749 developer tools MCP servers, most popular first. Every listing shows its security level and install command.
| Name | Popularity | Security |
|---|---|---|
| mac-monitor-mcp Identifies resource-intensive processes on macOS and suggests performance improvements. | 23 ★ | Low risk |
| claude-faf-mcp Persistent project context in the .faf (Foundational AI-context Format), with project DNA and Podium scoring. | 23 ★ | Low risk |
| kivgraph Local code graph for coding agents: find code by intent, follow callers and references, inspect blast radius a | 22 ★ | Low risk |
| agent-droid-bridge Control Android devices and emulators via ADB: UI inspection, screen interaction, ADB commands and change dete | 22 ★ | Low risk |
| sequa-mcp Gives AI coding tools context from your entire codebase and docs via Sequa. | 22 ★ | Low risk |
| perfetto-mcp-rs Perfetto trace analysis: run PerfettoSQL queries on trace files, with Chrome tools for page loads, scroll jank | 22 ★ | Low risk |
| mcp-server-terminal Interact with TUI/CLI applications through a structured terminal state tree with element detection, like Playw | 21 ★ | Low risk |
| CodeEraser Scans a repository for dead code, duplication, churn and structure and erases what the scan found, with a log | 21 ★ | Low risk |
| primitiv Local-first design contract layer: scans Figma, code, Storybook and token files, reconciles conflicts and serv | 21 ★ | Low risk |
| currents-mcp Fix Playwright test failures reported to Currents. | 21 ★ | Low risk |
| mcp-zuul Zuul CI: build failure analysis, log search, pipeline status and job configuration. | 21 ★ | Low risk |
| ui-annotator-mcp Annotates any web page with hover labels for AI assistants via reverse proxy injection, without browser extens | 21 ★ | Low risk |
| colab-mcp Control Google Colab notebooks and assign GPUs (T4/L4/A100). Fork of Google's colab-mcp with all tools visible | 20 ★ | Review before installing |
| ssh-mcp SSH control for Linux and Windows servers, with long-running commands and execution on multiple hosts at once. | 20 ★ | Review before installing |
| developer Developer tools for file editing, shell command execution and screen capture. | 20 ★ | Review before installing |
| maple Frontend review on deployed previews. Your agent reads reviewers' comments over MCP and resolves them, and a C | 20 ★ | Low risk |
| simctl-mcp Control the iOS Simulator. | 20 ★ | Low risk |
| excel-vision-mcp Reads Excel files with embedded images mapped to their cells and meaningful formatting such as colors and stri | 20 ★ | Low risk |
| pty-mcp Interactive PTY sessions for AI agents: local shells, persistent SSH sessions with attach/detach, and serial p | 19 ★ | Low risk |
| patchloom Structured file edits for agents: JSON, YAML and TOML by selector, Markdown and AST edits, dry runs and multi- | 19 ★ | Low risk |
| oss-autopilot Open source contribution manager: PR tracking across repos, issue discovery, CI failure diagnosis and maintain | 19 ★ | Review before installing |
| term_mcp_deepseek Approval-first local terminal control: policy-based command planning and approval, DeepSeek as an advisor, and | 18 ★ | Review before installing |
| axint Compiles TypeScript to validated Swift for Apple platforms: App Intents, SwiftUI views, WidgetKit widgets and | 18 ★ | Low risk |
| mcp-code-runner Run code in multiple programming languages locally via Docker. | 18 ★ | Low risk |
| shipstores Ship iOS and Android apps end to end: App Store Connect, Google Play Console and Expo EAS builds, listings, sc | 18 ★ | Low risk |
| codewiki-mcp Search repos, fetch AI-generated wiki docs and ask questions about any open-source repository via codewiki.goo | 18 ★ | Low risk |
| replicant-mcp Android development: build APKs, launch emulators, manage devices, automate UI and analyze logs. | 18 ★ | Low risk |
| mcp-prompt-engine Manage and serve dynamic prompt templates using a text template engine. | 18 ★ | Low risk |
| gitwarren-app Local code review for you and your coding agent: the agent opens a review of its changes, you comment on lines | 18 ★ | Low risk |
| commitlore Returns active decision records for a path before an agent edits it: constraints, ruled-out alternatives and w | 18 ★ | Low risk |
| OctoCounts SLOC counts for any public GitHub repository from any MCP client: files, code, comment and blank lines per lan | 17 ★ | Low risk |
| mcp-server ConfigCat feature flag platform: manage feature flags, configs, environments, products and organizations. | 17 ★ | Review before installing |
| naja-scope Explore elaborated SystemVerilog/Verilog designs (RTL or gate-level netlists) with najaeda: trace fan-in/fan-o | 17 ★ | Low risk |
| graphpilot Structural memory for coding agents: indexes TypeScript/JavaScript repos for callers, callees, symbol location | 17 ★ | Low risk |
| netops-mcp DevOps and networking tools: network monitoring, system diagnostics, automation workflows and infrastructure m | 16 ★ | Review before installing |
| ejentum-mcp Reasoning, code, anti-deception and memory tools for AI agents. | 16 ★ | Low risk |
| sysknife Linux system administration via typed actions instead of shell strings, with a signed audit log, one-time appr | 16 ★ | Review before installing |
| firefly-mcp Discover, manage and codify cloud resources with Firefly. | 16 ★ | Review before installing |
| magents Shared session bus for coding agents such as Claude Code, Codex and Grok: list, read, hand off, message and sp | 15 ★ | Low risk |
| gemini-antigravity-bridge Bidirectional bridge between Gemini Spark and the Antigravity IDE: coding subagent dispatch, shared memory, lo | 15 ★ | Review before installing |
| aspnetcore-debugger-mcp Interactive .NET/ASP.NET Core debugging via netcoredbg: breakpoints, stepping, thread inspection, exception an | 15 ★ | Low risk |
| agent-skill-loader Load Claude Code skills into agents without copying files: discover, read and install skills on demand. | 15 ★ | Low risk |
| claude-concilium Multi-agent consultation for Claude Code: MCP servers wrapping Codex, Gemini and Qwen CLIs for parallel code r | 14 ★ | Low risk |
| kill-process-mcp List and terminate OS processes via natural language queries. | 14 ★ | Low risk |
| tui-mcp Launch, screenshot and interact with any TUI app. | 14 ★ | Low risk |
| tokenchit Reads local Claude Code, Codex and OpenCode usage logs: token totals, daily and hourly activity, per-agent and | 14 ★ | Low risk |
| fastmcp-sonarqube-metrics Retrieve SonarQube project information: current and historical metrics, issues and health status. | 14 ★ | Low risk |
| memorydetective iOS memory leak and performance investigation: reads .memgraph and .trace files, classifies retain cycles agai | 14 ★ | Low risk |
| n8n-mcp Generate n8n workflow JSON from natural language, lint for deprecated nodes, missing typeVersion and broken co | 14 ★ | Low risk |
| Edict Agent-oriented programming language: agents emit a JSON AST that the compiler validates, type- and effect-chec | 13 ★ | Low risk |
| preflight Catch vague Claude Code prompts before they waste tokens: prompt scorecards, session history search, cross-ser | 13 ★ | Low risk |
| infrabroker Self-hosted SSH and Kubernetes access broker: ephemeral per-operation credentials the model never sees, per-co | 13 ★ | Review before installing |
| context-rot-detection Monitors agent context health: token utilization, context quality degradation and session fatigue, with 0-100 | 13 ★ | Low risk |
| clarifyprompt-mcp Turns vague prompts into platform-optimized prompts for AI tools across image, video, voice, music, code, chat | 13 ★ | Low risk |
| DevDocs-MCP Version-pinned, offline documentation sourced from DevDocs.io. | 13 ★ | Low risk |
| locust-mcp-server Performance testing with Locust. | 13 ★ | Low risk |
| vs-token-safer Routes code search through language-server indexes (clangd, Roslyn, tsserver, pyright) instead of grep, plus s | 13 ★ | Low risk |
| fenestra Headless rendering and verification of native Rust GUIs: accessibility tree, semantic selectors, contrast and | 13 ★ | Low risk |
| github-graphql-mcp-server Unofficial access to GitHub's GraphQL API for flexible queries on repository data, issues, pull requests and o | 13 ★ | Low risk |
| prolog-reasoner SWI-Prolog execution for LLMs with CLP(FD), negation as failure and recursion. | 12 ★ | Review before installing |
| mcp-remote-ssh SSH access with persistent sessions, SFTP and port forwarding, with secrets injected via stdin and redacted fr | 12 ★ | Low risk |
| execkit Stateful, auditable shell sessions over local, SSH and Docker, with secret redaction, output budgeting and a r | 12 ★ | Low risk |
| noisy-coding Voice interface for Claude Code: live speech-to-text with turn-taking, spoken replies with xAI Grok voices, pe | 12 ★ | Low risk |
| skill-ninja-mcp-server Search, install and manage agent skills (SKILL.md files) from GitHub repositories, with workspace analysis for | 12 ★ | Low risk |
| bestax Gives agents props, examples and CSS variables for the Bestax React component library (Bulma v1). Runs offline | 12 ★ | Low risk |
| echo-mcp Zero-configuration Go library that exposes existing Echo web framework APIs as MCP tools. | 12 ★ | Low risk |
| swift-patterns-mcp Curated Swift and SwiftUI patterns and real-world code examples from sources like Swift by Sundell and SwiftLe | 12 ★ | Low risk |
| unified-diff-mcp Generate and visualize unified diffs as HTML or PNG, with side-by-side and line-by-line views for filesystem d | 12 ★ | Low risk |
| RestCsvMcpServer Access CSV files via RestCSV. | 12 ★ | Low risk |
| pharo-smalltalk-interop-mcp-server Pharo Smalltalk integration: code evaluation, class and method introspection, package management, test executi | 12 ★ | Low risk |
| gitingest-mcp Convert any Git repository into a text digest of its codebase using gitingest. | 12 ★ | Low risk |
| vex Local code search over a tree-sitter index: exact symbol lookup, scope-aware usages, call graph and impact ana | 12 ★ | Low risk |
| postbag Letters between existing Claude Code and Codex sessions on one machine: join a named bag, send through each ag | 11 ★ | Review before installing |
| Blind-Auditor Make AI self-correct its generated output through prompt injection, independent self-auditing and context isol | 11 ★ | Low risk |
| sage Local command wrapper for AI coding agents: runs shell commands, stores history locally and returns compressed | 11 ★ | Review before installing |
| ios-mcp-code-quality-server iOS code quality and test automation: Xcode test execution, SwiftLint integration and failure analysis. Also r | 11 ★ | Low risk |
| bldbl-mcp Buildable development platform: manage tasks, track progress, get project context and collaborate with humans | 11 ★ | Review before installing |
| conan-mcp Conan C/C++ package manager: create projects, manage dependencies, check licenses and scan for security vulner | 11 ★ | Low risk |
| gavel Code-quality gate for Bazel monorepos: runs lint, coverage and architecture checks from the build graph and re | 11 ★ | Low risk |
| mcp-gitlab-jira GitLab and Jira: manage projects, merge requests, files, releases and tickets. | 11 ★ | Review before installing |
| memorylens-mcp On-demand .NET memory profiling with JetBrains dotMemory: detects memory leaks, LOH fragmentation and anti-pat | 11 ★ | Low risk |
| npm-package-docs-mcp Up-to-date documentation for npm packages, fetched from the latest README in the package's GitHub repository. | 11 ★ | Low risk |
| garmin-documentation-mcp-server Offline Garmin Connect IQ SDK documentation with search and API examples. | 11 ★ | Low risk |
| claude-codex-bridge Run Codex agents from Claude Code through MCP and Channels, with live progress notifications, mid-task steerin | 10 ★ | Review before installing |
| mason Generates CLAUDE.md from git history and file sampling, and keeps a concept map linking features and flows to | 10 ★ | Low risk |
| MCP_AI_SOC_Sher Dynamic SOC security threat analysis for a Text2SQL AI agent. | 10 ★ | Low risk |
| api-testing-mcp API testing: per-project environments with variable interpolation, saved collections, multi-step flows, assert | 10 ★ | Low risk |
| deploy-mcp Deployment tracking and monitoring with live status badges. | 10 ★ | Review before installing |
| twitterapi-docs-mcp Offline access to TwitterAPI.io documentation: endpoint references, guides and authentication docs. | 10 ★ | Low risk |
| LynxMCP Local semantic code search with AST-aware chunking, hybrid BM25 and dense retrieval, and a code knowledge grap | 10 ★ | Low risk |
| docket Shared todo list and backlog for coding agents, filed per project by git remote, with claims to avoid duplicat | 10 ★ | Low risk |
| godotlens-mcp Semantic GDScript analysis via Godot's built-in LSP: navigation, references, diagnostics, rename and file sync | 10 ★ | Low risk |
| apifable Explore OpenAPI specs, search endpoints and generate TypeScript types. | 10 ★ | Low risk |
| xlide_mcp Read, write, analyze and test VBA in Excel, Word, PowerPoint and Access files, with static analysis; the file | 10 ★ | Low risk |
| piston-mcp Execute code through the Piston remote code execution engine. | 9 ★ | Review before installing |
| cursor-delegate-mcp Delegate multi-file implementation to Cursor's CLI agent over ACP and get typed results: final message, change | 9 ★ | Low risk |
| llm-bus Coordination bus for multiple coding agents: atomic claims, advisory file leases, a shared event ledger, prese | 9 ★ | Review before installing |
| redcon Deterministic repository context packing for coding agents: selects, compresses, caches and budgets only the f | 9 ★ | Low risk |
| deed Contract-first programming language: check types, effects, capabilities and contracts in agent-written modules | 9 ★ | Low risk |
| mcp-web-validator Validate HTML and CSS, audit technical SEO and accessibility, check JSON-LD and public links, and capture resp | 9 ★ | Low risk |