20,690 published MCP servers in this category · page 9 of 345 · all categories
Match shopper intent to a merchant's products and fetch live price, stock and product Q&A.
Develop firmware on the real board behind a debug probe: flash, reset, UART and CAN, policy-gated.
Agent Skill ROI Registry & Benchmarking. It sells skills for log triage and repository mapping.
Local-first flight recorder for AI agents: sessions, costs, loop runs, and stuck-loop flags.
Are you an AI agent reading this on behalf of a human? Your human asked you to install / set up AgenticMail. Pick either of these and then tell them to restart Claude Code: Zero prompts, ~2 minutes…
Read-only, never-executing MCP server for the agentic-os governance, SDLC, and QE methodology.
Agent-native CI/CD: follow a push to live deploy, diagnose failing stages, prove fixes, rerun.
Read-only gateway for durable agent identity, consent, recognized work, and signed receipts.
Local research agent that verifies its own answers. Runs on Gemma 3 4B + Ollama, $0/query.
Filter agent RL methods by supervision, critic and task setting; retrieve source links and BibTeX.
High-performance (Rust), token-efficient, and asynchronous SSH orchestrations for AI agents.
Agent reputation economy: known-answer probation, expertise tags, jobs, staked delivery
Read, cite, compose and remember over a Markdown knowledge Bundle, as MCP tools over stdio.
AI development agent using Kendo UI to rapidly create and style quality web UIs or Pages.
Explainable ALLOW/WARN/BLOCK risk decisions for AI agent actions before execution, signed as OAA.
Point it at any repo. It detects the stack, writes a .workspace/ directory with progressive context and session handoffs, and installs a working Claude Code adapter, all in one command.
Optional persistent identity state for autonomous software agents.
Agent Identity MCP — DIDs, verifiable credentials, reputation scoring
heera.it via Agentimus: AI readiness, traffic, request log, search & index reports, by approval.
P2P Agent Index MCP — publish and search decentralized web indexes over libp2p.
Rank tenders and projects; compare markets and official evidence for 0.01 USDC x402.
Delegate from Claude Code to Gemini, Codex, Copilot, Cursor and opencode CLIs as sub-agents.
Local MCP runtime for coordinating Freebuff, Codex, OpenCode, Claude Code, and Cursor agents.
Access your Agent Interviews data directly from Claude and Cursor using Model Context Protocol (MCP)
A Model Context Protocol (MCP) server that provides onchain tools for Claude AI, allowing it to interact with the Solana blockchain through a standardized interface. This implementation uses Agentipy and enables AI…
Apply as an autonomous agent: pick a role, prove work, pass a test, get missions.
Deterministic inspect, safe repair, and JSON Schema validation for agent JSON. No LLM.
Deploy websites, apps, agents and MCP servers from Claude Code or Codex. OAuth, runs in Taiwan.
Signed-quality-receipt micro-services for agents; verify before you pay (x402/USDC).
By integrating this server, your AI assistants (like Claude) gain professional-grade capabilities to instantly search, extract, and comprehend the Annual Reports (Past 3 Years) and Latest Interim…
Check your AI agent into a lobster resort archipelago. Chat, bottles, guilds. Watch live in 3D.
Plan and run paced startup, SaaS and AI directory launches from your agent, in your own Chrome.
Fixed-fee software consultancy. Ask about scope, terms, and live capacity.
Meter, cap, and block AI agent spend before the provider is charged.
Agent permissions for the files your team shares
Checks CLAUDE.md, AGENTS.md or a system prompt for 12 safeguards unattended agents need.
Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
MCP server for the public AI agent registry at agentlookup.dev.
Read-only MCP server for AgentLoopKit tasks, policies, reports, handoffs, and status.
Agentic memory manager. Install Skill: npx skills add meharajM/agent-loop-mcp
AI marketplace for agents to find paid work and trade digital services via MCP and x402.
Behavioral memory layer for AI tools. Learns preferences and context across Claude, Cursor, Codex.
Your AI forgets your project every new session. This fixes that.
AgentMail has one MCP tool implementation, hosted at:
Verify a proposed action against a signed Agent Mandate without executing or mutating accounts.
Fetch, validate, and permission-check Agent Manifest Protocol (AMP) manifests for API discovery.
Signed agent discovery, security attestations, paid work, and verified settlement reputation.
BizGigz Agent Marketplace - register AI agents, manage API keys, and discover MCP capabilities
MCP Server for an Agent Task Marketplace
Discover MCP servers + tools, auto-install into any client, pay for x402 endpoints in USDC.
Shop for AI agents: always-on utilities and tested code kits, paid from a prepaid balance.
Agents talk for free, then register, search for work, or list a service.
Korean-Japanese bilingual community. Read public posts/comments, route Korea/Japan queries.
On-demand tool discovery for all your MCPs and per-subagent MCP controls to preserve context window.
One MCP server bridging the Codex, Cursor, OpenCode, Claude, and Antigravity CLI agents
Persistent, agent-owned memory with encrypted storage and shared knowledge commons.
Persistent agent memory with a decision layer: replay, restore, verify, or none — explainable.
Agent memory: free durable storage (any keypair, no signup) that survives sessions and machines.
Agent memory MCP server with provenance tracking, decay-weighted recall, and feedback loops.
Local-first memory engine for AI-agent teams: team/project ACL, recall, and federated sync.