"Comment perdre du poids (How to lose weight)" matching MCP servers:

Enables turning requirements documents into RFCs, functional test scenarios, and a traceability matrix, with tools to parse, diff, and verify coverage.

Automates the conversion of Figma designs into TypeScript React components and integrates with GitHub to create pull requests for the generated code. It includes visual regression testing with Playwright and accessibility validation to ensure implementations match the original designs.

Enables agents to turn a plain-language description of a device into a complete, validated build package — parts list, 3D-printable parts, wiring, firmware code, picture assembly guide, and tests — that anyone can assemble without electronics experience.

Provides a testable gateway path for running a local MCP-style server in hosted-like conditions, with tenant-isolated reads, approval-denied writes, deterministic failures, and smoke-test verification.

Free JSON Schema validation, JSON to TypeScript, CSV to JSON, JSON repair and JSON to CSV for AI agents. Hosted MCP plus local STDIO. Connect once with a scoped key; enforce tool allowlists and quotas, inspect request IDs. Runnable repair → validate → CSV workflow. Bounded OpenAPI and webhook checks. No LLM calls or payments. Setup: invokeport.com/agents.

Automates downloading mobile game performance data from PerfDog and converts it to Tableau-ready CSV format with device statistics, FPS metrics, and time-series data.

The pixel-diff verifier for Figma-to-code: converts a frame to HTML, React, Next.js or Tailwind with design tokens, then renders it and pixel-diffs it against Figma until it converges. Also verifies your own running app.

Enables migration of test automation projects from WebDriverIO to Playwright using AST-based transformations. Provides tools for analyzing tests, converting syntax, refactoring to Page Object Model, and generating migration reports.

Provides a read-only MCP bridge that lets Claude Web inspect workspace files, git state, and recorded test results while Codex remains the sole executor of changes.

Enables MCP clients such as Claude Desktop and Claude Code to read café rules, rota, and staff data, check proposed rota changes against the owner's rules, and evaluate customer chat replies before sending. Every tool is read-only, with code checks applied first and AI judging used only when needed.

Read visual bug reports from Feedbug in your AI coding agent: screenshot, console logs, failed network requests, session replay and the DOM context of the element the tester clicked. Trace the bug to its source file, comment and resolve without leaving the editor.

Screen-reader navigation cost analyzer. Measures how hard it is for assistive-technology users to discover, reach, and operate interactive targets on the web.

Exposes Semgrep as deterministic, rule-matching analysis tools over MCP so a code-review agent can scan only the lines changed in a diff, scan whole files on demand, and check analyzer availability, version, ruleset, and limits. Results are returned as compact per-finding lines with source snippets suitable as comment anchors, along with counts of suppressed out-of-diff matches.

A stdio MCP server that audits other MCP servers over the live protocol. It connects to any MCP target (stdio or HTTP), lints every tool's schema for agent-usability, then actually calls the tools with deliberately broken inputs to see how the server handles them, and returns a 0–100 conformance score with a per-dimension breakdown rendered as Markdown.

Enables testing how different MCP clients handle tool results containing both content and structuredContent, including outputSchema enforcement and mismatch scenarios.

Runs a regular expression on real engines — JavaScript (V8), Python (CPython re), PCRE2 and RE2 — reporting each engine's own compile errors with positions, every match with its groups and named groups, replacement results, and where the engines disagree. It also detects catastrophic backtracking (ReDoS), naming the at-risk part of the pattern, generating an attack string, and timing how long each engine actually takes on it.

Lets an MCP client query SQLite databases through validated, forced read-only, row-capped, time-limited and logged operations, so AI agents can explore data without risking writes or runaway queries. It also ships an eval harness that measures how accurately a model answers benchmark questions via text-to-SQL through the server.

Audits public web pages for tracking tags, duplicate pixels, page weight, header hygiene, and lab performance from inside Claude Code or Claude Desktop.

Enables agents to calculate how many evaluation test cases are needed to trust model comparisons, find the smallest detectable accuracy gap, and assess paired or unpaired results using McNemar and two-proportion statistical tests.

Enables testing and observing how MCP agents recover from deterministic, simulated order-lookup failures such as transient errors, rate limits, stale revisions, and unavailable services through a local stdio server.

Exposes one stdio tool, resolve_reference, that accepts any reference string and always returns the same byte-identical "unavailable" result instructing the caller to invoke it again with identical arguments. It enables testing how agents behave when a tool confidently asks to be called forever, with no network, state, or retries of its own.

Enables MCP clients to work with self-hosted Jira Server / Data Center 8.x through entity-based core tools, JSON-declared plugin tools, and bundled Zephyr Scale. It supports issue, comment, worklog, attachment, project, user, link, watcher, agile, and test management operations using Basic Auth or PAT with runtime field discovery.

A Model Context Protocol server that connects Flutter apps with AI coding assistants like Cursor, Claude, and Cline, enabling AI-powered analysis of widget trees, navigation, and layout issues.

Enables AI agents to retrieve public test fax numbers and email addresses, then list and inspect received test faxes to verify fax machine, fax service, or scan-to-email setups. It is read-only, requires no authentication, and returns masked sender details plus links to PDFs and thumbnails.

A lightweight Python-based microservice that provides simple echo functionality, receiving messages and returning them back to the client for diagnostic and testing purposes within the MCP framework.

Enables AI assistants to run inbox placement tests by handing over seed addresses from live mailboxes at Gmail, Outlook, Yahoo and 30+ other providers, then reporting which messages reached the inbox, which hit spam, and what to fix first.

Validates .mcp.json and claude_desktop_config files to catch duplicate server names, missing binaries, invalid environment variables, and unreachable endpoints. Reports each problem along with how to fix it, so silently failing MCP servers can be diagnosed and repaired.

Enables AI agents to compare database tables using read-only tools, with credentials managed locally and never exposed to the model.

Enables AI agents to interact with, test, click buttons on, and verify Telegram bots end-to-end via MTProto, including messaging, inline queries, media exchange, and automated test suites.

Creates disposable remote MCP servers and records only the protocol boundaries they observe, enabling safe receipts of how far managed hosts like Claude, ChatGPT, or Cursor actually progressed.