开发 MCP 服务器

Build, version, review, and export websites, web apps, and games from a conversation.

Search the awesome-mcp.tools catalog of MCP servers from an MCP client or the terminal.

Read-only local code graph for Rust, Cangjie, ArkTS, TS/JS, C/C++, Python and Shell: call graphs, quality gates, change review and impact…

Monitor GitHub repo health, DORA metrics and CI signals from your AI assistant.

ReSharper CLI inspection/cleanup via MCP. Unofficial: not affiliated with or endorsed by JetBrains.

On-prem Agentic AI on NVIDIA DGX. Query specs, model CapEx ROI, Purchase & join Partner Program.

Build, validate, and deploy multi-agent AI solutions from any AI environment.

Adversarial test generation in Cline: detects the stack, writes and runs tests, and classifies failures as real bugs, environment problems…

Live demand signals for idea validation: npm/PyPI downloads, GitHub + HN attention trends.

MCP server for Terse, an AI-native code language for coding agents: parse, evaluate, transpile to Python, and token-count Terse source…

BridgeNode — x402 pay-per-request AI inference. OpenAI-compatible API + MCP, Solana USDC, gas-free.

Checked dependency-bug records: look an error up, check versions before installing.

Deterministic local developer utilities for coding agents: inspect listening ports and processes, compute IPv4 CIDR subnet ranges, decode…

Fork, break and revert VirtualBox VMs with linked clones and RAM snapshots, and drive GUI-only guests via screenshots and input without…

Page inspection and runtime debugging in Chrome for AI coding agents: breakpoints, stepping, scope variables, source-mapped stacks, plus…

Publish HTML as live, shareable web pages with public, password-protected or email-restricted access.

Self-hosted relay: agent sessions on different machines share a board, chat and check git conflicts

Generate realistic relational test data — 156 field types, 22 locales, JSON/CSV/SQL, free previews.

Read-only SSH server diagnostics via a fixed 38-command whitelist; secrets redacted, no write path.

Grounding/hallucination guard: verify a claim against evidence (Supported/Refuted/NEE).

Hire agents, request quotes, delegate funded tasks, submit work, and collaborate on missions.

Discover, invoke, and verify ForceDream agents with cryptographic proofs. 14 local, 21 hosted tools.

Auditable market intelligence with calibrated forecast ranges, anomaly review, outcome.

Render PDFs and images from templates, validate data and convert Office files to PDF.

Hundreds of scraping & data APIs through one key. USD pay-per-request, normalized schemas, failover.

Deterministic code map for AI coding agents: a tree-sitter call graph with exact file:line over MCP.

Nahook webhook platform: trigger webhooks, inspect deliveries, retry failures and manage endpoints.

TokenLab MCP server: generate images and video, call models. 32 default and 89 full-profile tools.

Requires every AI agent code change to leave a problem, reason and approach audit record before commit, with a pre-commit hook and audit…

Check whether an LLM model id is deprecated, retiring, or retired, and what to migrate to.

Deploy a multi-user web app from your agent: hosting, auth, database, and permissions.

Search @imqueue docs and scaffold typed services & clients from your AI coding agent.

Developer and security utilities via the onlinecybertools.com API: encoding, hashing, JWT decoding, regex testing, formatters, network…

Build Telink and other embedded SDKs (Eclipse headless, Make or generic) via natural language, with automatic build pattern detection.

Stakeholders pin feedback on your live app; your AI agent reads the pins via MCP and fixes them.

Twelve tools to inspect CRAP scores, find work, and check edited functions against their ceiling.

Screen OCR on macOS via FreezeText: freeze the screen and extract text with Apple Vision, OCR regions or images, and search capture history.

Control Nemeton, a macOS virtual machine manager built on Apple's Virtualization framework: Linux and macOS VMs, APFS snapshots, console,…

The IDE for agents: read by symbol, edit against a revision, validate with your own build, revert.

Reduce your AI agent's token waste with collective intelligence — SaaS integration recipes

Labor marketplace protocol for AI agents with atomic escrow and weighted anti-Sybil reputation.

Time-travel debugger with bidirectional execution replay, hash-chain audit logging and SIMD-accelerated stack unwinding.

Offline calculator that evaluates expressions in fixed-point, IEEE-754 double or exact rational arithmetic, labelling each answer exact or…

Underground Cultural District: developer utilities (UUID, JSON, Base64, hashing, JWT, regex, cron), creative tools and a marketplace of…

Audit a domain email deliverability via Apify: SPF, DKIM, DMARC, MX, blacklist, catch-all, age.

The evidence layer for MCP: live operational grades plus Trust Receipts for every registry server.

MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.

MCP server for npm package management — publish, version, search, audit, and more

minia2a.uk — x402 pay-per-call APIs for AI agents, USDC on Base, 5 free trials per wallet.

Governed MCP server for DMTF Redfish BMCs. Read-only by default; writes are opt-in and dry-run.

Generate SaaS specifications for AI build tools: design systems, database schemas and RLS policies.

Control Claude Managed Agents: launch agents, watch their events, reply, approve tool calls and stop them.

Deterministic date and time reasoning: arithmetic, DST-aware time zones, business days, public holidays, RFC 5545 recurrence and…

ADB-based Android access: read-only logcat, UI hierarchy, package listing and allowlisted shell commands.

Read Woodpecker CI repositories, pipelines and logs, and drive builds, secrets and crons

Deployment-readiness checks for document-QA and extraction AI: grounding, extraction, CI gate.

WordPress plugin exposing Rank Math SEO fields, JSON-LD schema and restorable content snapshots as MCP tools, plus an additive-only write…

Local-first MCP server for task tracking and coordination of autonomous AI coding agents.

npm MCP — search packages, bundle sizes, vulnerabilities, compare downloads.

Is this dependency still maintained? Scores npm, PyPI packages and GitHub repos 0-100.