Developer Tools MCP servers
Source control, code execution, CI/CD, and IDE integrations for AI-assisted development.
116 servers
Microsoft's official browser-automation MCP using Playwright's accessibility tree (no vision model).
Up-to-date, version-specific library documentation injected into your coding agent.
Pack any local or remote repository into one AI-ready file your agent can grep and read incrementally.
Code intelligence engine that indexes repos into a persistent knowledge graph for AI coding agents.
LSP-powered coding agent toolkit: semantic symbol search, references and structural edits.
One hosted MCP server for 2,800+ apps and 10,000+ tools, with Pipedream Connect managing OAuth for your users.
AI-powered reverse engineering: bridge IDA Pro to LLMs for vibe reversing via MCP.
Lets LLMs reverse engineer binaries in Ghidra: decompile functions, rename symbols, trace imports, exports and xrefs.
Build, run, and debug iOS & macOS apps in Xcode from your AI coding agent.
Platform-agnostic mobile automation for iOS & Android — simulators, emulators, and real devices.
Connect MCP clients to a running JetBrains IDE (IntelliJ, PyCharm, WebStorm, Android Studio).
Free remote MCP that turns any GitHub repo into a live documentation source to cut hallucinations.
Let AI agents launch the Godot editor, run projects, capture debug output, and edit scenes.
Isolated, containerized dev environments for coding agents — each agent works in its own git branch.
Index local code into a graph database to give AI assistants deep, queryable code context.
Connect Claude, Cursor & Windsurf to the Unity Engine for AI-driven game development in Editor and Runtime.
Control and inspect iOS simulators — UI taps, swipes, text input, screenshots, video, and app install/launch.
Control Unreal Engine 5.5 from AI clients — spawn actors, build Blueprints, and wire node graphs via natural language.
Connect AI assistants to the Unity Editor to manipulate scenes, GameObjects, assets, and run tests via MCP.
Popular community GitLab MCP server for projects, MRs, issues, pipelines, wikis and releases.
Turn Claude Desktop into a pair programmer that edits files, runs tests, and Git-versions every change.
Gives MCP-enabled clients semantic code tools: definition, references, rename, diagnostics, and more.
Computer-use MCP server that automates Windows desktop and browser apps via the accessibility tree.
Connect Claude, GPT, and Gemini to ROS/ROS 2 robots via rosbridge, with no changes to robot source code.
Multi-agent collaboration protocol: orchestrate specialized AI agents over MCP with a shared knowledge graph.
Official hosted Sentry MCP for investigating issues, errors, traces and performance data.
MathWorks' official server that lets agents start MATLAB, write and run code, lint scripts, and execute test files.
AI-powered discovery and documentation for the @reactuses/core React Hooks library.
Structural code navigation, persistent memory, and Bash output compaction for AI coding agents.
Search and explore any OpenAPI spec in simple language, via oapis.org.
Research code like a senior staff engineer: GitHub, local FS, and LSP intelligence wired into your AI assistant.
Local Apple documentation index served to AI agents over MCP — docs, HIG, Swift Evolution, packages, and sample code.
Control Android devices from MCP clients via ADB — run shell commands, capture screenshots, inspect UI, manage packages.
Next.js development tools for coding agents: runtime diagnostics, upgrades, docs, and Cache Components migration.
AI-powered IDE assistance for the Intlayer i18n ecosystem: docs, CLI, and dictionary management.
REPL-driven Clojure development for AI assistants: live nREPL eval plus structure-aware, paren-safe code editing.
Real-time NixOS, Home Manager, nix-darwin, and Nixvim data so your AI stops hallucinating package and option names.
Shell and coding agent for Claude and other MCP clients with tightly integrated shell and file-editing tools.
Let AI agents open and manage secure HTTP/TCP/UDP tunnels to local services over stdio.
Official SonarQube MCP server: bring code quality, security, and coverage analysis from SonarQube Server or Cloud into AI agents.
Give MCP clients access to your iTerm session to run commands, read output, and drive REPLs.
Let any LLM interactively debug your code in VS Code via breakpoints and expression evaluation.
Research-backed mentor layer that interrupts agent pattern inertia to prevent over-engineering and reasoning lock-in.
Salesforce's official DX server: run SOQL, deploy and retrieve metadata, run Apex tests and manage orgs from your agent.
Cut Claude Code context usage 60-90% via caching, Brotli compression, and smart tool replacements.
Control Android devices with AI through the Model Context Protocol via ADB.
Run model-generated code in a secure, isolated E2B cloud sandbox.
Connect your LLM/MCP client to Binary Ninja for AI-assisted reverse engineering and malware analysis.
Comprehensive Xcode integration for AI assistants: projects, builds, tests, simulators, SPM and CocoaPods.
VS Code extension exposing the editor's file, symbol, diagnostics and shell capabilities to MCP clients.
Analyze BloodHound Active Directory attack paths with natural language via 75+ Cypher-backed MCP tools.
Control iOS simulators with natural-language commands from your LLM, powered by Facebook's idb.
Claude Code-style coding agent over MCP: read/edit files, run commands, search code, delegate to sub-agents.
Smart context management for LLM workflows — rule-based file selection shared via MCP or clipboard.
Ranks every file by importance, maps dependencies, and keeps AI summaries fresh in the background.
Let AI agents generate audited smart contracts using OpenZeppelin Contracts libraries.
Let AI assistants read, control, and observe your tmux terminal sessions, windows, and panes.
Gives AI coding assistants up-to-date, crate-specific Rust documentation via semantic search and LLM summarization.
A debuggable automation engine for AI agents — trace every step, replay from any point, 467 modules as MCP tools.
JetBrains IDE plugin exposing an MCP server so AI agents can use the IDE's indexing and refactoring.
Official Docker Hub MCP server for searching images, reading metadata and managing repositories.
Official CircleCI MCP server: inspect and fix failed builds, query pipelines in natural language.
Let LLMs run shell commands and processes on the host machine via a single run_process tool.
Exposes VSCode language-server features (find usages, rename, go-to-definition) to AI coding assistants via MCP.
Grounded access to the FLOX trading framework surface for AI coding agents.
Natural-language control of NVIDIA Isaac Sim — spawn robots, build scenes, and run simulations via MCP.
Securely execute whitelisted shell commands over MCP, with stdin, argv pipelines, timeouts, and audit logging.
Securely run whitelisted CLI commands within an allowed directory via MCP.
Distill large codebases into AI-friendly context — public APIs, types, and structure, 90-98% smaller.
Search and load Dash documentation docsets and code snippets from MCP clients on macOS.
Connect AI assistants to Bitbucket Cloud repositories, pull requests, and code via 6 generic API tools.
Manage Postman collections, environments, and APIs through the Postman API.
Run arbitrary JavaScript in ephemeral Docker containers with on-the-fly npm dependency installation.
Centralize ESP-IDF/ESP32 commands and drive embedded builds, flashing, and tests via LLM-driven MCP tools.
Meta-MCP server that manages, aggregates, and proxies other MCP servers so LLMs can extend themselves.
Unified MCP hub that aggregates all your MCP servers into one connection, with knowledge, memory, and tools.
Real-time framework docs (types + prose + examples) for any npm package via MCP.
Integrate LeetCode problems, solutions, contests, and user data into MCP clients, supporting leetcode.com and leetcode.cn.
Behavior regression gate for AI agents — snapshot behavior, diff tool calls, and catch silent regressions, exposed to Claude Code over MCP.
Semantic code search & navigation for AI agents — jump to the exact functions and chunks instead of reading whole files.
Local MCP server that delegates coding tasks to specialized AI sub-agents (Codex, Claude, Cursor, Gemini) in parallel.
Debug embedded systems (ARM Cortex-M, RISC-V) from AI assistants via probe-rs.
Integrate the LLDB debugger with Claude via MCP for AI-assisted debugging sessions.
Turn your codebase into a queryable knowledge base: search, impact analysis, ownership, dead code — via MCP.
Official Buildkite MCP server to inspect pipelines, builds, jobs and tests and fix failed builds.
Search NPM, crates.io, NuGet, PyPI, Go registries and GitHub Security Advisories for up-to-date package info.
Persistent, interactive PTY terminal for AI agents over MCP — SSH, REPLs, password prompts, long-running jobs.
Context compaction for AI coders: token-efficient, AST-level code intelligence across 17+ languages.
Persistent code index + memory, semantic search & live telemetry for AI coding agents — 50x less context than grep.
Universal MCP server that drives your test suite end-to-end: run pytest/Jest/Cypress/Go/Maestro, analyze pages, generate tests, and advise.
Give any coding agent instant semantic knowledge of your codebase — one tool call instead of 19, ~20x fewer tokens.
Bring CodeLogic's software dependency and impact-analysis data into your AI coding assistant.
Control robots in ROS2 environments with natural language via topics, services, and actions.
Give AI assistants Roslyn semantic analysis and the Visual Studio Debugger via MCP — 41 tools.
AI-powered code review automation: analyzes Git diffs to find bugs, security issues, and quality improvements.
Turn any source code repo into a searchable, AI-queryable knowledge base inside Claude or Cursor.
Turn any OpenAPI spec into an MCP server, exposing your API endpoints as strongly typed tools.
Check Maven dependency versions and look up the latest releases from Maven Central in real time.
Multi-model AI orchestration MCP server for automated code review, chat, compare, and debate in Claude Code.
Compiler-accurate Java code analysis for AI agents, built on Eclipse JDT with 75 semantic tools.
Context-aware knowledge base for Klever blockchain smart-contract development on the Klever VM SDK.
Native Rust MCP server giving coding agents a PTY-backed shell, file IO, and tree-sitter code navigation.
AI-powered architectural decision analysis and ADR management for AI coding assistants.
Manage Homebrew packages on macOS from Claude Desktop or Cursor — install, upgrade, search, and maintain.
Run arbitrary Python in a secure, throw-away sandbox from your LLM agent via a single run_code MCP tool.
A standalone MCP server for API testing and management — let AI assistants call REST APIs in natural language.
Secrets management for AI agents via MCP — agents call your APIs without ever seeing the keys.
AI code quality gate that detects hallucinated imports, stale APIs, over-engineering, and security anti-patterns in AI-generated code.
Maven Central dependency intelligence for JVM build tools: versions, upgrades, CVEs, licenses, and POM-aware analysis.
Let AI assistants browse public GitHub repositories, explore directories, and view file contents.
Explore .NET assemblies, namespaces, types and NuGet packages via reflection so AI agents write accurate code.
Points your AI agent to the most critical design issue in Java code so refactoring fixes what matters.
Run k6 load tests from your MCP client and let an LLM analyze the results.
Wix's official hosted MCP: search Wix docs, generate platform code, and call real site APIs from your AI client.
Shopify's official dev server: learn Shopify APIs, search docs, and validate GraphQL, Liquid and component code locally.
Cognition's official remote MCP: AI-grounded docs and Q&A for any public GitHub repo — free, no auth.
Built an MCP server?
List it free, or feature it for premium placement and tracked clicks.