mcpField
F
FieldEdge MCP Server and API by Cotlet

FieldEdge MCP Server and API by Cotlet

Remote
cotlet.devBusiness & Marketing0Updated 2d ago

About FieldEdge MCP Server and API by Cotlet

FieldEdge MCP Server and API by Cotlet connects AI clients to a signed-in FieldEdge account for field service contractors. It supports job booking, technician dispatch, and invoicing through a hosted MCP service, with a local stdio server and CLI option.

Key features

  1. 01Create and manage work orders
  2. 02Dispatch technicians to jobs
  3. 03Create and send invoices
  4. 04Read FieldEdge pages through tools
  5. 05Connect through hosted MCP or stdio
  6. 06Configure clients with the CLI

Use cases

  1. 01Book a service visit and assign a technician
  2. 02Review dispatch schedules by technician
  3. 03Invoice completed jobs and identify overdue bills

MCP support

The hosted Cotlet.dev service exposes FieldEdge operations to MCP clients. A local stdio server lists tools and forwards calls to the hosted service.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://cotlet.dev/mcp/v1/fieldedge/connect
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://cotlet.dev/mcp/v1/fieldedge/connect
Streamable HTTPhttps://cotlet.dev/mcp/v1/fieldedgeAuth required

Tools

Details

From the project README

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

Yes, Claude, ChatGPT and other AI agents can work in your FieldEdge account. There is no official FieldEdge app in the ChatGPT or Claude directories. Cotlet.dev connects your own signed-in FieldEdge account to any AI agent, so you can ask in plain words and the AI books jobs, dispatches techs and sends invoices for you.

What you can ask

Book a furnace tune-up for Mark Rivera at 42 Oak Street on Thursday at 9 am and assign it to Luis.

What does tomorrow's dispatch board look like per technician? Flag anyone with more than 6 jobs.

Move all of Dave's Friday jobs to Carlos and text the customers the new arrival window.

Create invoices for every job completed yesterday and email them to the customers.

Which invoices over $500 are still unpaid after 30 days? List them with the customer phone number.

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

Or with Docker:

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

Tools: fieldedge_guide, fieldedge_status, fieldedge_open, fieldedge_read, fieldedge_click, fieldedge_type, fieldedge_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 fieldedge-mcp        # or run it once: uvx fieldedge-mcp connect
fieldedge-mcp connect

Or straight from this repo:

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

Questions from FieldEdge users

Does FieldEdge have an API for developers?

FieldEdge has an API, but only on request: you ask for access through FieldEdge's onboarding form and wait for credentials. Cotlet.dev works in your own signed-in FieldEdge account instead, so your AI agent can book work orders, dispatch technicians and send invoices without that request.

How do I connect FieldEdge to ChatGPT?

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

Is there a way to use Claude with FieldEdge?

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 FieldEdge account.

Is there a FieldEdge MCP server?

FieldEdge has no official MCP server and no official app in ChatGPT or Claude (checked November 2026). Cotlet.dev is a hosted FieldEdge MCP server that works in your own account, with Claude, ChatGPT, Cursor, Codex, n8n, Make and Zapier.

Find it on

Also works with


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

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

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.