Development MCP Servers — Page 8

Gives AI agents safe computer use on Windows: screen perception via OCR, single frames and a live MJPEG stream, plus safety-gated mouse, keyboard, window, virtual-desktop and game-mode control over a local token-authenticated HTTP API and MCP (16 tools).

Provenance gateway for stdio MCP servers. Run `reasongate-mcp -- <server command>` in front of any MCP server: it drafts a policy per tool from the server's schemas and blocks tool calls whose destination or content came from an untrusted tool result, regardless of wording. Blocked calls are returned to the client as an error result with the provenance chain. Python, MIT, `pip install reasongate`.

D365 F&O: 90 AI tools over 200K+ objects, 25M+ cross-refs, 24M+ label translations.

Read-only MCP server for self-hosted SonarQube Community Build 26.4+. Lets AI agents (Claude Code, Cursor, Copilot) list projects, issues and security hotspots, drill into a finding, fetch the rule explanation and the source snippet around it — everything needed for the "read Sonar findings, fix the code locally" loop. 13 focused tools, no write endpoints. Java, stdio, Docker image on GHCR

MCP server for managing Gologin browser profiles, proxies, fingerprints and Cloud Browser sessions through AI conversations

Deploy multiplayer game servers from your coding agent. Ten tools that take a Unity, Unreal, or Godot dedicated server from container image to connected players.

CSS knowledge graph MCP server for AI coding agents — one tool call returns properties, overrides, specificity, callers and impact for any className. 100% local, zero-config.

Gives any AI coding agent your security and business rules, scans each diff (SAST, SCA, secrets, IaC) while it codes and blocks dangerous commands. Install with npx -y @cybedefend/vibedefend@latest install

Read-only Codex and Claude public quota reset evidence, history, source health and historical 24/48-hour estimates. Remote MCP at https://quotaresetwatch.com/mcp. No API key; no personal account monitoring.

Drive live iOS, Android, Apple TV and Android TV devices in the cloud to verify app changes: read the UI tree, tap, type, press the remote, assert, and read app logs from any MCP client.

Flowlines is the observability platform for MCP servers and AI agents. Instrument your MCP server with OpenTelemetry using Flowlines’ ready-made skills, then reconstruct complete agent sessions from the initial user request through tool calls to the final response.

Runtime CSS probe MCP server — inspect layout, overflow and scroll chains in a live browser. Returns confidence-classified findings for AI agents.

WordPress MCP server built into Tuli Builder: AI agents build pages, templates, query loops and custom post types.

Magery Forge — security audits for shipped code, built for VibeCoders. Turns scanner noise into clear risks with fixes, delivered as a weekly report. Exposed over MCP so your agent (Cursor, Copilot, Claude, OpenClaw) can trigger scans and read reports.

Run WCAG accessibility and color-contrast audits on any URL and file dev-ready QA issues, straight from Claude Code, Cursor, or Windsurf. Free tier: 3 scans/day.

Check if any website is down from Singapore and Boston, with uptime history, current outages and TLS certificate expiry. No API key.

MCP server for inspecting, searching, and decompiling Maven .m2 JARs for Java AI coding agents.

Lets a coding agent inspect the web page open on a real iPhone or Android phone connected to your Windows PC or Apple silicon Mac by USB: DOM, computed styles, console, network, and screenshots. You grant Observe, Interact, or Modify, and access starts at Observe every launch. Requires the CrocProbe desktop app. Inspection is free; agent pairing is licensed.

Local Windows MCP server for x64dbg/x32dbg: guarded launch and attach, breakpoints, verified memory writes, runtime capture, PE dumps, and IDA evidence using SHA-256 + RVA.

Architectural drift prevention for the agentic AI SDLC, with deterministic ADR guardrails across coding agents and CI.

Build, flash, and debug embedded firmware for any PlatformIO board (ESP32, Arduino, STM32, RP2040): parsed compiler errors, flash-then-verify against the serial boot log, crash backtrace decoding to file:line, firmware size reports, unit tests, static analysis. Python, uvx, no Node.

Free capability resolver for AI agents. Discovers and compares tools, APIs, MCP servers, and x402 machine services through a no-auth remote MCP endpoint.

Queay exposes a remote MCP server so a coding agent - Claude Code, Claude Desktop, GitHub Copilot, Kilo Code, and others - can list your test scripts, trigger a run, and check its status without leaving your editor. All execution still runs on Queay's own infrastructure; the agent only triggers and reads back results, the same as CI/CD

Cuts MCP tool-definition token overhead with lossless TOON encoding, so agents can load many tools without burning context. Zero-dependency Python CLI.

An AI agent that drives VS Code's real debugger — breakpoints, stepping, variable inspection — and an MCP server so external agents (Claude Code, Cursor) can debug through your editor too.

Test case management system TuskR

Official Featureflip server: create, toggle and target feature flags, see one flag across every environment, and find stale flags ready for cleanup.

MCP server for Redmine: lets AI agents (Claude Code, Cursor, Copilot) search issues, projects, wiki, attachments and time entries, run release and blocker analytics, and optionally create issues, notes and time entries

Read-only docs for the ADITUS event-technology APIs (ticketing, access, BI) and Shop Micro Frontend.

Three-layer firewall for MCP: inspects tool calls, content and tool results for prompt injection, credential leaks and data egress before they reach the model. Runs locally via npx.