evidence.
Claude Multicloud Lab
Hands-on lab series for deploying and building with Claude across AWS Bedrock, Google Vertex AI, and Azure AI Foundry
Qwen Playwright MCP Agent
A local AI browser agent built with Qwen3, Ollama, TypeScript, and Playwright MCP
TemporalThread
Give AI agents a persistent sense of time.
Knovaryn
Open, MCP-native training-data foundry: turn permitted documents into traceable, quality-gated SFT and preference datasets.
Attendai
AI-driven attendance management via MCP - mock college portal + audited AI agent tools (check/mark attendance, rosters, class summaries)
Chrome Tab Remote
Let an AI agent see exactly one browser tab — the one you chose, for as long as you allow, and nothing else. Trust-first Chrome/Brave extension + local MCP bridge.
Traces
A session replay engine an AI agent can interrogate. 17 WebMCP tools: it binary-searches the timeline for the millisecond a bug began, then tells you what it cannot see and asks y…
Spend Guard
Wrap any MCP server with a hard spend cap, per-tool rate limits, a wall-clock timeout and a kill switch. MCP has no built-in rate limiting - this is the drop-in stdio proxy that a…