Development MCP Servers

Inspect scheduled jobs, runs, durable workflows, and webhook health; run one confirmed job.

Give ChatGPT a real terminal on your Mac: shell, files, real PTY sessions, background jobs, and read-only Codex history over MCP.

Discover mobile app attack surfaces via BeVigil OSINT — hosts, subdomains, URLs, and more.

Turn anything your agent produces — diffs, logs, reports, HTML — into a shareable link that expires on its own.

Open-source CLI and local MCP bridge that connects AI agents to 2,000+ AI models through one account.

Deterministic security preflight for AI agents. Check URLs, files and shell commands before acting.

Pay-per-query API serving 22 field-tested Forward Deployed Engineering rules. Two free forever as a preview; the full set is gated behind Stripe's Machine Payments Protocol — an agent pays $0.50/query directly, no human checkout, no API key signup.

AI-powered code review for Claude Code, Cursor, Cline and any MCP client — OWASP security scans, bug detection, N+1 queries and performance profiling, fully local.

Abstraxn Agent Kit's public MCP server gives any AI agent instant access to Web3 and market data with no signup or API key required. Query live blockchain data including block numbers, gas prices, transaction status, and ERC-20 token information and prices across major EVM chains and Solana. You can also access x402engine's pay-per-call APIs for crypto market data, wallet, token and ENS lookups, on-chain transaction simulation, and flight and hotel search. Paid calls are settled directly from the caller's own crypto wallet through the x402 protocol, while Abstraxn never holds or custodies funds. Ideal for AI agents that need real-time blockchain, Web3, and market data without onboarding friction.

Ten keyless lookups for facts that go stale after a training cutoff: live model pricing, whether a library is still shipping, verified SaaS pricing and stack cost, agent skills, component registries.

Web Scraping, PDF Extraction, Data Processing

Drive a real iPhone via macOS iPhone Mirroring, taps, swipes, OCR, plus Xcode build/test automation on simulators and devices. No jailbreak.

41 tools over one document API: invoices, receipts, statements and tables to schema-valid JSON, plus field extraction, PII redaction and contract review, billed only on success.

Design, mock, test, document and monitor your APIs from one living OpenAPI spec.

Coordination room for several AI coding agents in one repo: an agent claims a path glob before editing and any conflicting claim is refused first-writer-wins, so collisions are prevented rather than merged later.

Semantic code retrieval over a graph of entities, relationships, changes, and provenance. Locate, search, context packs, data-flow tracing, and impact analysis without raw file search.

Google index monitoring with history. Which pages are indexed, which dropped out and when, and why the rest are not.

Tamper-evident action logging for AI agents: hash-chained ledger_append/ledger_verify MCP tools over one JSONL file, zero dependencies — proves the record wasn't altered in place (limits stated honestly in the docs).

Free hosted changelog: agents can sign up, publish release notes, and manage a public changelog page + RSS via MCP (no email or CAPTCHA needed).

Agent identity and key custody — provider keys held in a local encrypted vault and leased to agents under owner approvals, with env-var injection so secrets never enter model context and a one-command kill switch; plus a registry with Ed25519 agent identity, reputation, and messaging.

harvis.dev is zero-setup static hosting: run npx harvis in any folder and get a live URL in seconds

Mechanical citation and claim checks for AI-generated documents — counts, references, totals; located verdicts, no model on the free path, documents never stored.

Live infrastructure checks over MCP: domain health (SSL/DNS/reachability), MCP server health with A–F security posture, AI agent-readiness, email blacklist, broken links, and live status for 11 major cloud vendors — 8 tools, no signup.

Turn any OpenAPI 3.0 spec into an MCP server with zero code — deploy to Cloudflare Workers, Node.js, Docker, or run locally via npx, with a built-in OAuth 2.1 server for MCP clients that require custom connector authentication.

Pipehero tunnels your localhost to a public URL and captures every webhook, so you can inspect, replay, and debug them — including from your AI agent via MCP.

Verified GPU compute for humans, applications, and agents.

Secure Docker monitoring and management MCP server for containers, logs, alerts, diagnostics, and safe control across local and remote hosts.

Paid MCP tool store — register your own MCP server and keep 80% of revenue per call. Billing, auth, and abuse protection handled by teai.io.

Publish pages to a live URL and run skilled AI agents from your terminal.

Fail-closed CI gate for AI-written code: blocks known CVEs and serves human-approved acceptance criteria to Claude Code/Cursor/Codex over MCP, read-only to the agent.