mcpField
E
Experimental MCP Server for CommCare Connect (ccc)

Experimental MCP Server for CommCare Connect (ccc)

Local
github.com/dimagiData & Analytics0Updated 78w ago
Repository

About Experimental MCP Server for CommCare Connect (ccc)

An experimental MCP server that lets CommCare Connect users query dashboard statistics such as earnings, payments, active users, and visits, with optional date, program, or organization filters.

Key features

  1. 01Query global dashboard statistics
  2. 02Filter by date range
  3. 03Filter by program or organization
  4. 04Use an authentication token

Use cases

  1. 01Ask about amounts earned and paid
  2. 02Review active-user and visit statistics
  3. 03Check statistics for selected dates or programs

MCP support

Exposes CommCare Connect global statistics through an MCP server for clients such as Claude Code. It is built with the Python MCP SDK.

#commcare#mcp#server

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Experimental MCP Server for CommCare Connect (ccc)

This is an experimental MCP server for CommCare Connect. You can find a quick video walthrough here.

To use it with claude code you can run claude in this folder. You can see the .mcp.json for how it is set up. If you want to use a different tool you can modify the declaration accordingly. You will need to have uv installed on your system, and you may have to specify absolute paths to the uv executable and server.py file.

This project is built on top of the Python MCP SDK.

Usage

At the moment all this can do is query the global stats API which is used by the program dashboard. So basically you can ask it questions about amounts earned and paid, active users, and visit stats, optionally over specific date ranges (or programs/organizations if you know their IDs).

Getting an authentication token

The easiest way to get an authentication token is as a superuser to visit https://connect.dimagi.com/admin/authtoken/tokenproxy/ and find a token associated with your email.

If you don't have any tokens, you can run the following, replacing your username and password:

curl -X POST -d "[email protected]&<password=***" https://connect.dimagi.com/auth-token/

This will create a token and print its value on the command line.

You can test that the token is valid with the following:

curl -H "Authorization: Token YOUR_TOKEN" "https://connect.dimagi.com/admin_reports/api/dashboard_stats/?from_date=2024-01-01&to_date=2024-12-31"

Development

You can change the SERVER_ENDPOINT in .mcp.json to http://localhost:8000 to test this against a development server. This will require running a development server and getting an API token through the same process as above against it.

You can also run it against https://connect-staging.dimagi.com/ with a similar process.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.