Skip to main content
Glama

Monograph API and MCP server for Claude and ChatGPT

Yes, ChatGPT, Claude and other AI agents can work with your Monograph account. Monograph has no open API or official MCP server. Cotlet.dev connects your own signed-in Monograph account to AI agents for project, staffing, budget, time and billing work, with confirmation before sensitive actions.

What you can ask

Review project budgets against contracts and flag variances.

Show unbilled time by project and draft invoices for my approval.

Find staffing gaps and propose assignments for next week.

List overdue consultant bills and prepare follow-up notes.

Summarize utilization and project profitability for this month.

Related MCP server: cuybrowser

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

Or with Docker:

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

Tools: monograph_guide, monograph_status, monograph_open, monograph_read, monograph_click, monograph_type, monograph_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 monograph-mcp        # or run it once: uvx monograph-mcp connect
monograph-mcp connect

Or straight from this repo:

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

Questions from Monograph users

Does Monograph have an API?

Monograph does not offer an open API. QuickBooks Online and Stripe are built-in integrations, according to its account FAQ.

How do I connect Monograph to ChatGPT?

Sign up at https://cotlet.dev/signup?app=monograph, enable Monograph and sign in at app.monograph.com/login in your Cotlet.dev Cloud Browser. Add https://cotlet.dev/mcp/v1/connect to ChatGPT with OAuth.

Can I use Monograph with Claude?

Yes. Add https://cotlet.dev/mcp/v1/connect as a custom connector in Claude and sign in to Cotlet.dev.

Is this an official Monograph MCP server?

No. Cotlet.dev is independent and is not affiliated with Monograph. The hosted integration works in your own signed-in Monograph account.

Find it on

Also works with


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

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

Available Tools

7 tools
monograph_clickB

Click a numbered element on the current Monograph page.

Inputs: element (required).

monograph_closeA

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

Inputs: no named parameters.

monograph_guideA

How to work in Monograph (architecture and engineering firm management with projects, staffing, budgets, time and billing): its screens and the sign-in link. Call this first.

Inputs: task.

monograph_openB

Open a Monograph page in your signed-in Cloud Browser (default https://app.monograph.com) to work with architecture and engineering firm management with projects, staffing, budgets, time and billing.

Inputs: url.

monograph_readA

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

Inputs: element.

monograph_statusA

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

Inputs: no named parameters.

monograph_typeC

Type text into a numbered field on the current Monograph 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…

    TDQS

    A3.7/5.0

    Scored across 7 tools

    Disambiguation5/5

    Each tool has a clearly distinct role: guide, readiness check, opening a session, reading the page, clicking, typing, and closing. The boundaries between setup, interaction, and teardown are obvious, with almost no risk of tool misselection.

    Naming Consistency5/5

    All tools share the same monograph_ prefix and use short lower_snake_case names. The pattern is predictable throughout, with only guide/status being nouns and the rest actions, which is still highly consistent.

    Tool Count5/5

    Seven tools are well-scoped for a browser automation wrapper: just enough to cover setup, page interaction, and cleanup. No tool feels redundant or out of place.

    Completeness4/5

    The set covers the core browser lifecycle: guide, status, open, read, click, type, and close. Minor gaps exist for general browser operations like scrolling, selecting dropdown options, or explicit navigation, but agents can likely work around them.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Lets any MCP-speaking AI agent drive your everyday Chrome browser, opening pages, reading them, clicking, typing, taking screenshots, and inspecting DevTools console, network, storage and performance data with your existing sign-ins. Risky actions like submitting or paying require your explicit approval, and agents are confined to their own tab group with secrets hidden.
      Apache 2.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to drive Chrome through MCP tools for navigating pages, taking token-efficient snapshots and diffs, finding and acting on elements, and capturing screenshots. Sensitive actions such as submitting forms, downloading or uploading files, and running JavaScript require human approval through a system dialog.
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to operate a user's signed-in Joist account, creating estimates, sending invoices, managing clients, and reviewing overdue payments through natural language without a Joist API key. It supports hosted MCP access plus a local stdio server for clients that require it.
      7
      Elastic 2.0