billing-mcpSAFE
An AI agent's own account economics over MCP — plan quotas, metered usage, invoices, receipts, and earnings. Read-only, account-scoped. Powered by three.ws.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
@three-ws/billing-mcp
An AI agent's own account economics over MCP, plan quotas, metered usage, invoices, receipts, and earnings. Read-only and account-scoped.
A Model Context Protocol server that lets an AI agent self-serve its own account economics over stdio: how much of its plan quota is left, what its metered usage rolled up to this period, the line-item invoice and per-charge receipts behind every charge, and the earnings its agents have made, all without pulling in the human account owner.
Every read hits the live three.ws billing API: nothing is mocked. The account-scoped reads run against the account you own, resolved from your three.ws session. This server is read-only: it surfaces private billing data but never signs, charges, or moves funds.
Install
npm install @three-ws/billing-mcp
Or run with npx (no install):
npx @three-ws/billing-mcp
Quick start
Claude Code, one line:
claude mcp add billing -- npx -y @three-ws/billing-mcp
Claude Desktop / Cursor (`claudedesktopconf
dc95b7f6162cOBSERVED · 2026-10-10Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add billing-mcp --env THREE_WS_SESSION=${THREE_WS_SESSION} -- npx -y @three-ws/[email protected]Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
.nojekyll
@modelcontextprotocol/sdk, zod
Gates applied: no_behavioural_pass.
dc95b7f6162cfull audit observations/trust-audit/mcp-server/nirholas__billing-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | dc95b7f6162c | SAFE | B | 89 | first audit |
Questions
What is the billing-mcp MCP server?
An AI agent's own account economics over MCP — plan quotas, metered usage, invoices, receipts, and earnings. Read-only, account-scoped. Powered by three.ws.
Is billing-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does billing-mcp need?
It reads THREE_WS_SESSION from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does billing-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @three-ws/billing-mcp at 0.1.3.
How current is this page?
The grade is for one exact copy of the source (dc95b7f6162c), read on 2026-10-10. The repository is watched and re-audited when it changes.