开发 MCP 服务器

List, create and update test cases in TestCollab with filtering, sorting and pagination.

Chat, generate, pull, list and inspect models with Ollama.

The WhenLabs developer toolkit — 6 tools, 7 MCP endpoints, one install.

Deterministic local cross-service API-chain discovery for AI coding agents.

Wopee.io AI testing agents: dispatch analyses and test runs, fetch artifacts and results.

Access JSR, the JavaScript Registry.

Client teams' blueprints for coding agents (token from an engagement). Free: agentblueprint.ai/mcp

Discover AgentBodega paid data tools, contracts, and x402/L402 HTTP payment handoff metadata.

Search thousands of MCP connectors from the AgentHotspot marketplace via your AI agent.

Deterministic prose linter for LLM text — flags AI slop, filler, buzzwords, hedges, clichés.

Look up SDKs, frameworks and dependencies used by macOS and Windows desktop apps, search by technology adoption and compare stacks via…

Read-only registry of animated companion packs (pets) for Codex: search, preview and install community pets and generate badges and embed…

Operate Codex projects and tasks from a Chief of Staff with scoped access and durable receipts.

Agent-optimized MCP server with structured JSON tools. 20-45% token savings.

Local-first MCP runtime for coding agents with safe workspace access, AST/LSP navigation, and Git.

Prior art for AI agents. claim --yes --share-yes shares to the commons; claim --yes stays local.

Tools for agent supply-chain security, scanner consensus and x402 reliability, plus access to Vibes-Coded's commerce catalog.

UploadKit MCP — 40+ upload components, route scaffolds, BYOS setup, full docs search.

Drive a real iPhone or an iOS Simulator with an AI agent, through XCUIAutomation.

Delegates documentation and code analysis, including calls to other MCP servers, to a local or low-cost OpenAI-compatible LLM to save…

Shared fleet memory for AI agents: nightly self-correction, recall every prompt (supported agents).

914 paid market-data & token-safety endpoints — keyless x402 USDC: Base, Solana, XRPL, +8 chains

Version-aware docs for coding agents: finds llms.txt, OpenAPI and skill specs, resolves dependency versions, detects pitfalls and verifies…

AST-based codebase map, token compression and context packaging for AI coding agents and IDEs.

Transparent proxy that sits in front of any other MCP server and shrinks its tool output before it reaches the model. Lossless by default…

Feedback loop for coding agents: CI monitoring, process watching, file change detection and HTTP polling.

Search 25K+ verified engineering fixes by error or technology. For developers and AI agents.

Fail-closed quality gate and hash-chained receipt ledger for AI agent workflows.

Hot-reload for MCP servers + mount any community server mid-session, Docker optional. No restarts.

Semantic map of a .NET test-automation solution for AI agents — search, impact, endpoints

Bug fixing for AI-built apps: plain-English diagnosis + a ready fix, in your editor.

Read-only Nacos config and service discovery for Spring Cloud repos: finds environments from application/bootstrap files and diffs config…

21 Mamba Labs account-intelligence MCP tools in one server: identity, signals, ICP. Clay-ready.

Agency-grade MCP for WordPress Elementor — multi-site, safe edits, templates, versions.

Linux MCP server for real-time system monitoring - CPU, memory, disk, network, processes, Docker.

Write to Figma from any MCP client (Claude Code, Cursor). Complements the read-only official MCP.

Many stdio MCP servers from one container, published over HTTPS with OAuth 2.1 for any MCP client

9 MCP servers for React/TypeScript — dep auditing, a11y, test gen, and TypeScript enforcement.

Strict AI code reviewer powered by Groq. Finds bugs and vulnerabilities.

MCP server for DNS lookups, reverse DNS, WHOIS, and domain checks — zero auth, zero config

Coding agents build full-stack apps in persistent workspaces and share them by link.

Returns only the unit tests affected by your current Kotlin/Android code changes.

Snapshot tests and CI for agent workflows: record a run, replay it at 0 tokens, diff for drift.

Connect your AI agent to anything — APIs, databases, and agents; read and write, auto-discovered.

OzBridge: run Warp Oz agents from any MCP client — Claude Code, Cursor, Codex, VS Code.

x402station.io: independent risk-signal layer for x402 endpoints before agents pay.

AI phone number directory: query Voxie AI personas and third-party AI services such as ChatGPT and get webchat links.

Apple Music control on macOS: DJ daemon and energy mixes, multi-room AirPlay, Spotify and M3U playlist import, listening journal and Apple…

Hire and pay specialized AI agents in USDC on Base. Open MCP protocol above x402.

NowSecure Platform mobile security testing: list applications, pull remediation findings and generate PDF reports locally.

Deterministic context pruning middleware for AI coding agents. Cuts input tokens by 60%, drops local CPU TTFT by 62%, and enforces formal…

Host-level telemetry gateway letting sandboxed agents fetch container logs and track kernel resource metrics.

Generates Architecture Decision Records from Claude Code conversations, with quality review, duplicate detection, a dependency graph and…

Read-only MCP server for ROS2 and DDS: topics, participants, QoS mismatches, bags.

Turn a Mac into a remote computer-use server via CUA: screenshots, mouse, keyboard, windows and apps, token-protected and exposed through…

Debug STM32 firmware on real hardware via GDB + OpenOCD/ST-Link/J-Link with decoded results.

Dependency intelligence for AI agents. CVE scanning, health checks, upgrade planning.

Intelligence endpoints for security, company, threat, compliance, sales, sports, property and health data, paid via x402 micropayments on…

Outbound-only remote shell, detached long-running jobs and temporary file transfer for AI agents, without exposing SSH, ports or a VPN.

Local MCP proxy: collapses N servers' tools into 4 meta-tools and compresses large tool outputs.