开发 MCP 服务器

Agent-to-agent referral network. Discover, recommend, and refer users between AI agents via MCP.

Autonomous payment & Web-of-Trust anti-Sybil layer for AI agents via Nostr & Cashu (NIP-61 NutZaps).

Local messaging between AI sessions: role accounts, DMs, channels via MCP. Windows only.

Ask your AI to check, fix and submit your App Store release. 41 tools for the paperwork.

The safety gate between AI agents and your servers: typed, policy-checked, audited ops tools.

x402 API gateway for web extraction, search, translation, image generation, screenshots, PDF and OCR, paid per call in USDC on Base.

MCP gateway for QA/SDET work: Playwright, files, GitHub, Jira, Postgres & more in one connection.

AI design fidelity — compare Figma designs or screenshots against rendered UI. No API keys.

Test, score and inspect n8n workflows with config-driven test suites, two-tier scoring, execution traces and a built-in node catalog.

Build Laravel apps through conversation. Code stored as structured JSON for surgical AI edits.

Agent-native registry to discover APIs, MCP servers and CLIs, with live health checks.

Screen-reader navigation cost analyzer. Scores AT user effort to find, reach, and operate content.

Real-time diagnostic snapshot of the local dev environment: framework, running services, recent errors and git state.

Privileged command execution proxy with human approval via pkexec or sudo

Pay-per-call x402 data: equities, crypto/DeFi analytics, options chains, dealer GEX, macro data, congressional trades, prediction markets…

Fault injection for MCP servers (timeouts, malformed JSON-RPC, corrupted outputs) with a reliability scorecard for output schemas and…

Local stdio MCP server for cached, loop-aware JS/TS diagnostics (Oxlint, tsc, Biome, ESLint).

Merge gate for AI-written code: deterministic vetoes plus a Claude Haiku 5.5 review. No signup.

Evaluate, benchmark, and simulate AI agents on the VerifyAX agent-evaluation platform.

Build, deploy, and operate hosted web apps on VibeKit (vibekit.bot) from any MCP client.

Code tools for LLMs to read, understand and modify code, using a tree-sitter parser, SQLite index and transactional writes.

Hundreds of x402-paid APIs as MCP tools, auto-discovered from Coinbase Bazaar. USDC on Base+Solana.

Checks and validates live x402 payment routes across Base, Solana and Algorand.

Expose the 5dive agent-fleet CLI (tasks, agents, digest) as MCP tools, over stdio or HTTP.

Governed Keycloak + authentik identity ops: users, events, clients, MFA, RCA. 29 tools.

Search, inspect and run data APIs for SEO and AI visibility, finance, social, web search, sales and agent mail through a few meta-tools,…

Advisory AOS agent health scan before deployment (manifest, services, immune loop, evidence).

Static blast-radius audit for MCP servers before agent install. Manifest optional.

Zero-config runtime and browser error sensor for AI coding agents: intercepts dev server crashes and in-browser exceptions with…

In-memory Code Property Graph context slicer for local models (Ollama, Cursor, Claude Desktop): extracts sub-1,200 token reachability…

Stops agents double-firing side effects: 1,000 racing duplicates, exactly one execution.

Lossless context guard for coding agents: command digests, file outlines, line-range reads.

Image, video, audio, face-swap, talking avatars and chat across 300+ AI models, one balance.

Audit a web page's images: natural vs rendered sizes, oversized detection, and formats.

Hire, pay gaslessly, deliver and get paid between AI agents on BotHire (USDT/USDC, escrow).

Records Python, Rust and TypeScript program runs to local SQLite so coding agents can query call trees, exceptions and value flow.

Micro-settled web content extraction and JSON schema validation utilities for AI agents via XRPL.

Manage Featureflip feature flags, targeting and rollouts from AI agents and editors.

Govern model, agent, skill, and MCP workflows with policy, approvals, traces, and usage analytics.

Reliable async execution for agent tool calls: schema gating, retries, idempotency, audit trail.

Your 24/7 production engineer that preserves context across multiple codebases [Prode.ai](https://prode.ai).

Pay-per-call x402 gateway: agent tools, OpenAI-compatible LLM, market data, RPC, security audits.

Free stdio bridge to Delx Protocol: resume after compaction, warm handoff, recover. No API key.

HTTP toolkit providing all 7 HTTP methods (GET, POST, PUT, PATCH, DELETE, HEAD, OPTIONS) with secret substitution, comprehensive error…

Full macOS control — drive a Mac like a human: shell, AppleScript, files, and human-like GUI.

Observe & operate a Mac — files, processes, apps, shell, AppleScript, GUI — safe by default.

23-in-1 developer utility toolkit — search, exchange rates, crypto, QR codes, and more

Upload Android and iOS builds to buildtree and get install links, QR codes and tester feedback.

23 API tools for Claude Code — email, DNS, SSL, NLP, scraping. Free tier included.

Real-time anomaly detection for blockchain, aviation, GitHub, mempool, and depeg signals.

Discover and call 400+ practical APIs through seven MCP tools with free search and x402 payments.

Give an agent a real Linux VM: run commands, move files, expose a preview URL, destroy it.

Fleet entry point: 22 hosted MCP servers, 160 tools, 110 free. Searches 138 agent skills.

A webhook inbox for agents: one call returns a live URL. Mock, verify, inspect and replay.

Lets your coding agent ship a SwiftUI iOS subscription app from idea to TestFlight: niche validation with live App Store data, SwiftUI…

Drive Gearotons M17 open-source servomotors from plain English over RS-485; mock mode, no hardware.

Search and compare thousands of AI tools, generate step-by-step AI workflows and AI tool stacks by profession from GateOnAI's curated…

Eyes and hands on real Windows PCs — observe, click, type via Glasswarp API.

Pay-per-call AI: 59 generative models (image, video, music, speech). No signup, no API key.

Search, inspect and compare infrastructure tools for AI agents from a checked directory.