开发 MCP 服务器

USB-HID keyboard/mouse (Pico 2, open firmware) as MCP tools; --mock runs with no hardware

Turn any REST API into a hosted MCP server, with ready-made public servers for GitHub, Stripe, Slack, OpenAI, Notion and more.

iOS code quality and test automation: Xcode test execution, SwiftLint integration and failure analysis. Also runs as a CLI.

Search, install and manage agent skills (SKILL.md files) from GitHub repositories, with workspace analysis for personalized recommendations.

Zero-configuration Go library that exposes existing Echo web framework APIs as MCP tools.

Secure MCP gateway and quarantine for AI agent traffic — three-layer prompt injection defense

Agentic UX testing for real Electron apps: launch, inspect, interact, and assert through MCP.

Local-first persistent memory for AI coding agents - 96.0% R@5 on LongMemEval, zero LLM calls.

SSH access with persistent sessions, SFTP and port forwarding, with secrets injected via stdin and redacted from output before reaching…

Generate and visualize unified diffs as HTML or PNG, with side-by-side and line-by-line views for filesystem dry runs.

Add smart Backup ability to coding agents like Windsurf, Cursor, Cluade Coder, etc

Access CSV files via RestCSV.

Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM

Convert any Git repository into a text digest of its codebase using gitingest.

Electronic component datasheets for AI agents: pinouts, specs, package info and design checks.

MCP-to-ACP bridge — let any MCP client drive ACP coding agents

SWI-Prolog as a logic calculator for LLMs

Check, compile, run, and test Sounio programs locally.

Hybrid semantic and keyword code search for coding agents.

Local code search for agents: symbols, usages, call graph, AST patterns, grep and semantic search

Run Codex agents from Claude Code through MCP and Channels, with live progress notifications, mid-task steering and session continuation.

Search, inspect and install Ballmac UI React and Tailwind components, blocks and templates.

Code-pinned team memory for AI coding agents — typed artifacts, MCP-native, self-host.

Self-hosted federated MCP gateway: one OAuth 2.1 MCP server in front of N apps, user-level scopes.

Read, write, analyze, test and diff the VBA in Office files, and the document around it

Find, document and execute authenticated API calls across 1000+ apps via one MCP server

Lint AI agent context files (CLAUDE.md, AGENTS.md, etc.) against your actual codebase

Engineering decisions, change impact, documentation audits, and CI evidence for coding assistants.

Agent runtime with typed memory, knowledge and code graphs, plus file and web tools

Drop-in MCP proxy. 71% fewer tokens. Session dedup compounds to 92%. Zero code changes.

Buildable development platform: manage tasks, track progress, get project context and collaborate with humans on software projects.

Conan C/C++ package manager: create projects, manage dependencies, check licenses and scan for security vulnerabilities.

MCP server for Google Play: full Android Publisher API v3 and Play Developer Reporting API.

Code-quality gate for Bazel monorepos: runs lint, coverage and architecture checks from the build graph and returns a pass/fail verdict.

GitLab and Jira: manage projects, merge requests, files, releases and tickets.

Angular UI expert for NeuralNg discovery, composition, validation, icons and project-aware themes.

Modern SSH for AI agents — cloud servers to BusyBox routers, with destructive commands blocked.

Query a codebase map (routes, features, flows, impact) built by static analysis.

Jam recordings (video, console, network) as context and proof of work for your coding agent.

LynxMCP: 100% local MCP server for the code questions grep can't answer: call graph, hybrid search

MCP server for .NET memory profiling — in-process heap snapshots via EventPipe with leak heuristics

Vendor-neutral home for portable agents: skills, MCP tools, memory, canvas, and secret proxy.

Up-to-date documentation for npm packages, fetched from the latest README in the package's GitHub repository.

Coordinate local coding agents and track handoffs.

Author, edit and run Bruno collections as files: HTTP, WebSocket, gRPC, per-request pass/fail.

Local Claude Code and Codex sessions on one machine exchange letters through native inputs.

ASO analytics and App Store optimization tools for indie iOS developers and AI agents.

Command wrapper MCP server for coding agents, compression, workflows, and local automation.

Delegate small coding tasks to local Ollama/llama.cpp models; patches gated by real test runs.

Start and manage Reason cloud coding agents, projects and sessions from any MCP client.

Make AI self-correct its generated output through prompt injection, independent self-auditing and context isolation.

A map of your codebase for AI agents: code graph, search, call paths and change impact. No API key.

Serves coding agents one canonical doc per query instead of rereading the repo — ~60% fewer tokens.

Give AI coding agents access to your Vynix visual feedback, bug reports, and AI diagnosis.

Offline Garmin Connect IQ SDK documentation with search and API examples.

Dynamic SOC security threat analysis for a Text2SQL AI agent.

Deployment tracking and monitoring with live status badges.

Remote control for MiSTer-FPGA: launch games, search ROMs, take screenshots, manage systems and set up Tailscale VPN, with automatic core…

Let one coding-agent CLI consult another: Codex, Claude Code, OpenCode, Copilot or Antigravity.

Offline access to TwitterAPI.io docs for AI assistants. 67 endpoints, 32 pages, 24 blog posts.