Cursor Admin MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CURSOR_API_KEY | Yes | A Cursor team admin API key (get it from your team settings) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_team_membersB | Get list of team members with their names, emails, and roles |
| get_daily_usage_dataC | Get detailed daily usage metrics for the team including lines added/deleted, AI suggestions, and model usage |
| get_spending_dataC | Get team member spending information with optional filtering and pagination |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: get_daily_usage_data focuses on usage metrics, get_spending_data on financial data, and get_team_members on personnel information. There is no overlap in functionality or ambiguity between them.
All tool names follow a consistent verb_noun pattern with 'get_' as the prefix, followed by a descriptive noun phrase (e.g., daily_usage_data, spending_data, team_members). This uniformity makes the tools predictable and easy to understand.
With only 3 tools, the set feels thin for an admin server, as it lacks operations like update, create, or delete for team members or spending. While the tools cover key read-only functions, the scope suggests more administrative actions would be expected.
The toolset is severely incomplete for an admin domain, offering only read operations (get) without any ability to modify data, manage users, or handle configurations. This creates significant gaps that will limit agent effectiveness in administrative tasks.