Costlens — Ai Productivity Tracking

by Costlens-dev

274 downloads

Not rated

GitHub

About

Track AI productivity automatically via MCP. Measures sessions, commits, PRs, cost per deliverable, and generates ROI reports for engineering leaders. Zero latency — all tracking is async.

Details

Author: Costlens-dev
Downloads: 274
Categories: Other, Productivity, AI, Developer Tools

- Automatic session tracking (start, end, heartbeat)
- Event logging for commits, PRs, deploys, file edits
- Cost tracking per session and per deliverable
- GitHub PR metrics (review rounds, time to merge)
- Productivity reports with ROI calculation
- Zero latency – all tracking is async, never blocks

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name Costlens — Ai Productivity Tracking

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "costlens \u2014 ai productivity tracking": {
            "costlens": {
                "command": "npx",
                "args": [
                    "-y",
                    "@costlens/mcp-server"
                ],
                "env": {
                    "COSTLENS_MCP_KEY": "<YOUR_KEY>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "costlens \u2014 ai productivity tracking": {
            "costlens": {
                "command": "npx",
                "args": [
                    "-y",
                    "@costlens/mcp-server"
                ],
                "env": {
                    "COSTLENS_MCP_KEY": "<YOUR_KEY>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "costlens \u2014 ai productivity tracking": {
            "costlens": {
                "command": "npx",
                "args": [
                    "-y",
                    "@costlens/mcp-server"
                ],
                "env": {
                    "COSTLENS_MCP_KEY": "<YOUR_KEY>"
                }
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "costlens \u2014 ai productivity tracking": {
            "costlens": {
                "command": "npx",
                "args": [
                    "-y",
                    "@costlens/mcp-server"
                ],
                "env": {
                    "COSTLENS_MCP_KEY": "<YOUR_KEY>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "costlens \u2014 ai productivity tracking": {
            "costlens": {
                "command": "npx",
                "args": [
                    "-y",
                    "@costlens/mcp-server"
                ],
                "env": {
                    "COSTLENS_MCP_KEY": "<YOUR_KEY>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "costlens \u2014 ai productivity tracking": {
            "costlens": {
                "command": "npx",
                "args": [
                    "-y",
                    "@costlens/mcp-server"
                ],
                "env": {
                    "COSTLENS_MCP_KEY": "<YOUR_KEY>"
                }
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "costlens \u2014 ai productivity tracking": {
            "costlens": {
                "command": "npx",
                "args": [
                    "-y",
                    "@costlens/mcp-server"
                ],
                "env": {
                    "COSTLENS_MCP_KEY": "<YOUR_KEY>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "costlens \u2014 ai productivity tracking": {
            "costlens": {
                "command": "npx",
                "args": [
                    "-y",
                    "@costlens/mcp-server"
                ],
                "env": {
                    "COSTLENS_MCP_KEY": "<YOUR_KEY>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "costlens \u2014 ai productivity tracking": {
            "costlens": {
                "command": "npx",
                "args": [
                    "-y",
                    "@costlens/mcp-server"
                ],
                "env": {
                    "COSTLENS_MCP_KEY": "<YOUR_KEY>"
                }
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "costlens \u2014 ai productivity tracking": {
            "costlens": {
                "command": "npx",
                "args": [
                    "-y",
                    "@costlens/mcp-server"
                ],
                "env": {
                    "COSTLENS_MCP_KEY": "<YOUR_KEY>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "costlens \u2014 ai productivity tracking": {
            "costlens": {
                "command": "npx",
                "args": [
                    "-y",
                    "@costlens/mcp-server"
                ],
                "env": {
                    "COSTLENS_MCP_KEY": "<YOUR_KEY>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "costlens \u2014 ai productivity tracking": {
            "costlens": {
                "command": "npx",
                "args": [
                    "-y",
                    "@costlens/mcp-server"
                ],
                "env": {
                    "COSTLENS_MCP_KEY": "<YOUR_KEY>"
                }
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "costlens \u2014 ai productivity tracking": {
            "costlens": {
                "command": "npx",
                "args": [
                    "-y",
                    "@costlens/mcp-server"
                ],
                "env": {
                    "COSTLENS_MCP_KEY": "<YOUR_KEY>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "costlens \u2014 ai productivity tracking": {
            "costlens": {
                "command": "npx",
                "args": [
                    "-y",
                    "@costlens/mcp-server"
                ],
                "env": {
                    "COSTLENS_MCP_KEY": "<YOUR_KEY>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "costlens \u2014 ai productivity tracking": {
            "costlens": {
                "command": "npx",
                "args": [
                    "-y",
                    "@costlens/mcp-server"
                ],
                "env": {
                    "COSTLENS_MCP_KEY": "<YOUR_KEY>"
                }
            }
        }
    }
}

From the repository

Run npx @costlens/mcp-server setup – one command opens a browser for authentication and auto‑configures your agent. After setup, the server exposes seven tools: start_session, end_session, log_event, get_productivity_summary, get_spend_summary, get_github_metrics, and costlens_suggest_model. All tracking is async and never blocks your workflow.

`get_spend_summary`

Get current spend summary — daily, weekly, monthly, and session totals

`costlens_suggest_model`

Analyze a prompt and suggest the cheapest adequate model

`start_session`

Start a productivity tracking session

`end_session`

End a productivity tracking session

`log_event`

Log a productivity event within a session

`get_productivity_summary`

Get productivity summary for a time period

`get_github_metrics`

Get GitHub PR metrics — PRs merged, review rounds, first-pass rate, cost per PR

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "costlens \u2014 ai productivity tracking": {
            "costlens": {
                "command": "npx",
                "args": [
                    "-y",
                    "@costlens/mcp-server"
                ],
                "env": {
                    "COSTLENS_MCP_KEY": "<YOUR_KEY>"
                }
            }
        }
    }
}

McpServers

{
    "costlens": {
        "command": "npx",
        "args": [
            "-y",
            "@costlens/mcp-server"
        ],
        "env": {
            "COSTLENS_MCP_KEY": "<YOUR_KEY>"
        }
    }
}

CostLens MCP Server

AI productivity tracking for coding agents. Measures what AI actually ships.

Features

- Automatic session tracking (start, end, heartbeat) - Event logging (commits, PRs, deploys, file edits) - Cost tracking per session and per deliverable - GitHub PR metrics (review rounds, time to merge) - Productivity reports with ROI calculation - Zero latency — all tracking is async, never blocks your workflow

Quick Start

npx @costlens/mcp-server setup One command. Browser opens, authenticates, auto-configures your agent. 30 seconds.

Tools

- start_session — Begin tracking a coding session - end_session — End session with outcome + artifacts - log_event — Log commits, PRs, deploys - get_productivity_summary — Sessions, cost, output for a period - get_spend_summary — Daily/weekly/monthly AI spend - get_github_metrics — PRs merged, review rounds, cost per PR - costlens_suggest_model — Get cost-optimized model suggestion

Links

- Website: https://costlens.dev - Docs: https://costlens.dev/docs/mcp - npm: https://www.npmjs.com/package/@costlens/mcp-server

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

get_spend_summary

costlens_suggest_model

start_session

end_session

log_event

get_productivity_summary

get_github_metrics

Claude Desktop / Cursor

McpServers

CostLens MCP Server

Features

Quick Start

Tools

Links

Install

More like this

Sequential Thinking

Time

Filesystem

EverArt

Google Drive

Context 7

`get_spend_summary`

`costlens_suggest_model`

`start_session`

`end_session`

`log_event`

`get_productivity_summary`

`get_github_metrics`