Skip to main content
Glama
README.md
# Accelo API and MCP server

**Yes, ChatGPT, Claude and other AI agents can work in your Accelo account.** Connect your account to manage tickets, projects, time and quotes with your agent.

## What you can ask

> Show me open Accelo tickets from this week and group them by priority.

> Log 45 minutes on ticket 1042 for the export fix.

> Draft a reply to the oldest unanswered client ticket.

> Create a draft quote for Website Redesign phase 2.

> List overdue invoices and the outstanding amount for each client.

## Connect in 2 minutes

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

### Claude Code

```bash
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:

```json
{
  "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 Accelo 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.

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

Or with Docker:

```bash
docker build -t accelo-mcp .
docker run -i --rm -e COTLET_API_KEY accelo-mcp
```

Tools: `accelo_guide`, `accelo_status`, `accelo_open`, `accelo_read`, `accelo_click`, `accelo_type`, `accelo_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:

```bash
pip install accelo-mcp        # or run it once: uvx accelo-mcp connect
accelo-mcp connect
```

Or straight from this repo:

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

## Questions from Accelo users

**Does Accelo have an API?**

Yes. Connect Accelo through Cotlet.dev at https://cotlet.dev/mcp/v1.

**How do I connect Accelo to ChatGPT?**

Add the Cotlet.dev MCP connector at https://cotlet.dev/mcp/v1/connect.

**Can I use Accelo with Claude?**

Yes. Claude connects through Cotlet.dev.

**Is there an Accelo MCP server?**

Cotlet.dev provides a hosted Accelo MCP server.

## Find it on

- [Accelo on Cotlet.dev](https://cotlet.dev/integrations/accelo-api-mcp-server?utm_source=github&utm_medium=readme&utm_campaign=accelo&utm_content=find)
- [PyPI package accelo-mcp](https://pypi.org/project/accelo-mcp/)
- [Odel](https://odel.app/modules/cotlet/accelo)
- [mcpbeat](https://mcpbeat.com/mcp-servers/cotlet/accelo/)
- [Step-by-step guide (PDF) on Internet Archive](https://archive.org/details/cotlet-connect-accelo-to-ai-agents-guide)

## Also works with


- [All apps connected through Cotlet.dev](https://github.com/cotlet-connect)

---

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

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

TDQS

A3.7/5.0

Scored across 7 tools

Disambiguation5/5

Each tool maps to a single, clearly distinct browser-automation primitive (guide, status, open, read, click, type, close) with no overlapping responsibilities. The read/click/type triad is a standard, well-understood workflow where boundaries are unambiguous.

Naming Consistency5/5

All seven tools use the same accelo_ prefix with a short, consistent verb (guide, status, open, read, click, type, close). No mixing of camelCase, casing, or verb styles.

Tool Count5/5

Seven tools is a tight, well-scoped set for driving a web app through a cloud browser; each tool earns its place and nothing looks redundant. It sits comfortably in the 3-15 ideal range.

Completeness3/5

The core loop (open, read, click, type, close) plus onboarding and status is present, but common browser actions like scrolling, waiting for page load, pressing Enter/keys, or selecting dropdowns are absent. These gaps will likely force agents into failed attempts on forms and long pages.

Maintenance

ActivityMaintained
ResponsivenessOutdated data