cotlet-connect

Bolster MCP server

Community cotlet-connect
Updated

Connect Bolster to ChatGPT, Claude and AI agents through Cotlet.dev.

Bolster MCP server

Connect Bolster to ChatGPT, Claude, Codex and Claude Code through Cotlet.dev. Work with estimates, proposals, schedules, job budgets, bid requests and customer payment requests in your own signed-in contractor account. Review write operations before approving them.

What you can ask

Show which clients opened their estimate proposals.

Draft an estimate for a composite deck and show me the lines before saving.

List payment requests for the Maple Street job.

Connect in 2 minutes

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

ChatGPT

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

Claude Code

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:

{
  "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 Bolster 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:

python3 bolster_agent.py serve

Or with Docker:

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

Tools: bolster_guide, bolster_status, bolster_open, bolster_read, bolster_click, bolster_type, bolster_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:

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

Questions from Bolster users

How do I connect my account?

Request access at https://cotlet.dev/signup?app=bolster, sign in to Bolster in your Cotlet.dev Cloud Browser and enable it for agents.

Can I review changes?

Write calls ask for confirmation by default; you can change that per tool. Sending proposals and bid requests reaches your clients or vendors. Approving a finished schedule task can start a payment request.

Which plan do I need?

The live connection guide documents takeoff and scheduling from Pro, and RFQ management from Premium. Your Bolster plan and user permissions determine what the agent can access.

Is Cotlet.dev affiliated with Bolster?

No. Cotlet.dev is independent and not affiliated with Bolster. No tool pays vendor bills or moves money out of Bolster Wallet.

Learn more

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

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

Workflows on the hosted integration

Examples documented on the live integration page:

  • manage_crm_pipeline
  • generate_ai_estimates
  • measure_takeoffs
  • create_estimates
  • manage_selections
  • create_presentations
  • schedule_jobs
  • manage_job_budget
  • send_rfq_requests
  • collect_customer_payments

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.

MCP Server · Populars

MCP Server · New

    frontman-ai

    frontman

    The AI agent that lives in your framework/browser

    Community frontman-ai
    Laksh-star

    Screenward

    Movie and TV discovery, watch planning, and streaming availability—for browsers and MCP clients.

    Community Laksh-star
    codescene-oss

    CodeHealth MCP Server

    The CodeScene MCP Server exposes CodeScene’s Code Health analysis as local AI-friendly tools.

    Community codescene-oss
    Fan-Pier-Labs

    OpenRecord

    Let Claude read and manage your Epic MyChart health records — labs, meds, messages, refills, imaging. Claude Desktop extension (MCP server), iOS app, and CLI. Runs on your device.

    Community Fan-Pier-Labs
    video-db

    skills

    Server-side video workflows for agents: ingest, understand, search, edit, stream.

    Community video-db