Cursor Usage vs Cursor Delegate
A side-by-side look at the Cursor Usage and Cursor Delegate MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Cursor Usage for coding agents work as a local process; choose Cursor Delegate for coding agents as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Cursor Usage when
- You need dedicated capabilities in the Coding Agents domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: API key required.
- You have the keys it needs:
CURSOR_API_KEY. - You want tools like
get_team_members, get_spending, get_daily_usage.
Choose Cursor Delegate when
- You need dedicated capabilities in the Coding Agents domain.
- You prefer a local stdio subprocess transport.
- You want tools like
delegate, cancel, doctor.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Coding Agents | Coding Agents |
| Quality signal | 59/100 · Good | 61/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | API key required | Not declared |
| Pricing | BYOK (pay the provider) | Not declared |
| Required env vars | CURSOR_API_KEY | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 8 | 9 |
| Directory activity | 1 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 17 | 3 |
| Full listing | View Cursor Usage | View Cursor Delegate |
Tools & capabilities
Cursor Usage tools 17
get_team_membersList all team members with their roles and status. Returns name, email, role, and whether they've been removed.get_spendingGet current billing cycle spending for all team members. Shows spend in dollars, included vs overage, fast premium requests, and spend limits.get_daily_usageGet daily usage data per user: lines added/deleted, applies, accepts, rejects, tabs, requests by mode (composer/chat/agent), models used, and client versions.get_billing_groupsGet billing groups with member lists, group-level spend, and daily spend breakdown. Also returns billing cycle dates.get_usage_eventsGet granular per-request usage events with model, token counts, costs, and whether the request was chargeable. Supports filtering by user email and date range.set_spend_limitSet a hard spending limit (in dollars) for a specific team member. Use with caution — this will block the user from making requests once the limit is reached.get_dauGet daily active users over time, including breakdowns for CLI, cloud agent, and Bugbot usage.get_model_usageGet model usage breakdown per day: which models are being used, how many messages, and by how many users. Essential for understanding model adoption and cost drivers.get_agent_editsGet agent edit metrics: suggested vs accepted vs rejected diffs and lines. Shows how effectively the team is using AI-generated code.get_tabsGet tab autocomplete usage: suggestions shown vs accepted vs rejected, with line-level detail.get_mcp_usageGet MCP (Model Context Protocol) tool usage: which MCP servers and tools are being used, and how often.get_file_extensionsGet top file extensions being edited with AI: which file types get the most AI suggestions, accepts, and rejects.- +5 more on the listing page
Cursor Delegate tools 3
delegateDelegate a coding task to cursor-agent over ACP. Never shell out to cursor-agent — use this tool only. Auto-approves every permission the agent requests, in any mode and anywhere on disk. Clarifying questions arrive as prose in result — resume with resumeSessionId to answer. Keep model (composer-2.5), fast and effort at their defaults unless the user explicitly asks. See the delegate skill.cancelBest-effort cancel of an in-flight delegation by sessionId. session/cancel is advisory — the agent may finish the turn anyway, and the delegate result then carries cancelRequested. Status: cancelled, killed (agent process observed to exit), not-running (turn already ended, still resumable), not-found (id not in this process's recent session history).doctorSetup diagnostics: plugin version, MCP client capabilities, cursor-agent launcher resolution. Run when delegation fails or agent.found is false.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Cursor Usage
{
"mcpServers": {
"ofershap-cursor-usage": {
"command": "npx",
"args": [
"-y",
"cursor-usage-mcp"
],
"env": {
"CURSOR_API_KEY": "YOUR_CURSOR_API_KEY_HERE"
}
}
}
}
Cursor Delegate
{
"mcpServers": {
"cursor-delegate": {
"command": "npx",
"args": [
"-y",
"cursor-delegate-mcp"
]
}
}
}
Frequently asked questions
Cursor Usage is categorized under Coding Agents and uses a local stdio subprocess. Cursor Delegate belongs to Coding Agents and uses a local stdio subprocess. Pick Cursor Usage for coding agents work and Cursor Delegate for coding agents.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Cursor Usage is bring-your-own-key: usage is billed by the API provider you supply a key for. Auth: api key required. Cursor Delegate has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add ofershap-cursor-usage and cursor-delegate as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Cursor Usage has a quality signal of 59/100 (Good) with 1 views, 0 installs and 8 GitHub stars. Cursor Delegate has 61/100 (Good) with 1 views, 0 installs and 9 GitHub stars.