saybooksCAUTION
Saybooks — open-source books an AI agent can keep: invoicing, order to cash, CRM, job hunt and personal finances over one MCP connector, with rules the agent cannot break and one audit trail for people and agents. AGPL-3.0.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
The books you can talk to. The books that stay books.
Saybooks is an open-source ERP where your agent and your interface are the same system: one command registry, one rulebook, one audit trail. Tell Claude to ship the order, issue the invoice or import a card statement, or click the button: same command, same rules, same record of who did what and why.
Live: [saybooks.io](https://saybooks.io). Try the demo with no signup, or sign in with Google and pick the modules your books carry. Connect Claude by adding https://saybooks.io/mcp as a connector (OAuth, no keys to paste); the same books are in the browser as ordinary pages.
Eight modules today, every one spec-first with executable conformance scenarios:
Why this exists
"Conversational ERP" usually means a chat la
8d4bfccafba7OBSERVED · 2026-10-12Connect
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 saybooks --env GOOGLE_CLIENT_SECRET=${GOOGLE_CLIENT_SECRET} -- npx -y [email protected]{
"mcpServers": {
"saybooks": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"GOOGLE_CLIENT_SECRET": "${GOOGLE_CLIENT_SECRET}"
}
}
}
}Trust audit
CAUTIONgrade B · trust 84/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (5 observation(s))
- Network
- declared (7 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (15)
console.log(`\nbrowse: npm start → http://127.0.0.1:8140/?ws=${WS}`);console.log(`\nbrowse it: npm start → http://127.0.0.1:8140/?ws=${WS}`);const PUBLIC_FALLBACK = () => CFG.publicUrl || `http://127.0.0.1:${PORT}`;const key = require('crypto').createHash('sha1').update(logo).digest('hex');const entryNo = (e) => 'SB-' + require('crypto').createHash('sha1').update(`${e.date}|${e.memo}|${e.customer || ''}`).digest('hex').slice(0, 8);if (a.text) hash = 'sha1:' + require('crypto').createHash('sha1').update(String(a.text).replace(/\s+/g, ' ').trim().toLowerCase()).digest('hex').slice(0, 24);const { defineCommand, f, Rejected } = require('../../../registry.js');const H = require('../../../db.js');const CFG = require('../../../config.js');const wsp = require('../../../workspace.js');const scan = require('../../core/index.js').journal({ from, to: a.to });npm start # workbench on http://127.0.0.1:8140
const MODEL = arg('model'); const SCRIPT = arg('script'); const URL_ = arg('url', 'http://127.0.0.1:1234');@modelcontextprotocol/sdk, @napi-rs/canvas, better-sqlite3, express, pdfjs-dist, pdfkit
Gates applied: no_behavioural_pass.
8d4bfccafba7full audit observations/trust-audit/mcp-server/alviso__saybooks.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 |
|---|---|---|---|---|---|
| 2026-10-12 | 8d4bfccafba7 | CAUTION | B | 84 | first audit |
Questions
What is the saybooks MCP server?
Saybooks — open-source books an AI agent can keep: invoicing, order to cash, CRM, job hunt and personal finances over one MCP connector, with rules the agent cannot break and one audit trail for people and agents. AGPL-3.0.
Is saybooks safe to connect to an agent?
With care. The audit graded it B (84/100) and found 15 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does saybooks need?
It reads GOOGLE_CLIENT_SECRET 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 saybooks run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as saybooks at 0.2.0.
How current is this page?
The grade is for one exact copy of the source (8d4bfccafba7), read on 2026-10-12. The repository is watched and re-audited when it changes.