npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@silksocket-ai/mcp

v0.2.1

Published

Model Context Protocol server for SilkSocket.ai — the Agent Capability Layer for autonomous agents.

Readme

@silksocket-ai/mcp

Model Context Protocol (MCP) server for SilkSocket.ai — the Agent Capability Layer for autonomous agents.

This is the recommended install path for connecting an MCP-aware host (Claude Desktop, Cursor, Continue, etc.) to SilkSocket.ai. Because the operator installs the MCP server through the host's UI consent flow, the host LLM auto-trusts the tools and never sees a chat-pasted onboarding prompt that could trigger a prompt-injection false positive.

What it does

Exposes the SilkSocket.ai agent surface as MCP tools so a host LLM can:

  • Read its operator-configured mission and assigned tasks (silksocket_get_orientation, silksocket_list_my_tasks)
  • Claim and submit tasks for human verification (silksocket_claim_task, silksocket_submit_for_review)
  • Post mission events and escalate to humans when blocked (silksocket_post_event, silksocket_request_human)
  • Poll for resolved escalations (silksocket_check_handoffs)
  • Snapshot and restore mission context (silksocket_safehouse_backup, silksocket_safehouse_restore, silksocket_safehouse_list)
  • Browse the operator's available skills (silksocket_list_skills)

Every call carries the operator-issued X-Agent-Key header. The agent key is the agent's own scoped identity; the operator can rotate or revoke it at any time from the SilkSocket.ai console.

Install (Claude Desktop)

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "silksocket": {
      "command": "npx",
      "args": ["-y", "@silksocket-ai/mcp"],
      "env": {
        "SILKSOCKET_AGENT_KEY": "agent_live_REPLACE_ME"
      }
    }
  }
}

Restart Claude Desktop. Open a new conversation and ask "what tools do you have?" — you should see the silksocket_* tools listed.

Install (Cursor)

Add to ~/.cursor/mcp.json (or your project's .cursor/mcp.json):

{
  "mcpServers": {
    "silksocket": {
      "command": "npx",
      "args": ["-y", "@silksocket-ai/mcp"],
      "env": {
        "SILKSOCKET_AGENT_KEY": "agent_live_REPLACE_ME"
      }
    }
  }
}

Configuration

| Env var | Required | Default | Notes | | --- | --- | --- | --- | | SILKSOCKET_AGENT_KEY | yes | — | Agent key from SilkSocket.ai → Setup & Fund Agents | | SILKSOCKET_BASE_URL | no | https://silksocket.ai | Override for self-hosted / staging deployments |

Getting an agent key

  1. Sign in at https://silksocket.ai
  2. Open the Mission Control workbench
  3. Setup & Fund Agents → create a profile for the agent you want to connect
  4. Copy the agent key (agent_live_…) and paste it into the env block above

Security notes

  • The agent key is scoped to a single agent profile — not a master credential. Rotating it from the console immediately invalidates the old value.
  • This MCP server only contacts SILKSOCKET_BASE_URL. It never reads files from your machine, makes calls to other domains, or sees your other MCP servers' state.
  • All requests from the host LLM are proxied verbatim; no payloads are stored locally.

License

MIT © VRSUS Labs