Skip to main content
Glama
Sign In
Bloom MCP

Bloom MCP

by cotlet-connect
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

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

Yes, Claude, ChatGPT and other AI agents can work in your Bloom account. Cotlet.dev connects your own signed-in Bloom account to any AI agent, so you can ask in plain words and the AI books clients, prepares invoices and contracts, and follows up on payments for you.

What you can ask

Book Maria Lopez for a 2-hour engagement shoot on Saturday at 10 am and email her the confirmation.

Create a $1,800 invoice for the Carter wedding with a 30% deposit due this Friday.

Send the wedding contract to Jake and Emma Brooks and tell me on Monday if it's still unsigned.

Which invoices are more than 14 days overdue? Draft a friendly reminder for each client and show me first.

What sessions do I have next week? List each client, the time and whether their contract is signed.

Related MCP server: invoice2go-mcp

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 Bloom 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":{"bloom":{"command":"uvx","args":["bloom-cotlet-mcp"],"env":{"COTLET_API_KEY":"your-key"}}}}

Or with Docker:

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

Tools: bloom_guide, bloom_status, bloom_open, bloom_read, bloom_click, bloom_type, bloom_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 bloom-cotlet-mcp        # or run it once: uvx bloom-cotlet-mcp connect
bloom-cotlet-mcp connect

Or straight from this repo:

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

Questions from Bloom users

Does Bloom have an API?

You don't need one. Cotlet.dev works in your own signed-in Bloom account, so your AI agent can book clients, prepare invoices and send contracts without a Bloom API key or developer setup.

How do I connect Bloom to ChatGPT?

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

Is there a way to use Claude with Bloom?

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

Is there a Bloom MCP server?

Cotlet.dev is a hosted MCP server that works in Bloom for you, 24/7, with Claude, ChatGPT, Cursor, Codex, n8n, Make and Zapier.

Is there an official Bloom app for ChatGPT or Claude?

We could not find a verified official Bloom listing in ChatGPT's apps directory or Claude's connector directory. The Bloom Profit Analytics app in ChatGPT is a separate Shopify analytics product. Cotlet.dev connects your Bloom account to both ChatGPT and Claude.

Find it on

Also works with

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

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

Available Tools

7 tools
bloom_clickC

Click a numbered element on the current Bloom page.

Inputs: element (required).

bloom_closeA

Close the Bloom browser session when the work is done, so credits stop running.

Inputs: no named parameters.

bloom_guideA

How to work in Bloom (manage client bookings, invoices and contracts): its screens and the sign-in link. Call this first.

Inputs: task.

bloom_openB

Open a Bloom page in your signed-in Cloud Browser (default https://app.bloom.io) to work with manage client bookings, invoices and contracts.

Inputs: url.

bloom_readA

Read the current Bloom page: its text and numbered buttons, links and fields.

Inputs: element.

bloom_statusB

Check that your Cotlet.dev account and Bloom are ready: account, credits and Bloom connection.

Inputs: no named parameters.

bloom_typeB

Type text into a numbered field on the current Bloom page.

Inputs: text (required), element (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.6/5.0

    Scored across 7 tools

    Disambiguation5/5

    Each tool has a clearly distinct role: guide, status check, browser open/close, and page read/click/type. No two tools overlap in purpose, so an agent can easily select the right one.

    Naming Consistency4/5

    All tools share the bloom_ prefix and snake_case, but most are verbs (open, read, click, type, close) while guide and status are noun-based. The pattern is still predictable and readable.

    Tool Count5/5

    Seven tools are well-scoped for a browser-automation server: one setup guide, one readiness check, and five core session/page operations. Each tool earns its place.

    Completeness4/5

    The surface covers session lifecycle and basic page interaction (open, read, click, type, close), which is sufficient for core UI workflows. Minor gaps like scroll, select, or keyboard shortcuts exist but agents can work around them.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers