Skip to main content

How to connect Tradify to Claude Code, ChatGPT and any AI agent

Yes, Claude, ChatGPT and other AI agents can work in your Tradify account. Tradify has no public API, no API keys and no official ChatGPT or Claude app. Cotlet.dev connects your own signed-in Tradify account to any AI agent, so you can ask in plain words and the AI creates the job, writes the quote, turns it into an invoice, records the payment and books your staff. It shows you the draft first and sends nothing to a customer until you say so.

What you can ask

New job for Sam Lee at 12 Oak St: replace the hot water cylinder. Book Mike for Thursday morning.

Quote the bathroom rewire at 14 Elm Rd from my notes: 6 hours labour, 6 LED downlights at $24, one extractor fan at $85. Show me before you send it.

Turn every quote accepted this week into a 30% deposit invoice.

Which invoices are overdue? Total them per customer, oldest first.

What is on tomorrow's schedule, per staff member?

Connect in 2 minutes

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

Claude Code

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

ChatGPT

Settings → Apps → add connector URL https://cotlet.dev/mcp/v1, then sign in with Cotlet.dev. No API key needed.

Cursor

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

{
  "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 Tradify 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.

{"mcpServers":{"tradify":{"command":"uvx","args":["tradify-mcp"],"env":{"COTLET_API_KEY":"your-key"}}}}

Or with Docker:

docker build -t tradify-mcp .
docker run -i --rm -e COTLET_API_KEY tradify-mcp

Tools: tradify_guide, tradify_status, tradify_open, tradify_read, tradify_click, tradify_type, tradify_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+, nothing else to install. From PyPI:

pip install tradify-mcp        # or run it once: uvx tradify-mcp connect
tradify-mcp connect

Or straight from this repo:

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

Questions from Tradify users

Does Tradify have an API?

Not a public one. Tradify offers no public API, no self-service API keys and no webhooks, only built-in integrations such as Xero, QuickBooks, MYOB and Stripe. Cotlet.dev works in your Tradify account directly, so your AI agent can handle jobs, quotes, invoices and the Scheduler without one.

How do I connect Tradify to ChatGPT?

Add Cotlet.dev as an app in ChatGPT (Settings → Apps, connector URL https://cotlet.dev/mcp/v1/tradify), sign in to Tradify once in your Cotlet.dev Cloud Browser, and ask ChatGPT in plain words. No code and no Tradify API key.

Is there a way to use Claude with Tradify?

Yes. In Claude Code run the one-line claude mcp add command above; in the Claude app add https://cotlet.dev/mcp/v1/tradify as a custom connector. Claude then works in your own Tradify account.

Can AI do my Tradify quotes and invoices?

Yes. Give it your notes and it writes a draft quote with labour and materials lines, turns an accepted quote into a full or deposit invoice, records payments and lists what is overdue. Nothing reaches a customer before your OK, and invoices still sync to Xero or QuickBooks as you set it up.

Is there a Tradify MCP server?

Tradify has no official MCP server. Cotlet.dev is a hosted MCP server that works in Tradify for you, 24/7, with Claude, ChatGPT, Cursor, Codex, n8n, Make and Zapier. A self-hosted version for developers is on GitHub.

Find it on

Also works with


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

Start free: https://cotlet.dev/signup?app=tradify&utm_source=github&utm_medium=readme&utm_campaign=tradify

Metadata

Release files for tradify-mcp 1.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for tradify-mcp 1.1.0
File Size Uploaded Provenance Actions
tradify_mcp-1.1.0.tar.gz 9.8 kB Without provenance Details for tradify_mcp-1.1.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for tradify-mcp 1.1.0
File Interpreter ABI Platform Actions
tradify_mcp-1.1.0-py3-none-any.whl Python 3 none any Details for tradify_mcp-1.1.0-py3-none-any.whl

Total release size: 19.7 kB

Release files / tradify_mcp-1.1.0.tar.gz

Download URL tradify_mcp-1.1.0.tar.gz
Size 9.8 kB
Tags Source
SHA-256 checksum
How to use checksums
10bd6dea5a9125b09bcccf33442e44f5ccfd9263876566864c2bdd9c353c5c16
BLAKE2b-256 checksum
How to use checksums
18a7eaf03991423eb6917830ef694da4b8a2c1fce2194def77fccd2f65cf2f28
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.9

Release files / tradify_mcp-1.1.0-py3-none-any.whl

Download URL tradify_mcp-1.1.0-py3-none-any.whl
Size 9.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
d7bb47ea196fe54de99adf6887efd0411a2b4601b073dc82f02e796130239f07
BLAKE2b-256 checksum
How to use checksums
1073935207b92f9febfe98d0111fc6c4f76e63860b98ed3816f5b7e3132e0f2b
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.9

Security for tradify-mcp 1.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

1.1.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page