Every tool in the registry
50 listed · 12 vetted by hand so far. Vetted listings sort first; everything else is in intake, listed with facts and no verdict until a human runs it.
MCP servers · 37
context7 MCP server “It does what it promises, fresh version-specific docs on demand, and the one thing to know is right there in how it works. context7 is a thin client for a hosted service, not a local tool. Both of its tools send your query text and the library name to context7.com over HTTPS; the docs corpus and the reranking live on Upstash's servers, so the task you're asking about leaves your machine. That's by design, not a leak, but if you work under an NDA that covers your prompts, treat it accordingly. Small tool surface (two tools), no filesystem access, no local data touched, and no telemetry beyond the API calls it exists to make. Free without a key (rate-limited by IP); an optional key raises the limit.”
playwright-mcp MCP server “The rare tool that's safe by default. Filesystem access is restricted to your workspace roots, and navigation to file:// URLs is blocked unless you explicitly pass --allow-unrestricted-file-access. That's the opposite of the usual "wide open until you lock it down." No telemetry, and the only dependencies are Microsoft's own playwright packages. Two honest caveats, both about what the tool is rather than a flaw. It drives a real browser, so the agent can reach any site it navigates to, and the --allowed-origins and --blocked-origins flags say plainly in their own help text that they are not a security boundary. And by default it persists a browser profile to a temp dir (cookies, logins); pass --isolated to keep the session in memory only. Treat it like handing your agent a real browser with access to your project files, because that's what it is.”
postgres-mcp MCP server “Restricted mode is genuinely read-only, and it holds by two independent checks. Every statement is parsed with pglast and rejected if it isn't a read, then run inside a real BEGIN TRANSACTION READ ONLY, so Postgres refuses the write even if the parser were fooled. All 66 of the project's own enforcement and safe-SQL tests pass. Two things to know before you install. The default access mode is unrestricted, so execute_sql runs any SQL, including DROP; pass --access-mode restricted unless you mean to give an agent write access. And the LLM index-tuning method (method="llm") builds an OpenAI client against your own key, while the default method, "dta", is pure algorithm and never leaves your machine. No telemetry, no hidden network calls. The only outbound URLs it parses are your connection strings.”
posthog-mcp MCP server “This is not a read-only tool, and its reach is exactly the scopes of the personal API key you hand it. Of its 44 tools, 26 read and 18 write, and 5 of those delete production objects (delete-feature-flag, insight-delete, dashboard-delete, experiment-delete, survey-delete). The safety is real and server-enforced: every tool declares its required_scopes and PostHog checks them, so a key minted with only :read scopes mechanically blocks every write and delete. So mint one that way. Create a read-scoped personal API key unless you specifically want an agent creating feature flags in your live project. Second thing to know: the default install points at https://mcp.posthog.com/mcp, a hosted Cloudflare Worker, so your key and query results transit PostHog's own infrastructure (you already trust them with this data, and you can self-host by pointing POSTHOG_BASE_URL at your own worker). Two smaller notes: the docs-search tool sends your question to api.inkeep.com, a third party, and the server reports its own tool-call usage back to PostHog via posthog-node. No filesystem access, no other egress.”
sentry-mcp MCP server “Official, and it connects the way you'd hope. On sentry.io you don't paste a token, you approve a device-code login; self-hosted takes a token and a --host. Once connected it reads your org's real issues, errors, and traces. That's the point, and also the thing to be deliberate about. Production error data is where stack traces, user emails, and other PII live, and this pulls it into the model's context. Fine for most work, worth a thought under strict data rules. Two smaller notes. The server reports its own telemetry to Sentry via a built-in DSN (Sentry using Sentry; override it with --sentry-dsn if you'd rather it didn't), and --agent mode collapses the tool surface to a single use_sentry tool, which is the lighter way to run it inside an agent.”
serena MCP server “Because it works through language servers, it edits code at the symbol level instead of rewriting whole files. On a big repo that's more precise and a lot cheaper in tokens, and it's the real reason to reach for it. Two cautions before you install. First, this is an editing tool, not a reader. It modifies your source and writes "memory" files into a .serena directory in your project, so it earns a place in your .gitignore and the same review you'd give any other diff. Second, it ships an optional local web dashboard that binds to 127.0.0.1 only; the one outbound call in the whole tool is that dashboard fetching a news feed from the author's site, and you can turn the dashboard off. Tool-usage and token stats are computed and shown locally. Nothing about your code or activity is reported anywhere. Give it the respect you'd give anything that can edit your repo.”
21st-magic-mcp MCP server It's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic
apify-mcp MCP server The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scrapers…
atlassian-mcp MCP server MCP server for Atlassian tools (Confluence, Jira)
aws-mcp MCP server Open source MCP Servers for AWS
blender-mcp MCP server Open-source MCP to use Blender with any LLM
browserbase-mcp MCP server Allow LLMs to control a browser with Browserbase and Stagehand
chroma-mcp MCP server A Model Context Protocol (MCP) server implementation that provides database capabilities for Chroma
clickhouse-mcp MCP server Connect ClickHouse to your AI assistants.
cloudflare-mcp MCP server mcp-server-cloudflare: a Claude Code / MCP tool.
desktop-commander-mcp MCP server This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities
duckduckgo-mcp MCP server A Model Context Protocol (MCP) server that provides web search capabilities through DuckDuckGo, with additional features for content fetching and parsing.
elevenlabs-mcp MCP server The official ElevenLabs MCP server
exa-mcp MCP server Exa MCP for web search and web crawling!
fetch-mcp MCP server A flexible HTTP fetching Model Context Protocol server.
figma-context-mcp MCP server MCP server to provide Figma layout information to AI coding agents like Cursor
firecrawl-mcp MCP server Official Firecrawl MCP server. Adds web scraping and search to Claude, Cursor, and other LLM clients.
git-mcp MCP server Put an end to code hallucinations! GitMCP is a free, open-source, remote MCP server for any GitHub project
github-mcp-server MCP server GitHub's official MCP server: repos, issues, pull requests, and Actions through the GitHub API, hosted remotely or run locally in Docker.
grafana-mcp MCP server MCP server for Grafana
heroku-mcp MCP server Heroku Platform MCP Server using the Heroku CLI
hyperbrowser-mcp MCP server A MCP server implementation for hyperbrowser
mongodb-mcp MCP server A Model Context Protocol server to connect to MongoDB databases and MongoDB Atlas Clusters.
neon-mcp MCP server MCP server for interacting with Neon Management API and databases
notion-mcp MCP server Official Notion MCP Server
obsidian-mcp MCP server MCP server that interacts with Obsidian via the Obsidian rest API community plugin
qdrant-mcp MCP server An official Qdrant Model Context Protocol (MCP) server implementation
slack-mcp MCP server A Slack MCP server with no permission requirements: apps support, GovSlack, DMs and group DMs, and smart history fetching.
stripe-mcp MCP server One-stop shop for building AI-powered products and businesses with Stripe.
tavily-mcp MCP server Production ready MCP server with real-time search, extract, map & crawl.
unstructured-mcp MCP server UNS-MCP: a Claude Code / MCP tool.
zen-mcp-server MCP server Routes work to other models (Gemini, GPT, local) as second opinions inside one session: extended reasoning, review, and consensus workflows.
skills · 6
anthropic-skills skill “The reference pack, and it earns the title. Seventeen skills (the document formats docx, pdf, pptx, xlsx, plus builders like mcp-builder and skill-creator and the design skills), with an always-on cost of about 1,629 tokens, measured with tiktoken. The heaviest single description is xlsx at 238 tokens, fair for how much that one does; everything else is lean. Nothing here is a surprise, and that's the point of a reference implementation. This is what a well-built, well-scoped skill looks like, from the people who defined the format. Install the whole thing without worrying about the cost.”
cc-skills skill “Twenty skills, about 4,000 always-on tokens measured with tiktoken (~200 each), because until a skill fires only its one-line description is loaded. The scoping is better than most: descriptions say "use when X" and "do not use for Y," and cross-reference their siblings. The catch is the default install. Both the marketplace path and the CLI's --all load all 20, and a few triggers are deliberately greedy (frontend-design-deslop fires on "build a UI for X," deep-research on "look into X," copywriting-hooks on the word "hook"), so they fire on generic requests. Install the ones you want by name with --skill instead of taking the whole set. No scripts, no network calls of its own, no telemetry, MIT. Clean, with a cost you should choose on purpose.”
marketing-skills skill “Forty-seven senior-level marketing skills (SEO, CRO, copywriting, ads, analytics), and the content is the real thing: framework-driven, correct, cross-referenced. Two things to size up before you install all of it. First, the whole pack is about 8,000 always-on tokens on every turn, roughly five times Anthropic's official pack, for skills most engineering work will never trigger. Second, it bundles 64 Node scripts under tools/clis/ that read vendor API keys from your environment and call those vendors' APIs (Resend, Klaviyo, Google Ads). Those are opt-in and never auto-run, each reads only its own vendor's key, and they support a dry-run, but they are a surface worth knowing. Nothing phones home, no self-promo is injected into output, MIT. Install the two or three skills you need with --skill, and the cost and the scripts both stay out of your way.”
vercel-agent-skills skill “Vercel's own skills for React, Next, and deploys, and they are built with care: about 850 always-on tokens across nine skills, token values redacted from output, shell calls made through execFile rather than a shell string, and no telemetry. One skill needs a clear-eyed look before you use it. deploy-to-vercel tars your whole project and POSTs it to a Vercel endpoint (claude-skills-deploy.vercel.com) with no auth, producing a preview URL anyone can claim. It excludes node_modules, .git, and .env files first, and the skill asks before pushing, so it is a disclosed design, not a leak. Know that your source leaves your machine when you run it. The rest (react-best-practices, composition-patterns, view-transitions, web-design-guidelines) are read-and-advise skills with no such surface.”
writing-humanizer skill “A single, clean skill that lives inside a large collection, and the install command is the whole verdict. Point it at the one skill (pnpx skills add hairyf/skills --skill writing-humanizer) and it costs about 145 always-on tokens: a text editor that scans writing for two dozen AI tells (inflated significance, rule-of-three, em-dash overuse, copula avoidance) and rewrites them, from Wikipedia's "Signs of AI writing." Install the whole collection with --all -g and you pay for 68 skills at about 32,000 always-on tokens, most of them auto-generated from library docs and, by the author's own note, "not fully tested." The skill dir holds only markdown, no scripts or network calls. Vet the skill, not the dump.”
kostja-marketing skill “A large, genuinely well-researched marketing pack (172 skills across SEO, 40 page types, paid ads, and channels) with two problems that put it behind the gate. It is heavy: about 17,000 always-on tokens if you install all of it, roughly ten times Anthropic's official pack, on every single turn. And ten of the skill bodies embed the author's own site (alignify.co) as a "reference" link, so your agent's output quietly carries the author's lead-gen. Neither is fatal. The content is substantive and correct, the source has no scripts or telemetry, and it is MIT. But install the whole thing and you pay a large standing token tax and hand the author placement in your output. Install the handful you need with --skill, and both problems shrink to nearly nothing.”
plugins · 2
superpowers plugin “The discipline pack, and it's honest about its cost. Fourteen skills (brainstorming, test-driven development, systematic debugging, plan writing, git worktrees), and the whole set adds only about 577 tokens of always-on context, measured with tiktoken, because until a skill fires, its one-line description is all that's loaded. The scoping is tight. Most descriptions are "use when…" triggers, so they stay quiet until they're relevant. One stylistic heads-up rather than a fault: a few are written as hard commands ("You MUST use this before any creative work"), which will nudge the model firmly. That's the point if you want the guardrails, worth knowing if you don't. Progressive disclosure done the way the mechanism intends.”
awesome-claude-code plugin A hand-picked collection of the finest of resources for the most awesome of agents, Claude Code, the undisputed champion of coding companions, from the unstoppable team at…
subagents · 2
claude-code-subagents subagent “Seven subagents (code refactorer, frontend designer, PRD writer, security auditor, and more) with genuinely useful system prompts, held back by stale packaging. One commit, dated 2025-07-25, and it shows. The tool grants are the problem. Three agents (content-writer, frontend-designer, vibe-coding-coach) declare no tools: line, so they inherit every tool including Bash and web access. The security-auditor is granted Write and Edit but no Read, an auditor that can rewrite your files while shelling out to read them. The project-task-planner is told in its own prompt it is "not allowed to action any tasks," then handed Bash, Write, and Edit anyway. Add deprecated tool names (MultiEdit, LS) and two agents whose examples call themselves by names that no longer match. The prompts are worth reading. Copy the one or two you have reviewed into .claude/agents/, set each agent's tools: to the minimum it needs, and do not bulk-install the folder.”
wshobson/agents subagent A large catalog of production-focused Claude Code subagents: reviewers, architects, and language specialists, installed per project or globally.
