Development MCP Servers

Scans an MCP server for security gaps before your agent connects. Free tier, no signup.

Hosted MCP server with OAuth sign-in, and plugins for Claude Code, Codex and Cursor: coding agents read each story's acceptance criteria, designs and tests from Stride and update it as they work.

Build, check and fix n8n workflows from your AI assistant: 1,100+ n8n node definitions, curated templates and a validator.

Scores whether a page reads as AI-generated and names the tells to fix.

Secure OAuth remote MCP control of explicitly paired computers: files, terminal, browser and desktop automation. Device operations can modify state.

40x fewer tokens while reading the RFC corpus, with obsoleted specs flagged

Logs your AI agent into websites, catches verification codes, and asks you before anything risky.

Turn a repeatable task into a self-correcting AI agent loop; a deterministic gate, not the model, decides when it's done.

LadDoc → SimaticML 云服务 MCP：严格校验梯形图文档（LadDoc IR），确定性生成可被 TIA Portal V19 直接导入的程序块（FC/FB/OB）。

Calibration Court MCP from ScriptMasterLabs: model-calibration leaderboard, per-model reports, and verification of a hash-chained calibration ledger. Paid recalibration endpoints settle in USDC on Base via x402 ($0.01 / $0.05).

Canonical x402 Gateway MCP from ScriptMasterLabs. Free discovery surface: find the x402 Gateway contract, inspect gateway status, and read the canonical payment contract (Base mainnet, USDC, payTo and header rules) before an agent pays anything. Paid capabilities are resolved per-target from fresh payment requirements.

Passive website security check graded A+ to F, free with a no-signup agent key; credit top-ups by card link or USDC over x402.

云端 PLC 仿真 MCP：校验并逐扫描周期运行梯形图（LAD）与 SCL 程序，跑场景化验收并返回 PASS/FAIL，不需要安装 TIA Portal。

GhostKey from ScriptMasterLabs: scoped browser session delegation — short-lived, origin-scoped sessions into a browser the user authenticated themselves.

See which AI models fall for planted traps on everyday business jobs (refunds, invoices, bookings), refereed with replays; run your own agent through the Gauntlet for a trap card; and check a skill, MCP server or package before install (scan, advisories, field reports). Free, no account.

Free, open-source MCP server and CLI: scans your running React app at 3 widths, finds UI drift and gives your coding agent each fix with file, line and token.

Free MCP server, no sign-in: scan a web page for AI-agent readiness, or check a remote MCP server against ChatGPT and Claude directory rules.

141 tools for design, accessibility, UX, typography, colour and site audits. Free tier, with Pro for unlimited use.

Hosted remote MCP server: lets Claude Code, Cursor, VS Code and Cline ask other models (GPT, Gemini, DeepSeek and 680+ more) and generate images, speech, music and video with one Gisoo API key. Billed per use.

Independent verifier for AI agents: checks agent claims and doc promises against the code, with signed receipts.

135 pay-per-call agent intelligence, token risk, developer and AI data tools for AI agents: prompt-injection and scam filters, PII redaction, token due diligence, OCR and speech-to-text, sports data, app stores and developer data. Paid per call with x402 (USDC on 11 networks, or RLUSD/XRP); no signup, no API key, a failed call is not charged. Part of SiteCheck: 9 MCP servers, 1,194 tools.

Per-call utility + assurance API for agents: 46 MCP tools — hashing/codec utils, market data, corpus search, deterministic honesty-audit scans. x402 micropayments (Base/Solana USDC) + prepaid credit.

AI model shutdown dates, replacements, and migration diffs for OpenAI, Anthropic, Google and more. Free, no API key.

Lints an agent skill before you install it: manifest, declared capabilities and instructions checked for contradictions. Remote MCP server.

One entry point for an agent's work, money and mandates: routes to artifact verification, spend accounting and limits. Remote MCP server.

Run several coding agents on one repo without them stepping on each other: they see each other's files, get warned before a shared edit, and message each other.

Experimental local stdio MCP adapter for typed agent workflows using caller-supplied Python session factories, registered tools and explicit action verification.

Local stdio MCP server for filtering records, code candidates and logs into typed evidence with recoverable source IDs. Requires a TypeSafe Jev API key.

Invisible bot shield for HTML forms: the browser solves a proof of work and your server checks it.

Permission tiers, human approval gates, and a secret-redacting audit log for Python MCP servers. Declare each tool READ, WRITE or DESTRUCTIVE; gated tiers wait for an approver and fail closed; every call is logged to append-only JSONL.