HelloBooks AI MCP Server
HelloBooks Public MCP Server
A public, read-only Model Context Protocol server that lets AI agents answer questions about HelloBooks accurately — pricing, integrations, country support, compliance frameworks — instead of relying on stale web snippets.
This is the public server. It exposes only marketing-derived, public-domain data. The authenticated MCP server that reads a customer's books lives in
AI-MCP-Hellobooks.
Install
Claude Code / Claude Desktop / Cursor
claude mcp add --transport http hellobooks https://agents.hellobooks.ai/mcpOr, for local development:
claude mcp add hellobooks-local node /path/to/HelloBooks-MCP-Public/dist/stdio.jsRelated MCP server: penni-mcp
Tools
Tool | Description |
| All HelloBooks plans (Free, Pro, Business, CPA) + Warehouse / Manufacturing add-ons. Optional |
| Banks, payments, payroll, time tracking, shipping, tax-compliance, accounting sync, ecommerce, CRM, storage (Drive/OneDrive), freelance (Upwork). Optional |
| Per-country feature availability (BAS, STP, GST e-invoice, MTD, 1099, etc.). |
| For a given country, the supported compliance frameworks with version + cert info. |
| Competitor positioning (QuickBooks, Xero, FreshBooks, Wave, Zoho Books, Tally) with where HelloBooks wins, where the competitor wins, and pricing notes. Optional |
| When statutory returns and payroll filings are due, per country. Covers IN (GSTR-1/3B/9/9C, CMP-08, Form 24Q, Form 16, PF ECR, ESI), AU (BAS, STP, Super Guarantee), GB (VAT MTD, RTI, Self Assessment), US (1099-NEC/MISC, W-2, Form 941/940), CA (T4, GST/HST). Optional |
| Local bank-rail / wallet payment methods (UPI, BACS, PayID, BPAY, ACH, RTP, Zelle, PayNow, FAST, Interac, …) with rail speed, use-cases, authority, and HelloBooks support level. Optional |
| Free-text search across the marketing feature catalog, plan features, integrations, country features, compliance frameworks, competitor positioning, statutory deadlines, local payment methods, and published articles. Queries like |
| Full 96-feature marketing catalog. Filter by |
| The 13 feature categories on the marketing site with per-category counts by status (live/beta/planned). |
| Published content on hellobooks.ai — head-to-head compare pages and curated flagship blog posts. Optional |
| Statutory tax-rate slabs by jurisdiction — IN GST (5/12/18/28 + zero + exempt + composition trader/manufacturer/restaurant), UK VAT (20/5/zero/exempt), AU GST (10/GST-free), US state-administered summary, CA GST + HST (ON, Atlantic), SG GST 9%, NZ GST 15%, AE VAT 5%. Filter by |
| Pick a single statutory rate by exact |
Resources
URI | Description |
| Markdown product summary. |
| Recent release notes as JSON. |
| Full marketing feature catalog (96+ features across 13 categories) as JSON. |
Security posture
Read-only by construction. No tool mutates state. No tool reaches a customer system.
Public data only. All catalog content is sourced from the public marketing site.
No authentication. Intentional — this is a knowledge endpoint.
Rate-limited. 120 req/min per IP, 60 req/min per session.
Audit gate.
npm run audit:public-datablocks deploys if any PII / auth token strings appear insrc/data/.
Development
npm install
npm run dev # HTTP server on :8080 with watch mode
npm run dev:stdio # stdio transport for local MCP client testing
npm test # node:test runner
npm run build
npm run audit:public-dataProject layout
src/
data/ # Static catalogs — plans, integrations, countries, articles, about
tools/ # One file per MCP tool
resources/ # MCP resource registry
server.ts # MCP server factory (wires tools + resources)
http.ts # Streamable HTTP transport with rate limiting
stdio.ts # stdio transport entry point
test/
tools.test.ts
resources.test.ts
public-data.test.ts # Audit gate
scripts/
audit-public-data.ts # CI-callable auditDeployment
Containerised — see Dockerfile. Designed to run behind a TLS-terminating load balancer.
Set PORT and HOST via environment.
Optional anonymous usage telemetry (Layer-2 server-side analytics) is sent to GA4 via
the Measurement Protocol when GA4_MEASUREMENT_ID and GA4_API_SECRET are both set —
see .env.example and src/analytics.ts. Leave them unset and the server runs with
telemetry fully disabled. No customer data, request bodies, tool-argument values, or
IP addresses are ever sent — only anonymous counts. See strategy doc 73.
docker build -t hellobooks-mcp-public .
docker run -p 8080:8080 hellobooks-mcp-publicDiscoverability
Listed in the MCP registry.
Linked from the marketing site footer and
/mcppage.Referenced in
https://hellobooks.ai/llms.txt.
License
MIT — see LICENSE.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Meru-Fin-Tech/HelloBooks-MCP-Public'
If you have feedback or need assistance with the MCP directory API, please join our Discord server