开发 MCP 服务器

Converts any OpenAPI/Swagger specification into MCP tools automatically.

Let your coding agent see the squiggles — LSP diagnostics, navigation, refactoring, and extras

Discover and compare L402 and x402 paid API services from satring.com, a curated Lightning and USDC API directory.

Git content governance, 23 deterministic MCP tools. Hosted: docs.contentrain.io/developer/mcp-cloud

Keyless local MCP server for QA: standards retrieval, effort estimation, doc review, test analysis.

Wraps Claude Code CLI as MCP tools: query, search, structured, ping, listSessions.

Find a retrieval MCP server that works today: a daily-checked list of servers that search knowledge.

Local launch-readiness audit for AI-built apps: read-only checks, an evidence-based 0-100 score and guided fixes.

Local serial hardware access for coding agents with typed YAML commands, checksum validation, audited writes, lossless captures,…

Transform project ideas into paint-by-numbers development plans with phases, tasks, and subtasks.

Convert a codebase into a local AST knowledge graph that gives coding agents structural context for navigation and refactoring.

Read-only search over a local index of your engineering stack (GitHub, Jira, Slack, PagerDuty, Datadog and more): incidents, PRs,…

Turn any OpenAPI spec into an executable agent interface using graphs and semantic search.

Enforces critical rules for Claude to prevent documented failure patterns, with a compliance verification checklist and rules summary.

Live docs MCP server. 793+ libraries, evidence-verified answers, code audit, snippets, dispatch.

Search, retrieve, and diff the full output of past terminal commands recorded locally by backscroll.

Delegate real-world actions from Claude Code, Codex, and other agents to Hermes Agent.

WasmAgent MCP server — WASM-sandboxed code execution with capability manifests and Tasks API.

.FAF Context — persistent project context for Cursor, VS Code and every MCP-compatible IDE.

Search 13,870+ MCP servers, 4,384+ agent skills, and plugins from your terminal or agent.

Search, compare, and get docs for 210+ APIs ranked by CLI and agent relevance.

React Native and Expo health check: upgrade blockers, store rules, crash risks, security findings

Checks whether your idea already exists before your agent builds it. Searches GitHub, npm, Python.

Connects the AI agents you use: your agent hands a task to another and gets the answer back

Local MCP broker that exposes one compact entry for many upstream servers.

Markdown reader and editor that tells coding agents what you are reading: the open document, section and selection, unread changes, your…

Exposes .context/ folder files as MCP resources so Claude Code can reference project documentation via @ mentions.

Interact with feature flags in Flipt.

Gentoro generates MCP Servers based on OpenAPI specifications.

ChatGPT (Codex CLI) and Claude (Claude Code) discuss until they agree, on your own subscriptions.

Mobile E2E MCP (51 tools): iOS + Android, native UI + canvas/WebGL, no-vision, RN debug

Local-first safety and verification layer for coding agents: workspace confinement, command allowlists, scope-violation detection and…

Drive tmux locally or over SSH: sessions, windows, panes, keystrokes, pane capture and raw commands, with shared sessions for pair…

Authenticated calls to any REST API: auto-login, token caching, 2FA/OTP support, Swagger spec fetching and fuzzy endpoint search.

Self-hostable GPU-aware job broker: submit, route by VRAM, babysit jobs across machines via MCP.

WordPress management via WP-CLI, locally or over SSH: themes, plugins, posts, menus, users, database, scaffolding and cache.

Multiplayer mode for AI coding agents: team huddles, master prompt, task board, file claims.

Monitors coding-agent token cache using inventory theory (EOQ) and signals optimal session restart timing via a live dashboard and…

Web scraping MCP — extract clean markdown, links, and metadata from any URL.

Record and share AI-driven development history: saves project milestones with summaries, generates planning prompts and publishes to…

Aggregates tools from multiple MCP servers with unified BM25/regex search and deferred loading.

MCP server exposing rlg log streams to LLM agents via JSON-RPC 2.0 over stdio.

Agent gateway for Index discovery, AN Score evaluation, and Resolve governed execution

Cut 95% of framework noise and token bloat from error logs for AI agents.

Converts website and web app feedback and bug reports into context-enriched developer tasks for coding agents via Webvizio.

CNC machine control via Universal G-code Sender. Jog, home, run files with hardware safety tokens.

Local image and video processing: resize, convert, compress, crop, thumbnails, metadata extraction, rotate, flip, filters and ffmpeg-based…

Bridge MCP servers to the AGENIUM agent:// network with DNS resolution and mTLS

Utility tools with x402 micropayments: JSON validation, base64, hashing, UUIDs, regex testing, Markdown and datetime conversion, cron…

Reports which of your code's API usages break when you upgrade a dependency (Python, .NET, Java).

Timezone-aware date and time operations: IANA timezones, timezone conversion and daylight saving time handling.

Find and remove the writing patterns a profile lists. Deterministic rules, model rewrite opt-in.

Hybrid computer-use runtime combining the accessibility tree, Chrome DevTools Protocol and vision into structured context, with offline…

Let agents drive vim, htop, lazygit: send keys, wait on screen state, read the rendered cell grid.

Job aggregator for AI agents across platforms such as x402, RentAHuman and Virtuals.

Local full-text search over zsh, bash and fish history, with secret redaction and optional capture of cwd, exit code and duration.

Translate design tokens between Tailwind, Figma, CSS, Material 3, and SwiftUI

Terminal, filesystem and background-job tools for Linux and macOS.

Control an OBSBOT Tiny 2 camera: pan/tilt/zoom, AI tracking, focus, exposure, snapshots, recording

Autonomous coding pipeline: frontier models plan and review, open-weight models write the code.