CALL-E For Cursor
Use this skill when the user wants Cursor to use CALL-E for setup checks, authentication recovery, phone call planning, planned call execution, or call status inspection.
This Cursor plugin is MCP-first. Prefer the Cursor MCP tools exposed by the
bundled calle server whenever they are available:
plan_callrun_callget_call_run
Use the CLI fallback only when Cursor MCP tools are unavailable or the user explicitly asks to verify CALL-E through the CLI.
When to use
Use this skill for:
- verifying CALL-E setup in Cursor
- checking that the
calleMCP server is connected - recovering from missing or expired CALL-E MCP authentication
- planning a phone call
- running a planned call after planning returns complete run credentials
- checking a call run status
- reporting the final call summary, details, and transcript when a call reaches a terminal status
Do not use this skill when the user only wants a call script, roleplay, simulated conversation, or general contact lookup that does not require CALL-E.
Safety and consent
- Real phone calls may contact external people or businesses.
- Always use plan_call before run_call.
- Only call run_call when the user clearly intends to place the call.
- Preserve plan_id and confirm_token exactly.
- If the user asked only to verify setup or only to plan, do not run the call.
- Do not guess phone numbers, country codes, language, region, plan_id, confirm_token, or run_id.
- Do not expose OAuth tokens, bearer tokens, authorization codes, callback URLs, refresh tokens, or access tokens.
- Do not configure CALL-E run_call for auto-run.
MCP readiness
Use this flow whenever this Cursor plugin is actively invoked for a CALL-E request. Run it before call planning, when setup is uncertain, when auth fails, or when the user asks to verify CALL-E setup:
- Confirm the
calleMCP server is connected. - Confirm that
plan_call,run_call, andget_call_runare available. - If Cursor asks to authorize the
calleMCP server, use Cursor's MCP authorization flow and continue after authorization completes. - Never ask the user for OAuth tokens, bearer tokens, authorization codes, callback URLs, refresh tokens, or access tokens.
- If the MCP server cannot be connected or authorized, use the CLI fallback.
Setup verification must not place a real phone call. Use only tool discovery,
authorization recovery, and plan_call when the user explicitly asks to plan.
MCP call flow
- Use
plan_callfirst. If the user has not provided enough explicit fields forplan_call, call it withuser_inputset to the latest user message verbatim so CALL-E can ask for missing details. - Read the returned
plan_idandconfirm_token. - If the user's request is to place a call, immediately use
run_callwith the exactplan_idandconfirm_tokenreturned by planning. - Do not ask for a second confirmation between
plan_callandrun_call. - Read the returned
run_id. Preserve it exactly. - After
run_call, wait 60 seconds before the firstget_call_runrequest unless the call already returned a terminal status. - Keep using
get_call_runwith that exactrun_iduntil the call reaches a terminal status or the user asks you to stop. Poll every 5 to 10 seconds after the first status check. - Use
get_call_runonly with a knownrun_id.
Terminal statuses include COMPLETED, FAILED, NO_ANSWER, DECLINED,
CANCELED, CANCELLED, VOICEMAIL, BUSY, and EXPIRED.
For non-terminal statuses, reply with progress in this shape:
Phone call is in progress! Progress:
- <HH:MM:SS message>
Use one bullet per activity item, preserving the order returned by CALL-E.
For each item, prefer the event ts formatted as HH:MM:SS plus message.
If ts is missing, use the message by itself. If there is no activity, use
- Status: <status> when a status exists; otherwise use
- Waiting for the next status update. Do not include the final summary,
details, or transcript until a terminal status is returned.
When the call reaches a terminal status, reply with the final call result, including these sections in this order:
[Status]
<status>
[Call Summary]
<post_summary or summary or message>
[Details]
Callee Number: <primary callee or Not available>
Duration: <duration or Not available>
Time: <start/end time or Not available>
Call id: <call_id or Not available>
[Transcript]
<transcript or Not available.>
If the user asked for extra final content, such as key takeaways or next steps,
add it after [Transcript] under a short heading. Base all final sections only
on the JSON returned by run_call or get_call_run; do not invent a
transcript.
CLI fallback
Run every CLI command through the bundled scripts/run-agent-command.mjs.
Follow the entry-point checks
and write command arguments as JSON data, never shell text.
Stop before authentication if either check fails.
Do not run bare calle or use npx to select the CLI.
Reuse the verified entry point for every command.
Include this attribution in every request:
{"integration": {"source": "cursor", "name": "cursor_plugin", "version": "0.1.1"}}
If the package is missing, use npm install --prefix <directory> @call-e/cli
in a dedicated directory you control, then select that installation.
Use CLI fallback readiness commands in this order:
- Verify the CLI entry point as described above.
- Run
auth status. - If
auth statusreportsusable: false, run blockingauth loginand keep that command running until it exits. - After login completes, run
mcp tools. - Confirm that
plan_call,run_call, andget_call_runare available.
Call recovery
If CLI call start or call run returns call_started: "unknown" with
retry_safe: false, the call may already be in progress.
Do not create a new plan or repeat call start or call run.
Use the CLI-generated top-level next_argv array as the next request's argv.
Keep the same package and integration. Do not parse or execute next_command.
The call recover --recovery-id <recovery_id> arguments use the private local record.
Follow the recovery steps.
If recovery is still uncertain, keep the local record and stop for manual
review. Do not loop call recover.
Keep recovery_id and the recovery command out of user-visible replies and shared logs.
If a CLI command returns auth_required, switch to the CLI fallback readiness
flow and complete login. Before retrying a call command, follow
Call recovery if the submission was uncertain, or use
call status if a run_id is already known.
Use references/commands.md for exact CLI command examples, supported options,
and JSON handling rules.