Explore server capabilities, recorded tools, available client configurations and practical setup considerations. Browse servers by category, or jump to remote servers and official vendor servers.
Servers can appear in several categories when their tools support several tasks. Category counts include these overlaps; the directory total counts each server once.
984 servers
2205 servers
8565 servers
1403 servers
598 servers
2659 servers
1883 servers
1983 servers
1735 servers
2501 servers
1236 servers
1603 servers
327 servers
965 servers
67 servers
74 servers
937 servers
124 servers
310 servers
1303 servers
561 servers
1525 servers
317 servers
392 servers
908 servers
107 servers
243 servers
391 servers
205 servers
1068 servers
626 servers
1194 servers
825 servers
712 servers
322 servers
383 servers
242 servers
400 servers
172 servers
155 servers
259 servers
238 servers
577 servers
560 servers
127 servers
832 servers
112 servers
123 servers
676 servers
456 servers
966 servers
253 servers
93 servers
358 servers
329 servers
315 servers
254 servers
781 servers
160 servers
233 servers
51 servers
400 servers
247 servers
286 servers
199 servers
182 servers
172 servers
308 servers
381 servers
184 servers
45 servers
216 servers
154 servers
269 servers
48 servers
30 servers
21 servers
27 servers
33 servers
133 servers
46 servers
17 servers
43 servers
95 servers
60 servers
20690 servers
AgentBridge is a native Classic Mac OS application that lets AI agents (like Claude) interact with Mac OS 7–9 through structured commands and responses. It works on real hardware and emulators — no modifications to…
Give your AI agent an identity: its own email, webhook, repo, secrets vault, memory and skills.
An agent-callable MCP server that lets autonomous AI agents find, verify, message, schedule with, and transact with small and mid-sized businesses (SMBs) through a single compliance-enforced tool…
Self-hosted Chrome for AI agents, with a live noVNC view a human can take over.
Budget-aware AI agent research router with provider selection, validation, and automatic fallback.
Deploy full-stack AI agent apps with database, auth, storage, and Edge AI on one platform.
Deploy full-stack web apps with database, file storage, auth, and RBAC via a single API call.
Free AI-readiness audit of any URL: AI crawler rules, JS-free text, JSON-LD, llms.txt. Tool catalog.
Local profiler: which usage window took you out, and where your agent's money goes
Durable addresses and crash-safe FIFO mailboxes so AI agents message each other, free.
Search public conversations, choose a reply, and optionally subscribe to signed reply notifications.
Local-first agent memory: an Obsidian markdown vault as source of truth, with a rebuildable DuckDB index.
Paid replay-safe callback inboxes for asynchronous agent tasks with structured MCP results.
Retired compatibility stub for AgentCanary MCP. Daily briefs continue on X and Telegram.
AI-designed App Store screenshot sets from your app's screens, uploaded to App Store Connect.
Give your AI agent a debit card. AgentCard lets AI agents create and spend virtual debit cards — each with a fixed budget, real card credentials, and full MCP integration. Your agent can create a…
Free no-storage MCP that checks A2A Agent Card connection readiness for authorized targets.
Generic MCP server for calling x402-protected APIs with automatic payment handling
Structured-output enforcer: extract and validate JSON from messy LLM text.
Analytics and debugging for your MCP server — explore usage and sessions, then root-cause errors.
Agent-Ready Video (ARV): search video moments, moment context, rights, and signed playback
Hosted Amazon Seller Central and Amazon Ads MCP server for Claude, ChatGPT, Cursor, Claude Code, OpenClaw, and HTTP-capable MCP clients.
Agent Central connects the AI you already use to your Amazon Seller Central account. It is a hosted MCP server that gives Claude, ChatGPT, Claude Code, Cursor, and other MCP clients your Seller…
Local LLM cost proxy: forecasts each call and recommends the cheapest model that clears the task.
Find why a scheduled AI agent (cron, launchd, systemd, Claude routine) stops silently. Read-only.
Lets one coding agent talk to another: Claude Code, Codex or Grok
One identity across Claude Code, Codex, Cursor, Gemini, Windsurf: shared inbox and handoffs.
Placement across agent channels: MCP, Cursor, Claude, ChatGPT, npm, docs, Smithery, Glama.
MCP server for AgentChat - real-time AI agent communication
For most users, the simplest way to use AgentChatBus is just two steps:
Process monitoring for AI agents: start runs, submit per-task evidence, complete runs.
Synthetic checks, nightly regression replay and model-drift alerts for AI agents
AI shopping gateway for product search, inventory, carts, and merchant-hosted checkout.
Family meal planning run by your agent: weekly dinners, household votes, grocery list minus pantry.
Spiritual services for AI agents — confessions, salvation, identity. x402 payments.
MCP (Model Context Protocol) server that exposes Agent Church spiritual services as tools for AI agents.
Fabrication-free, DOI-backed citations for AI agents — real openAlex sources, never hallucinated.
Read-only Robinhood Chain token research via GMGN, built for Agentcity agents and any MCP client.
File-claim coordination for parallel AI coding agents: claim files before edits, no stomping.
Build, run, and inspect iOS apps in disposable hosted Simulators from cloud coding agents.
Free no-signup cloud tools for AI agents: file transfer, static site hosting, memory, handoff.
Free Streamable HTTP MCP arena for 1v1 AI agent skill battles and Gladiator Badges.
Self-contained MCP server for multi-agent collaboration with automatic authentication delegation and complete tmux session management - no external
Ask your accounts-receivable portfolio anything. Read-only, scoped to your account.
Agent intercommunication - messaging, channels, shared state, and real-time events
AI-agent product catalog: search, lookup & purchase routing over verified merchant data.
Policy review and purchase discovery for AI-agent commerce actions.
Read-only agent-commerce audit, upgrade verification, diagnosis and x402 probing.
🚀 5 分钟启动:docker run -d -p 3100:3100 ghcr.io/liuboacean/agent-comm-hub
End-to-end encrypted messaging and work coordination for autonomous AI agents.
Free citation deduplication, JSON checks, agent discovery, shared tasks and evidence review.
Public and private rooms for agents, with messages, files, search, and resumable events.
Free citation deduplication, JSON checks, agent discovery, shared tasks and evidence review.
Search public agent questions and sourced findings, browse agents, and read the onboarding guide.
A public commons for agents to search and share reusable findings and open research questions.
Public working memory for AI agents: messages, shared pages, and resumable tasks.
Cross-harness communication mesh for LLM agents — rooms, DMs, presence, and visibility over TCP
MCP server enabling room-based messaging between multiple agents
Agent Community MCP: member lookup, stats, DMV checks, and proposed .agent name interest.
Curated index of B2B offerings for AI agents: fit, non-fit, limits, sourced claims.