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

@reventlovmcp/mcp

v0.1.0

Published

Model Context Protocol server for Reventlov — log agent actions, decide approvals, issue directives, post financials, and more, directly from Claude.

Readme

@reventlovmcp/mcp

Model Context Protocol server for Reventlov — the control plane for AI-run businesses. Exposes the Reventlov dashboard API as MCP tools so Claude (Code, Desktop, Web) and any MCP-capable LLM can drive it directly.

> What's the state of Valerie right now?

  Claude calls get_company_overview.

> Approve the AWS payment.

  Claude calls list_pending_approvals → finds the match → decide_approval.

> Tell Valerie to follow up with last quarter's top customers.

  Claude calls issue_directive.

npm license

What it does

Thirteen tools, wrapping the public Reventlov API:

| Tool | Purpose | |---|---| | log_action | Record any agent action — emails, payments, code commits, files written | | list_recent_actions | Pull the recent activity timeline | | list_pending_approvals | See what's waiting on a human decision | | decide_approval | Approve or reject a pending action | | resolve_flag | Resolve / dismiss / snooze an open flag | | list_rules | Inspect the threshold / policy / anomaly rules a company has | | create_rule | Add a new rule | | issue_directive | Issue an instruction to the agent (hash-chained) | | list_directives | Read the directive history | | list_filings | Get the regulatory filings calendar with statuses | | post_cash_balance | Record a daily cash position | | post_bank_transactions | Bulk-ingest bank transactions | | post_financial_snapshot | Upsert an income / balance / cash flow statement | | get_company_overview | One-shot snapshot for "what's going on with X right now?" |

Full API docs: https://docs.reventlov.ai.

Install

You need:

  • Node 20+ (brew install node)
  • A Reventlov account with a human-scope API key (Dashboard → Settings → API keys)
  • A company id (looks like co_..., find it in the dashboard URL)

Then wire it into Claude.

Claude Code

claude mcp add reventlov \
  --scope user \
  --env REVENTLOV_API_KEY=sk_xxx \
  --env REVENTLOV_DEFAULT_COMPANY_ID=co_xxx \
  -- npx -y @reventlovmcp/mcp

Verify in any session:

/mcp

You should see reventlov listed with all 13 tools.

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS; similar paths on Windows / Linux):

{
  "mcpServers": {
    "reventlov": {
      "command": "npx",
      "args": ["-y", "@reventlovmcp/mcp"],
      "env": {
        "REVENTLOV_API_KEY": "sk_xxx",
        "REVENTLOV_DEFAULT_COMPANY_ID": "co_xxx"
      }
    }
  }
}

Restart Claude Desktop. The tools appear under the 🛠 icon.

Self-hosted Reventlov

If you're running Reventlov on a different host, set:

REVENTLOV_API_BASE=https://your-reventlov.example.com

Default is https://dashboard.reventlov.ai.

Running for an agent (instead of an operator)

If your agent runs on a model that speaks MCP natively, give it the same config and it can call log_action directly after every step. No bridge daemon required for those agents.

Security

API keys can read and write your account's data. Treat the value of REVENTLOV_API_KEY like a password:

  • Don't commit it to git.
  • Don't paste it in screen recordings.
  • Rotate via Dashboard → Settings → API keys if it leaks.

The MCP server runs entirely on your machine — no telemetry, no remote call-home. The only outbound traffic is to your REVENTLOV_API_BASE.

Versioning

The MCP follows SemVer. Breaking changes to the underlying Reventlov API are pinned via the X-Reventlov-API-Version header on every request, so a published MCP keeps working when the API evolves.

License

MIT. See LICENSE.

Contributing

Issues and merge requests welcome at https://gitlab.com/reventlov/mcp. Each tool is ~10 lines of zod schema + an async handler — adding a new one is a small change.