Frappe MCP
Read-only MCP server for TourScale ERPNext, enabling agents to query franchisees, agreements, invoices, and GL entries via natural language.
README
Frappe MCP
Read-only Model Context Protocol server for the TourScale ERPNext / FranOS instance at erp.tourscale.com. Lets agents query Franchisees, Franchise Agreements, FBUs, Assets, COIs, and ERPNext invoices/GL entries.
What it exposes
| Tool | Purpose |
|---|---|
whoami |
Connectivity probe — returns the API user identity |
list_franchisees(status, brand, limit) |
Franchisees with optional filters |
get_franchisee(name) |
Full Franchisee doc by name (e.g. FZE-00001) |
list_fas(franchisee, status, expiring_within_days, limit) |
Franchise Agreements; expiring window key for Compliance Watchdog |
get_fa(name) |
One FA with child tables (brands/royalty/territory) |
list_fbus(franchisee, brand, limit) |
FBUs |
get_fbu(name) |
One FBU with operating addresses |
list_assets(franchisee, asset_type, limit) |
Vehicles/vessels |
list_cois(franchisee, expiring_within_days, limit) |
Certificate of Insurance, with renewal-window filter |
frappe_list_docs(doctype, filters_json, fields_json, limit, order_by) |
Generic escape hatch for any doctype |
frappe_get_doc(doctype, name) |
Generic get-by-name |
frappe_count(doctype, filters_json) |
Count records |
erpnext_list_invoices(franchisee, status, date_from, date_to, limit) |
Sales Invoices |
erpnext_gl_entries(account, party, date_from, date_to, limit) |
GL ledger entries |
How auth works
Talks to ERPNext REST API as the claude-mcp@tourscale.com user via API key + secret (Frappe-native auth scheme: Authorization: token <key>:<secret>).
The user has the System Manager role on ERPNext. The MCP layer is the trust boundary — the tools above are read-only by design. Don't add write tools casually; agents that need to mutate should call narrow, purpose-specific tools, not generic CRUD.
To rotate keys: re-run the generate_keys flow in bench --site erp.tourscale.local console, update FRAPPE_API_KEY + FRAPPE_API_SECRET in master env, restart ts-frappe-mcp.
Deployment
- Container:
ts-frappe-mcpontourscale-net - Port: bound to
127.0.0.1:8096(loopback only — reach via local agent client or SSH tunnel) - Compose entry lives in
/opt/tourscale/docker-compose.services.yml - Env file:
/opt/tourscale/frappe-mcp/.env(sourced from master env)
Local dev
FRAPPE_API_URL=https://erp.tourscale.com \
FRAPPE_API_KEY=... \
FRAPPE_API_SECRET=... \
python3 server.py
Then call tools via any MCP client (Claude Code, FastMCP debug tools, etc.).
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.