开发工具 MCP 服务器

Secure secrets proxy for AI agents — manages API keys so agents never see raw credentials.

Maintain and use API collections, replacing REST clients like Postman or Insomnia.

Repository intelligence, code graph, history, papertrail, and cross-agent memory for coding agents.

Identifies refactoring hotspots to help agents improve code.

Read-only debugging for Hono apps: recent exceptions with their requests, logs and queries, requests filtered by status or duration, and…

Self-hosted server that captures design patterns, conventions and decisions from git history and developer feedback and serves them to…

Endor: run services like MariaDB, Postgres, Redis, Memcached, Alpine or Valkey as pre-configured apps in isolated sandboxes.

Encoding-aware, indentation-smart file tools for AI coding agents with SSH, SFTP, and 20+ tools.

Persistent decision memory for AI agents: rationale, rejected approaches, and entity history.

Performance testing with Grafana k6.

Manage Reflag feature flags from chat in your IDE.

Securely store and access API keys across projects using the macOS Keychain.

Interact with Bugsnag.

Analyze and compare public GitHub repo line counts (SLOC) via OctoCounts, from any MCP client.

Local, deterministic review of Git changes: weakened tests and CI gates, risky flows, blast radius.

Code generator for Arbitrum: Stylus smart contracts, SDK bridging, full-stack dApps and Orbit chain deployment, backed by RAG over…

Keep the state. Change the model. Shared context and a multi-model panel across coding assistants.

Manage Higress gateway configuration and operations.

Cross-repository semantic code intelligence for AI coding agents, from a local code graph.

MCP server giving AI agents eyes and hands inside Android devices via ADB

Identifies resource-intensive processes on macOS and suggests performance improvements.

Persistent project context for Claude. IANA-registered .faf format.

Let AI agents explore SystemVerilog, Verilog and VHDL designs: connectivity, hierarchy, source.

Review comments pinned to a running frontend, read and resolved by your coding agent.

Gives AI coding tools context from your entire codebase and docs via Sequa.

Perfetto trace analysis: run PerfettoSQL queries on trace files, with Chrome tools for page loads, scroll jank, main-thread hotspots and…

Local-first design contract layer: scans Figma, code, Storybook and token files, reconciles conflicts and serves a single source of truth…

Self-healing CI tests and proof of work for AI agents

Ship iOS and Android apps end to end: App Store Connect, Google Play Console and Expo EAS builds, listings, screenshots, privacy labels,…

Zuul CI — build failure analysis, log search, pipeline status, and job configuration

Annotates any web page with hover labels for AI assistants — zero extensions, any browser

Control the iOS Simulator.

Agent-safe structured edits: JSON/YAML/TOML/md/AST, dry-run, batch/tx. Not a filesystem MCP.

Excel MCP with image extraction and write support — AI agents see and edit xlsx files

MCP server for codewiki.google: search repos, fetch wiki docs, ask questions

Android MCP server for AI-assisted development. Build, test, emulate, and automate.

Proof and repair for Apple coding agents: validate Swift, run Xcode evidence, and repair failures.

Run code in multiple programming languages locally via Docker.

Drive an Android emulator or device over adb: screenshot, inspect UI, tap, type, build and test.

Manage and serve dynamic prompt templates using a text template engine.

Enables AI agents to interact with ConfigCat, a feature flag service for teams.

Structural memory for coding agents: callers, callees, blast radius and symbols over MCP.

Discover, manage and codify cloud resources with Firefly.

Extract a visual contract from a reference page and measure an implementation against it

Dynamically load Claude Code skills into AI agents without copying files.

MCP server giving AI agents interactive .NET / ASP.NET Core debugging via netcoredbg + DAP.

Scans a repository for dead code, duplication, churn and structure and erases what the scan found, with a log of every erasure; the…

Hierarchical context tree and 13-tool MCP server for AI code context management.

Props, examples, CSS variables and Agent Skills for bestax-bulma React components (Bulma v1)

Retrieve SonarQube project information: current and historical metrics, issues and health status.

MCP server for n8n: generate, lint, explain failed executions, drive live n8n via REST.

iOS leak/perf debugging via MCP: memgraph cycles, .trace analysis, SourceKit-LSP bridging.

Reads local Claude Code, Codex and OpenCode usage logs: token totals, daily and hourly activity, per-agent and per-model breakdowns and a…

Local DevDocs MCP Server (Developer Docs with project specific context awareness)

Voice interface for Claude Code: talk to your agent and it talks back while it works.

Render and verify native Rust GUIs headlessly: access tree, query, a11y, screenshots, motion.

MCP server for API testing. 35 tools: HTTP, assertions, flows, OpenAPI, collections.

Curated Swift and SwiftUI patterns and real-world code examples from sources like Swift by Sundell and SwiftLee.

Routes code search through language-server indexes (clangd, Roslyn, tsserver, pyright) instead of grep, plus symbol-level edits and git/p4…

AI prompt optimization for 58+ platforms across 7 categories with custom platforms