"Using Claude to Check the Current Weather Without an API Key" matching MCP servers:

Runs SQL statements in memory against real PostgreSQL 18 and SQLite 3.49 engines after loading your schema and sample rows, returning each statement's own verdict: errors with line, column, and hints, constraint violations, or the resulting rows. It also compares both dialects to expose portability differences, all with no database server, network, or API key.

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.

Enables agents and users to validate Kubernetes manifests (YAML/JSON, multi-document) against the API of a chosen Kubernetes version without needing a cluster. It reports removed or deprecated APIs with replacements, unknown or misspelt fields, misconfigurations the API server would reject, Pod Security Standard violations, and common risks, each with file, line, and fix.

Provides a stable, side-effect-free MCP tool contract that enables AI workflows to be prototyped, demoed, tested, or dry-run without connecting to databases, APIs, files, or other real data sources. It enables swapping in a real data server later without changing the AI-facing interface.

Provides six read-only MCP tools for checking an agent reply against explicit rules and preserving exact findings as regressions.

Scores any remote MCP server for readiness across the Claude Directory, ChatGPT Apps, Gemini Connected Apps, and MCP Registry, returning a 0–100 score, A–F grade, per-store status, failing checks, and one-line fixes. Also provides report links, badges, and explanations of each check.

Enables agents to verify that a deploy actually worked by checking pages, links, and comparing environments, catching blank 200 responses, broken links, stray noindex, and staging that never updated.

Reads a small-business website like a customer would and shows where they get stuck. Every AI answer has to quote the page, and the server checks the quote before it counts.

Analyzes websites for broken links, missing meta tags, and redirect chains, returning a health score and actionable suggestions.

Custom version of vibecheck

Enables Codex and Claude Code agents to submit drafts for local rubric-based review through TypeSafe Jev, returning keep, rewrite, or uncertain decisions so agents can fix flagged issues and re-check once.

Enables deliverable conformance and evidence-chain checks by turning requirements into executable specs, validating numbers against a provenance ledger, and auditing PDF/OOXML metadata and archive manifests.

Enables running deterministic package.json checks for Next.js, Expo, and Convex projects via a read-only stdio tool, returning JSON findings usable by CI and coding agents.

Enables AI coding assistants to scan an iOS, Android, Flutter, React Native or Expo project for App Store and Google Play rejection risks, returning deterministic findings that cite the guideline section, link to the official Apple or Google page and explain how to fix each problem. Nothing leaves the machine and no AI is used in the checks.

Serves the paper fact-checking checks over the Model Context Protocol, enabling an agent to recompute reported statistics, percentages and changes, compare text against tables, and verify references against Crossref, OpenAlex and arXiv. Each finding quotes the paper, shows the arithmetic and suggests a fix, with HTML, Markdown and JSON reports.

Minimal MCP server for testing GitHub PR checks pipeline, with deterministic tools echo, add, and server_info.

Enables AI agents to submit npm, PyPI, Go, or Maven packages and manifests to the free OSV.dev database and receive per-package and per-advisory results with CVE mappings, CVSS scores, severities, and the versions that fix each issue. It also supports filtering by minimum severity, de-duplicating alias advisories, and machine-readable error/warning rows for CI gates and upgrade recommendations.

Enables Claude to capture screenshots of the screen, windows, regions, and web pages, and compare screenshots for visual regression testing.

An MCP server that makes backend API requests and packages request+response pairs as evidence to prove an endpoint works.

Turns an OpenAPI spec into a ready-to-run test harness with local LLM agents: WireMock stubs, contract tests, robustness probes, and chaos scenarios you can switch on and off in a running WireMock.

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 regex testing, replacement, splitting, validation, explanation, escaping, common patterns, and benchmarking through an MCP server.

Enables testing and interacting with any REST API endpoints directly from MCP clients such as Claude and Cline, supporting GET, POST, PUT, DELETE, and PATCH requests with detailed status, header, and body responses. It handles Basic, Bearer, and API Key authentication, custom headers, configurable SSL verification, and response size limits.

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.

Exposes 11 agent-native QA tools over stdio so coding agents can discover a project, analyze risk, select the smallest relevant test set, generate and dry-run tests, triage failures, propose tiered heals, analyze flakes, generate quality reports, and evaluate release readiness. Planning and healing tools stay read-only or propose-only, while execution defaults to dry-run, keeping agent actions safe and evidence-backed.

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.

Enables natural-language chat-driven API testing, letting users upload API specs, run deterministic pytest checks against live targets, inspect results, create defects, and view failure trends.

Enables testing and interacting with any REST API endpoint directly from MCP clients like Claude and Cline, supporting GET, POST, PUT, DELETE and PATCH requests with detailed response information, custom headers, and Basic, Bearer or API key authentication.

Starter scaffold for a workshop to build an MCP API testing server, intended to be extended through incremental steps.