Extract a website’s design tokens (colors, type, spacing, shadows) as DESIGN.md, W3C, or CSS.
Loading MCP servers…
Extract a website’s design tokens (colors, type, spacing, shadows) as DESIGN.md, W3C, or CSS.
Showing 7,681–7,728 of 34,399
Task management system for AI assistants with MCP protocol, templates, and bilingual support (TR/EN)
Harbor Registry MCP — projects, repos, artifacts, storage reports, cleanup (with dry-run).
Kibana/Elasticsearch MCP — log search, aggregations, index discovery, dashboards.
SonarQube MCP — projects, metrics, quality gate, issues, worst-metric ranking.
A second opinion from an unrelated AI model before you commit to a decision.
App Store Connect MCP Server for AI coding agents
Google Play Console MCP Server for AI coding agents
Structured-output enforcer: extract and validate JSON from messy LLM text.
Token-aware message truncation: fit a chat history into your model's context budget.
Network-egress firewall for agent tools: check URLs against a declarative policy.
Validate tool-call args before execution. Returns LLM-friendly retry hints.
Context optimization for LLM agents: tool registry, result masking, budgeting, compaction.
Let AI agents use secrets without seeing them: inject into a command, redact the output.
Unofficial macOS MCP for Douyin AR (像塑): assets, menus, AI combine, delivery. For learning only.
Bridges any GraphQL API to Claude Code — auto-generates MCP tools via schema introspection.
Notify people through Cue: preferences, attention budgets, quiet hours and approval apply.
Python MCP server for PostgreSQL database inspection and querying
Auto-document vibe coding sessions - collect, summarize, and publish
Search 9 public discussion platforms for real opinions. Semantic routing, no API keys required.
Adversarial Quality Gate MCP for vibe-coding: IDE AI vs Critic AI, human decides on deadlock
Orccut: a real timeline video editor for AI agents - journaled edits, FFmpeg/MLT rendering
Interact with Frappe/ERPNext sites — document CRUD, search, and whitelisted method calls
Plan and verify multi-ecosystem packaging (Linux, Windows, macOS, HarmonyOS) for AI agents.
Safe MCP server for PostGIS and Oracle Spatial: query geodata and answer with maps.
Deterministic sub-0.2ms AST security circuit breaker and agent containment engine.
Hosted video editing for AI agents: cut, caption, mix and export real video. Sign in with OAuth.
Search, retrieve, compare, and render SVG icons visually for AI agents.
Talk to any Figma file with your AI: ask what's in it, change it, or turn it into code.
Google Workspace MCP — Docs, Drive, Calendar, Gmail, Sheets, Slides, Tasks, Chat, People, Forms
Google Workspace MCP — Docs, Drive, Calendar, Gmail, Sheets, Slides, Tasks, Chat, People, Forms
Read-only Lunch Money accounts, transactions, categories and budgets. Unofficial connector.
Unofficial read-only MCP server for your local WhatsApp chat history (stays on your machine).
Live forex, gold & crypto quotes, economic calendar, screener, currency strength, lot-size calc
MCP server for DiskCleanKit - One Touch Scan and Clean for Mac
Read-only network & security recon tools (DNS, TLS, headers, CORS) for AI agents, each graded.
Verifiable random decisions, audit sampling, fair selection, and proof verification using QnEvt.
Terminal output, project snapshots and semantic diffs as LLM-ready context
Your saved nanoodle workflow graphs as MCP tools — BYOK or pay per call in Nano (x402)
Thai data for AI agents: DBD company-registry lookup, address normalization, holidays, VAT/WHT.
Localize text, images, audio and subtitles with brand voice, memory and style guides.
Serve a Caotang writing project to an MCP host: read it, and, when you allow it, change it.
Self-hosted MCP server for Android Health Connect — 34 metrics, daily rollups, dedup, 5 LLM tools.
Figma designs pulled once into a local vault; AI agents read them offline with no rate limits
Local hybrid-search memory for AI agents over plain Markdown. Multi-tenant, offline, no LLM.
Refund eligibility notary for US subscriptions. Returns ALLOWED/DENIED/UNKNOWN.
Get a second opinion on your code from every coding agent you have. No API keys.
Read-only Spring Boot runtime evidence for agents: beans, routes, health, startup.