Skip to main content
Glama
README.md
# Trusso MCP server

Connect Trusso to ChatGPT, Claude and any AI agent through Cotlet.dev. Reply to leads, draft estimates, schedule crews and manage invoices in your own signed-in Trusso account. Write actions ask for approval by default.

## What you can ask

> Read today's jobs and the assigned crew.

> Draft an estimate for the new Angi lead and show me before sending.

> List overdue invoices and their outstanding balances.

## Connect in 2 minutes

Get your API key at https://cotlet.dev/app and export it as `COTLET_API_KEY`.

### ChatGPT

Settings → Apps & Connectors → Create, with connector URL `https://cotlet.dev/mcp/v1/connect`, then sign in with Cotlet.dev. No API key needed.

### Claude

Settings → Connectors → Add custom connector, with URL `https://cotlet.dev/mcp/v1/connect`, then sign in with Cotlet.dev.

### Claude Code

```bash
claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"
```

### Cursor

Copy `.cursor/mcp.json` from this repo into your project:

```json
{
  "mcpServers": {
    "cotlet": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": {
        "Authorization": "Bearer ${COTLET_API_KEY}"
      }
    }
  }
}
```

## Run it locally (stdio)

This repo is a real MCP server. It speaks MCP over stdio, lists its Trusso tools without any key, and forwards every tool call to the hosted Cotlet.dev server. The hosted URL above stays the recommended way. Use this when your client only starts local servers.

Run the included Python module with Python 3.10 or later:

```bash
python3 trusso_agent.py serve
```

Or with Docker:

```bash
docker build -t trusso-mcp .
docker run -i --rm -e COTLET_API_KEY trusso-mcp
```

Tools: `trusso_guide`, `trusso_status`, `trusso_open`, `trusso_read`, `trusso_click`, `trusso_type`, `trusso_close`. Without `COTLET_API_KEY` a tool call answers: "Set COTLET_API_KEY. Get a key at https://cotlet.dev/app".

## Command line

Python 3.10+, with no third-party runtime dependencies. Clone this repository and run:

```bash
export COTLET_API_KEY="your-key"
python3 trusso_agent.py connect   # ready config for Claude Code, Cursor, ChatGPT
python3 trusso_agent.py status    # is Trusso ready in your Cotlet.dev account
python3 trusso_agent.py guide     # Trusso screens and sign-in link
python3 trusso_agent.py read      # open Trusso, read the page, close the browser
python3 trusso_agent.py tools     # list Cotlet.dev tools
python3 trusso_agent.py serve     # start the stdio MCP server (same as no argument)
```

## Questions from Trusso users

**Which Trusso login should I connect?**

Use an owner or manager login on the web dashboard. Crew logins do not expose the customer list, pricing or financials.

**Does the agent text my customers?**

Trusso sends SMS only to customers with confirmed consent and stops texting anyone who replied STOP. Customer-facing writes ask for approval by default.

**Is Cotlet affiliated with Trusso?**

No. Cotlet.dev is independent and not affiliated with Trusso.

## Learn more

- [Trusso integration and hosted tools](https://cotlet.dev/integrations/trusso-api-mcp-server)

---

More: https://cotlet.dev/integrations/trusso-api-mcp-server?utm_source=github&utm_medium=readme&utm_campaign=trusso

Request access: https://cotlet.dev/signup?app=trusso&utm_source=github&utm_medium=readme&utm_campaign=trusso

## Workflows on the hosted integration

The live integration page documents these 11 operations:

- `manage_leads`
- `manage_customers`
- `import_customers_from_another_crm`
- `manage_estimates`
- `list_jobs`
- `schedule_jobs`
- `manage_recurring_jobs`
- `send_invoices_and_collect_payments`
- `add_crew_members`
- `read_clock_history`
- `bid_out_jobs_to_subs`

The local stdio adapter exposes seven browser helpers listed above. These helpers forward to Cotlet.dev; the workflow operations are documented on the hosted integration page.