# Digible Data — an MCP server

Six composable tools over a multifamily marketing dataset. Ask about money out,
people through the leasing funnel, and phone calls — grouped however you need.

**Live:** `https://mcp-digible-queries.fastmcp.app/mcp` — public, no sign-in, no key.

## The tools

| Tool | What it answers |
|---|---|
| `list_properties` | The apartment communities under management, optionally by market |
| `list_channels` | The marketing channels, and how each one is billed |
| `date_range` | What a period means, and which months the data covers |
| `marketing_spend` | What we spent, and how it compares to budget |
| `leasing_funnel` | How many people moved through the funnel, and what they cost |
| `phone_calls` | How many calls came in, and how many nobody answered |

Three shapes — money, people, phone — plus three lookups. The variety lives in
`group_by`, not in more tools. `leasing_funnel(include_cost=True)` joins spend on
the same grouping key, so cost per lead and cost per lease need no extra tool.

`period` takes what a person would say: `"May"`, `"Q2"`, `"last month"`,
`"first half"`, or `"2026-02-01..2026-04-15"`. If it cannot read one, it says so
and lists what it does understand.

Every tool takes an optional `caller` for attribution. It defaults, so nobody
using Claude Desktop has to invent a name.

## Connecting it

**Claude Desktop** — add it as a connector with the URL above, then ask in plain
language. Nothing to install.

**Claude Code**

```bash
claude mcp add --transport http digible-data https://mcp-digible-queries.fastmcp.app/mcp
```

**Locally**

```bash
pip install -r requirements.txt
python server.py            # http://127.0.0.1:8030/mcp
python server.py --stdio    # or stdio, if your client prefers it
```

## Where this came from

Built for the Overclock Accelerator MCP training as the worked answer to an
exercise: six agents, each with its own way of querying the same database,
consolidated into one server. Agent code dropped from 942 lines to 141.

The exercise and the write-up live in
[digible-mcp-training-starter](https://github.com/Overclock-Accelerator/digible-mcp-training-starter).

## Data

`digible.db` is synthetic, committed, and opened read-only. Properties,
campaigns, channels, spend, leads, calls, tours, applications and leases,
covering 2026-01 to 2026-06.

MIT licensed.