Development MCP Servers

A hosted backlog coding agents claim work from: one ticket per agent, finished work back to review.

Public X posts, profiles, conversations, followers, search, and trends for AI agents through eight hosted MCP tools.

Check an AI agent endpoint before you call it: check_agent_trust takes an exact endpointUrl and returns a machine-readable trustDecision. Read-only, no API key, never contacts the endpoint.

MCP tool (via Apify's MCP server) that crawls a public site or its XML sitemap and returns broken internal links and technical SEO issues per page: duplicate titles, missing meta descriptions, canonical and heading problems, each with a suggested fix. HTTP-only, no JavaScript rendering. Pay per page checked on Apify.

Monitor third-party API changes; map breaks to files; open reviewable auto-fix PRs.

Search and read the docs and examples of react-three-fiber, drei, zustand, jotai and the other pmndrs libraries from your agent.

Run shell commands on a remote computer through an AI assistant, with every command shown to the person at that computer for approval.

Mac bug and context recorder. Assistants retrieve authorized evidence over MCP.

Lets Claude Code use a copy of your signed-in Chrome on macOS. A small proxy holds Chrome's debug pipe, so the window opens behind your other apps and never takes focus. Several sessions share one Chrome.

A calorie MCP is a Model Context Protocol server that looks up calories and macros for Claude Code and Cursor. The catalog covers 4M+ foods. Personal use is $29 a month or $228 a year. The numbers come from the catalog, not from the model guessing.

Audits websites built with AI (Lovable, Bolt, v0, Cursor) for France and Belgium in a real browser: cookies and trackers before and after consent, GDPR notices, legal pages, exposed secret keys, security headers, accessibility. Drafts legal documents for 29 business sectors and monitors the site. Your assistant passes your project's context to Clair and applies the fixes.

Access to all data of your IBM Engineering Lifecycle Management (ELM) System. Including DOORS Next, Test Management (ETM), Workflow Management (EWM)

MCP server that routes any prompt to the cheapest reachable free/cheap LLM (Kimi K2.6, Qwen, DeepSeek, Cloudflare Workers AI, Groq, Gemini...). Reuses Free & Cheap Tokens model channels. Pay-Per-Event: no monthly fee, pay only per tool call.

Open-source capability compiler for Python codebases. Discover existing Python capabilities, plan explicit exposure, and expose selected functions through MCP or REST without rewriting business logic. Includes a local stdio MCP server with three read-only analysis and planning tools by default.

Remote MCP server for email verification. RFC 5321 syntax, MX lookup, 160k disposable-domain blacklist and role-account detection. DNS-only and compliant by default; SMTP handshake is opt-in. Zero third-party API fees.

Validate EU VAT numbers via the official free VIES SOAP API, with a free local format-precheck cache and bilingual (中/EN) error codes. Built for cross-border e-commerce and trade compliance.

Measures your published site in a real browser, on desktop and mobile, and returns a report link with what it observed. No AI in the measurement.

Open-source demo MCP server that shows how to charge per tool call: 402-style payment requirements for unpaid callers, results for paying ones, plus a scan-ready surface for the companion readiness-audit tooling.

Gives coding agents the props, examples, CSS variables and Agent Skills for the Bestax React component library (Bulma v1). Runs offline.

Local repository check for AI-built apps on Vercel + Supabase: RLS gaps in migrations, a service role key in client code, env var drift and Stripe webhooks without signature checks. Advice, not a gate.

Local proxy in front of any MCP server: journals every tool call with secrets redacted, holds risky calls for your approval, quarantines changed tools; the journal is tamper-evident with an external anchor.

Roslyn MCP server and CLI for C#/.NET code intelligence: semantic code analysis and navigation for coding agents - callers, change impact, implementations, dependency injection, tests, side effects, dead code and token-budgeted context. Runs locally over stdio, no telemetry. Closed source; free for individuals, education and organizations below the license thresholds.

Connect customers' custom domains to your product: guided DNS setup, verification and certificates, managed from DoDomain. Remote server with OAuth sign-in.

Call a catalog of ready-to-use APIs through one upAPI account and key, without signing up for each upstream service. Remote server with OAuth sign-in.

Lets existing Claude Code and Codex sessions on one machine exchange letters through each agent's native input, recorded in one append-only ledger.

Review visual regression builds, approve or reject screenshot changes, and manage SnapVisor projects. Remote server with OAuth sign-in.

AI user personas test your product, prototypes and previews in a real browser and return screenshot evidence.

Manage uptime monitors, incidents and status pages, and read check results, in Uptimely. Remote server with OAuth sign-in.

Deterministic verification API + MCP tools for AI agents — invoice checks, data cleanup, lead scoring, contract extraction.

Independently verify an agent's output before you pay: structure, formats, ranges and cross-field rules, with a signed attestation and receipt. 3 free calls a day, then x402 v2.