Development MCP Servers

Ask your own coding agent about your product's analytics: 82 tools over one MIT Go binary that does funnels, retention, paths, cohorts, flags, A/B and AI-visibility, with every answer computed from your events rather than generated.

MCP server connecting AI assistants to Taiga - projects, epics, user stories, tasks, issues, sprints, wiki, and more.

MCP tools for crawler-readability and discovery-file diagnostics, including crawler-visible HTML inspection, raw-vs-rendered comparison, and discovery-file checks.

Tells agents what CSS you can actually ship today — Baseline status, per-browser support, stylesheet audits and UX reviews — from live webstatus.dev and MDN browser-compat-data.

An agentic reviewer with authority: 17 deterministic reality gates — mock/placeholder veto, gaming & bypass detection, invented-API checks — fused with a frontier-model enterprise review (ISO/IEC 25010: performance, scalability, reliability)

Manage user feedback, roadmap, changelog and user surveys all from your favorite LLM

Live OS ground truth for agents: running agent sessions, listening TCP ports, loaded daemons and system load, read straight from the OS instead of stale docs or memory.

Give your coding agent the dependency graph it is about to change: scan a source tree, SBOM, Git ref, or container image; explain why a package is present; diff two graphs; check findings against policy.

Read access to your product's living PRD — generated from your code and kept current on every merge — with tools to browse and search domains, capabilities, and acceptance criteria.

MCP server to manage your GitHub starred repositories and lists

Persistent global state database and context compression engine for AI coding agents

MCP server that lets AI agents analyze Claude Code session cost & context attribution — token usage, cached re-reads, and cache writes. Local, read-only.

Run, debug, and triage tests via natural language across HyperExecute, Automation, SmartUI, and Accessibility on the TestMu AI cloud.

Full Render.com control for AI agents: deploys, scaling, databases, logs, disks. All 207 API endpoints, generated from Render's OpenAPI spec.

Wireshark-MCP，Give your AI assistant a packet analyzer. Drop a .pcap file, ask questions in plain English — get answers backed by real tshark data.

Find, wire, and render microcharts — word-sized React charts with generated alt text.

AI Evaluations agent

Search 41,000+ agent skills, MCP servers, plugins & loops — real install counts and stars.

Drive the iOS Simulator from an AI agent: real HID gestures, token-efficient accessibility snapshots plus OCR, and deterministic replay flows for CI.

MCP server for managing Squidex CMS content and schemas from AI agents

A local-first MCP server that provides runtime visibility for AI coding agents. It replaces blind `print()` debugging with causal chains, allowing agents to instantly locate bugs by finding missing `.success` events in Python and TypeScript code. Single binary with MCP, CLI, and HTTP interfaces.

Western, Vedic, and Chinese astrology calculations, charts, forecasts, and geocoding over hosted MCP.

Hosted mock-API MCP server: agents create live REST/GraphQL mock APIs, import OpenAPI/CSV/db.json, seed fake data, query and write records — free, no auth, stateless Streamable HTTP.

Behavioral test gap analysis and grounded integration test generation via knowledge graph; finds untested behaviors, ranks by blast radius, proves via mutation kill.

Official MCP server for Proxidize — manage mobile & residential proxies from Claude, Cursor, and any MCP client. Rotate IPs, monitor usage.

Administers Linux for AI agents through typed, approval-gated actions with an Ed25519-signed audit trail, never raw shell strings.

Search everything your terminal ever printed. Local MCP server over per-command recorded output: full-text search, exit codes, diffs, secret redaction. Built and maintained by an AI agent (Soren Achebe).

LeakRank Guard scans your code changes for leaked secrets and insecure config, then hands your AI coding agent the exact fix and the keys to rotate.

Build, run, and test firmware on virtual instances of real chips (STM32, Nordic, etc.) via MCP, no hardware required.

Remote MCP server that gives your AI agent a dead-man's-switch: it calls create_heartbeat, pings on schedule, and emails you the instant an agent or cron loop stops checking in.