Cursor Cloud MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CURSOR_API_KEY | No | API key from cursor.com/dashboard/api. Alternatively, sign in in the browser with `npm run login` to store a key at `~/.config/cursor-cloud-mcp/credentials.json`. | |
| CURSOR_EXTENDED_MODE | No | Set to 1 for the same unofficial account endpoints Cursor for Android keeps behind Extended mode. Off by default. | 0 |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| cursor_statusA | Check auth (v1/me) and report documented vs Extended-mode availability. Start here. |
| list_agentsC | List Cloud Agents (v1, newest first). Filter triage queue. |
| list_agents_v0A | Legacy v0 list with repo/branch/PR/summary in one round-trip. Best for PR triage. |
| get_agentB | Durable metadata for one agent (repos, autoCreatePR, latestRunId). |
| get_conversationC | Full verbatim user/assistant transcript (v0/conversation). v1 has no equivalent. |
| list_runsB | List runs (turns) for an agent, newest first. |
| get_runB | One run: status, result text, durationMs, pushed git branches/PRs. |
| get_run_streamC | Fetch SSE run stream and summarize: status/assistant/thinking/tool_call/result events, tail text. |
| get_usageB | Token usage for an agent, total + per run. |
| list_artifactsC | List screenshots/videos/logs under artifacts/. |
| get_artifact_urlB | 15-minute presigned URL for one artifact path. |
| list_modelsA | Recommended model ids for create_agent. |
| create_followup_runB | Send a follow-up prompt to an existing agent (new run). |
| cancel_runB | Cancel the active run (terminal, cannot resume). |
| archive_agentB | Archive (soft-delete). Idempotent. |
| project_lineageC | Extended: Project lineage = ListWorkersForManager + ListBackgroundComposerChildren. Workers, side chats, subagents. |
| start_side_chatD | Extended: StartSideChatBackgroundComposer. |
| steer_agentC | Extended: InjectBackgroundComposerContext (steer / queue message). |
| agent_lifecycleC | Extended: pause | resume | wake | cancel_tool_call. |
| list_pending_followupsD | Extended: account queue (ListPendingFollowups). |
| list_agent_storesD | Extended: Project Context stores (ListAgentStores). |
| read_store_fileC | Extended: ReadAgentStoreFile (Project Context / shared notes). |
| list_workspace_filesD | Extended: live VM workspace (ListWorkspaceFiles). |
| get_diff_detailsC | Extended: branch diff (GetBackgroundComposerDiffDetails). |
| get_prC | Extended: account view of any PR (SCMService/GetPullRequest). |
| get_pr_diffC | Extended: PR file diffs (SCMService/GetPullRequestDiff). |
| get_pr_statusC | Extended: checks + review decision + counts. |
| prewarm_transcriptD | Extended: StreamConversation PREWARM initial_state + blob ids. Raw record behind the transcript viewer. |
| get_blobC | Extended: GetBlobForAgentKV one record blob (base64 blob_data). |
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 29 tools
Most tools target distinct resources and actions, and descriptions clarify differences. The main overlap is list_agents vs list_agents_v0 (legacy version), with minor potential confusion between get_run/get_run_stream and PR-related tools, but these are mostly resolvable by descriptions.
Most names follow snake_case verb_noun conventions (list_*, get_*, create_*, cancel_*), but several are noun-first or state-oriented (cursor_status, project_lineage, agent_lifecycle, prewarm_transcript), creating a mixed but still readable pattern.
29 tools is heavy for the server's apparent scope. The set includes legacy variants (list_agents_v0) and many extended endpoints, pushing well beyond the 3-15 range that tends to be well-scoped.
A critical gap is the absence of a create_agent tool, despite list_models explicitly referencing create_agent. There is also no update_agent or initial run creation, leaving core lifecycle operations incomplete despite extensive read and extended coverage.