"Writing about MCP" matching MCP servers:

Enables coding agents to compile supplied files, run optional focused tests, and get static findings across ten programming languages, providing a deterministic feedback loop on the code they are about to return.

Enables independent, read-only adversarial review of candidate test cases and bug findings, returning a review delta that authoring agents reconcile before writing final artifacts.

Exposes six evidence-oriented tools over stdio so MCP clients can navigate unfamiliar code, ask typed questions about repository evidence, review completed changes, and select existing tests.

Umbra is the trust layer for AI-generated code. It scores any repo 0-100 with file:line evidence (security, slop, Docker-verified build/boot, and claim receipts that catch agents lying about tests), and guards agent file writes mid-stream blocking leaked keys, alg:none JWTs, and git-hook plants before they land. Tools: scan_repo, guard_content, get_score.

Automated Playwright E2E test repair powered by a self-improving, governed MCP server that runs failing tests, collects failure artifacts, reasons about root causes, validates and applies fixes, and re-runs to verify.

Finds and removes AI writing tells with a deterministic ruleset. Runs locally by default; an optional pass can call a model if you turn it on.

An MCP server that turns Zod schemas into mocks, violations, and contract tests, enabling AI agents to reason about API contracts without manually crafting payloads.

Enables deterministic, LLM-free checking of text against a prose editorial standard, returning violations with rule IDs, locations, severity, confidence, and suggested fixes, while also supporting safe fixes and writing measurements.

Enables auditing any public website, returning a scored plain-English report that flags issues costing customers, covering speed, phone experience, search visibility, contact options, writing quality, and modernity.

Provides content guard checks as MCP tools, enabling an assistant to verify keyword coverage, translation drift, internal links, regulated claims, and sitemap lastmod while writing pages.

Turns JUnit XML test reports from CI into queryable QA metrics, letting AI assistants answer plain-English questions about failures, flaky tests, regressions pinned to a commit, root-cause clusters, and performance drift. Also generates ready-to-share QA health reports and self-contained HTML dashboards without logging into separate tools.

Rarefaction is a Model Context Protocol (MCP) server that gives a coding agent the call graph and code context for one symbol straight from the project's language server (Language Server Protocol, LSP). Ask about a function, method or type and get, in one call: its signature and doc, its body, who calls it (tests marked), what it calls, who implements it, the tests that reach it and the short list

Enables natural-language validation of IFC models against Türkiye's building-permit BIM regulation, including compliance checks, EK-9 form generation, and queries about required classes and properties.

Local MCP server for querying VCD waveform files via SQLite; enables AI agents to ask precise questions about signal values, transitions, and clock cycles without dumping raw VCD text.

Delegates test writing to a headless second coding agent in an isolated git worktree, then builds, runs the tests, verifies that only test paths changed, and returns a compact report plus optionally applies the verified tests to your checkout. It also flags failures that point to bugs in the production code rather than the tests, keeping test code and terminal logs out of the main agent's context.

Enables an assistant to verify whether claims about AI systems hold against supplied evidence bytes, replay conformance vectors, and inspect related terms and artifact digests offline without fetching, writing, or sending data.

Enables RTL simulation and hardware verification with Verilator through automatic testbench generation, natural language queries about simulations, waveform analysis, and protocol-aware testing for Verilog/SystemVerilog designs.

A server that converts Allure test reports into LLM-friendly formats, enabling AI models to better analyze test results and provide insights about test failures and potential fixes.

Enables MCP apps to read, issue, verify, and ask about Agent Readiness Reports, including deployment status, risk grade, gates, findings, fixes, validity, and authenticity.

Provides a local MCP inspection workspace for testing permission-gated note reading and writing, showing rules, request payloads, execution status, and before/after SHA-256 hashes so developers can verify whether denied writes actually left files unchanged.

Enables bounded, source-write-free Rust development workflows: inspect Cargo workspaces offline, search and read source, collect compiler diagnostics, select and run tests or binaries/examples, resolve exact-version docs, and produce verified navigation or change/refactor packages without writing the workspace.

Generates importable Optimizely CMS 12 .episerverdata packages from content plans by reading a content-type export and writing the file, without interacting with a CMS instance.

Enables developers to scaffold a working TypeScript MCP server in about a minute, complete with two example tools using typed Zod schemas and structured output, in-process and stdio tests, CI across multiple Node versions, and a ready-made Patchbowl catalog entry so the result installs in any stdio-speaking MCP client.

MCP server that monitors source changes, recommends test types, and provides language-agnostic test writing guides and a /tdd skill for Claude Code.

Enables AI coding agents to drive a real browser like a person — crawling every page and role, running real user journeys, and auditing controls a DOM-based test misses — so UI, accessibility and permission bugs are found and only the screens affected by recent changes are re-tested. Runs are script-driven and read-only by default, so testing costs no model tokens and nothing about the app is sent to an AI.

Enables Claude Code or Cursor to reproduce issues, run sealed acceptance tests, verify claimed fixes, and retrieve fix tasks locally over stdio without writing into the user's repository.

Enables AI clients to control and observe Candela LANforge test systems through a secure MCP gateway, supporting Wi-Fi stations, traffic, monitoring, events, alerts, automation, and more via about 40 tools plus dynamic universal access.

Enables natural-language testing of MCP servers—covering tools, resources, prompts, contracts, and transports—without writing test code, with deterministic validation and CI integration.

Enables an agent to drive a running Unreal Engine game via UE4SS by reading/writing UObject properties and calling UFunction, with verdicts that verify whether the requested state change actually happened.

Pattern-intelligence MCP server for ServiceNow Discovery that enables AI agents to read, search, validate, author, surgically edit, and reason about Discovery patterns, including NDL grammar, SNMP OIDs, data sources, and emulator blueprints.

Enables an agent to evaluate a target MCP server and verify attestations about it from inside the editor, using read-only, allowlisted tools that never send credentials.

Enables read-only static posture audits of Tor Browser and Firefox configurations and residue, including layer-mismatch assessment, without launching or modifying the applications or writing files.

An MCP server that provides curated test cases and behavior specifications for common software features, enabling AI coding agents to define acceptance criteria before writing code.

Enables ChatGPT conversations to retrieve writing instructions and references, run lint and diff checks against source materials, and verify a signed receipt confirming that the final text matches what was checked.

Enables pulling test data, inspecting telemetry channels, running analysis, and writing results back from any MCP client.

Enables checking Minecraft Bedrock content before it ships by validating JSON, commands, scripts, Python and whole packs against official schemas, a real tsc, and version-pinned game data, and by looking up whether identifiers, versions and fields actually exist. It reports what will silently fail to load — including errors schemas structurally cannot catch — without generating or writing anything itself.

MCP server for Allure TestOps that enables searching, reading, and writing test cases, authoring and importing test suites in Markdown, managing launches, and retrieving project statistics, all scoped to a single configured project.

Give AI agents visual + structured feedback about live web UIs — and give humans deterministic demo reels while you're at it.

Enables natural language analysis of Perfetto traces to diagnose Android app performance issues like ANRs, jank, CPU hotspots, memory leaks, and lock contention without writing SQL queries.

Enables AI agents to analyse local source trees, generate starter projects for multiple targets without overwriting files, and verify generated manifests and entry files. It also exposes source and runtime inspection tools so agents can gather evidence about software artifacts within bounded, honest checks.