Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
An agent's account economics — plan quotas, metered usage, invoices, receipts, and earnings.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
THREE_WS_BASE, THREE_WS_TIMEOUT_MS, THREE_WS_SESSIONValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"billing": {
"command": "npx",
"args": [
"-y",
"@three-ws/billing-mcp"
],
"env": {
"THREE_WS_BASE": "your-value",
"THREE_WS_TIMEOUT_MS": "your-value",
"THREE_WS_SESSION": "your-value"
}
}
}
}Run this in your terminal
claude mcp add billing --env THREE_WS_BASE=your-value --env THREE_WS_TIMEOUT_MS=your-value --env THREE_WS_SESSION=your-value -- npx -y @three-ws/billing-mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"billing": {
"command": "npx",
"args": [
"-y",
"@three-ws/billing-mcp"
],
"env": {
"THREE_WS_BASE": "your-value",
"THREE_WS_TIMEOUT_MS": "your-value",
"THREE_WS_SESSION": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"billing": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@three-ws/billing-mcp"
],
"env": {
"THREE_WS_BASE": "your-value",
"THREE_WS_TIMEOUT_MS": "your-value",
"THREE_WS_SESSION": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
THREE_WS_BASE envTHREE_WS_TIMEOUT_MS envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account nirholas, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: THREE_WS_SESSION
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.3) reached the registry 27 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, FactLot
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Cited CRE facts and deterministic calculators for agents: rent, CAM, debt sizing, IRR, parcel IDs.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
@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.
npm install @three-ws/billing-mcp
Or run with npx (no install):
npx @three-ws/billing-mcp
Claude Code, one line:
claude mcp add billing -- npx -y @three-ws/billing-mcp
Claude Desktop / Cursor (claude_desktop_config.json or mcp.json):
{
"mcpServers": { "billing": { "command": "npx", "args": ["-y", "@three-ws/billing-mcp"], "env": { "THREE_WS_SESSION": " " } } } }
THREE_WS_SESSION is required for every read except the public fee rate, it's the value of the __Host-sid cookie from a signed-in three.ws browser session, and the API uses it to resolve your account and return only your data.
Inspect the surface with the MCP Inspector:
npx -y @modelcontextprotocol/inspector npx @three-ws/billing-mcp
| Tool | Type | What it does |
|---|---|---|
get_billing_summary | read · session | Your plan tier, its quota ceilings, and live usage against them (avatars + storage, agents, MCP calls, LLM calls) + headroom. |
query_usage | read · session | Metered usage rolled into an invoice statement for a period, per-action line items, totals, and reconciliation. |
export_billing_history | read · session | The same line items as a ready-to-save CSV payload (with a suggested filename and a parsed preview). |
get_receipt | read · session | One itemized receipt, per-charge by event_id (with settlement tx + explorer link) or a signed skill-purchase receipt by purchase_id. |
get_fee_info | read · public | The current platform fee rate (fee_bps + fee_percent). Needs no session. |
Everything reads live state: usage and invoices move between calls, so no tool is idempotent, and nothing here mutates anything.
`get_billing_summary`: none.
`query_usage`: period (YYYY-MM, optional), from / to (ISO-8601, optional; ignored when period is set). Defaults to the current UTC calendar month.
`export_billing_history`: period, from, to (same as query_usage), preview_rows (0-100, default 5, how many parsed rows to echo in preview; the full CSV is always returned).
`get_receipt`: exactly one of event_id (numeric, per-charge receipt) or purchase_id (UUID, signed skill-purchase receipt).
`get_fee_info`: none.
// get_billing_summary: plan ceilings and live usage against them
{}
{ "ok": true, "plan": "free", "quotas": { "max_avatars": 10, "max_bytes_per_avatar": 26214400, "max_total_bytes": 262144000, "mcp_calls_per_day": 1000 }, "usage": { "avatar_count": 1, "total_bytes": 1234540, "agent_count": 1, "mcp_calls_24h": 0, "llm_calls_month": 0 }, "remaining": { "avatars": 9, "total_bytes": 260909460, "mcp_calls_today": 1000 } }
// query_usage: the period statement (defaults to the current UTC month)
{}
{ "ok": true, "period_label": "2026-08", "period": { "from": "2026-08-01T00:00:00.000Z", "to": "2026-09-01T00:00:00.000Z" }, "line_item_count": 0, "line_items": [], "totals": { "charge_count": 0, "gross_atomics": "0", "fee_atomics": "0", "net_atomics": "0", "gross_usd": "0.00", "fee_usd": "0.00", "net_usd": "0.00", "currency": "USDC" }, "reconciliation": { "total": 0, "reconciled": 0, "unreconciled": 0, "all_reconciled": true } }
// export_billing_history: the same statement as a ready-to-save CSV
{ "preview_rows": 5 }
{ "ok": true, "filename": "three-ws-invoice-2026-08.csv", "content_type": "text/csv; charset=utf-8", "row_count": 1, "preview": [ { "action": "TOTAL", "count": "0", "gross_usd": "0.00", "fee_usd": "0.00" } ], "csv": "action,label,count,units,gross_usd,fee_usd,discount_bps\nTOTAL,,0,,0.00,0.00,\n" }
// get_fee_info: the one read that needs no session
{}
{ "ok": true, "fee_bps": 250, "fee_percent": "2.5" }
A quiet account reads like the statements above: zeroed totals with all_reconciled: true. That is the healthy empty state, not a failed call. Every read without THREE_WS_SESSION (except get_fee_info) fails loudly instead of returning empty data:
{ "ok": false, "error": "no_session", "status": 401,
"message": "/api/billing/summary is account-scoped and needs your three.ws session. …" }
query_usage / export_billing_history / get_receipt, metered charges, the period statement, and the receipt behind any single charge.get_billing_summary sits above them: your plan, its quota ceilings, and how much headroom is left.
*_usd string, e.g. gross_atomics: "150000" is gross_usd: "0.15".reconciliation on the usage reads tells you whether every metered charge maps to a real on-chain settlement (all_reconciled, plus counts).https://three.ws (or your own THREE_WS_BASE).| Variable | Required | Default |
|---|---|---|
THREE_WS_BASE | no | https://three.ws |
THREE_WS_TIMEOUT_MS | no | 20000 |
THREE_WS_SESSION | yes (all reads but get_fee_info) | - |
THREE_WS_SESSION is the value of the __Host-sid cookie from a signed-in three.ws browser session. Treat it like a password, it grants read access to your private billing data.
Part of the three.ws SDK suite, 3D AI agents, on-chain identity, and agent payments.
Website · Changelog · GitHub