Cueapi

ai.cueapiPublished by cueapi.aiv0.1.3Updated Oct 24, 2026

Schedule agent work and report write-once outcomes via CueAPI from any MCP host.

VerifiedSTDIODesktop onlyProductivity & Workflow AI & ML

Server details

Identifier: ai.cueapi/mcp
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified that this server's namespace belongs to cueapi.ai. It runs from a package rather than a hosted endpoint, so there is no endpoint to match against that domain.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/ai.cueapi%2Fmcp.svg)](https://sourceweft.com/mcp/ai.cueapi%2Fmcp?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Lets an assistant schedule recurring or one-time agent jobs through CueAPI and report their outcomes with evidence.

What you can do: This is the official CueAPI MCP server, exposing tools to create, list, inspect, update, pause, resume, fire, and delete cues (cron or one-time scheduled jobs). It also lists and fetches execution history, claims unclaimed worker executions, extends claim leases with heartbeats, and reports write-once outcomes backed by an external ID or result URL.
When to use it: Use it when an assistant needs to schedule its own follow-up work, coordinate handoffs across time or agents, or close the loop by recording a verifiable outcome for a job. It suits agent workflows that span multiple calls rather than single-turn tasks.
Requirements: Runs locally over stdio, typically via npx @cueapi/mcp or a global npm install, so Node.js is needed. A CueAPI API key must be supplied in the CUEAPI_API_KEY environment variable; CUEAPI_BASE_URL can override the default endpoint for self-hosted instances. Network access to CueAPI is required.

Before you install

The server requires the secret CUEAPI_API_KEY, which is passed in the host configuration environment. Tools can create, update, fire, pause, resume, and permanently delete cues, and can claim executions and report outcomes, so an assistant can change or remove scheduled work and write records. Outcome reports are described as write-once. Job payloads and callbacks are sent to the CueAPI service.

Installation

In SourceWeft

Open Cueapi in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

cueapi-mcp

Official Model Context Protocol server for CueAPI, the open-source coordination layer for AI agent systems.

Give your MCP-enabled assistant (Claude Desktop, Cursor, Zed, or any other MCP host) the ability to schedule agent work, fetch execution history, and close the loop with evidence-backed outcome reports, all from inside a conversation.

Why

Agents don't finish in one call. They coordinate across time, tools, environments, agents, and humans. Every handoff is a place where silent failure hides. CueAPI closes each handoff with structured evidence: an external ID, a result URL, or an artifact. This MCP server gives the agent direct access to that surface, so the agent can both schedule its own follow-up work and report outcomes with proof.

Install

Configure (Claude Desktop)

Add this to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

json

{  "mcpServers": {    "cueapi": {      "command": "npx",      "args": ["-y", "@cueapi/mcp"],      "env": {        "CUEAPI_API_KEY": "cue_sk_..."      }    }  }}

{  "mcpServers": {    "cueapi": {      "command": "npx",      "args": ["-y", "@cueapi/mcp"],      "env": {        "CUEAPI_API_KEY": "cue_sk_..."      }    }  }}

Generate your API key at cueapi.ai. Self-hosting? Set CUEAPI_BASE_URL alongside CUEAPI_API_KEY.

Configure (Cursor / Zed / other hosts)

Any MCP host that supports stdio servers can run this. Point the host at the cueapi-mcp binary and pass CUEAPI_API_KEY in the environment.

Tools exposed

Tool	What it does
`cueapi_create_cue`	Create a recurring (cron) or one-time (`at`) cue
`cueapi_list_cues`	List cues, filter by status
`cueapi_get_cue`	Fetch details for a single cue
`cueapi_fire_cue`	Fire an existing cue immediately, optional payload override
`cueapi_update_cue`	Update a cue's mutable fields (name, schedule, callback, payload, etc.)
`cueapi_pause_cue`	Pause a cue so it stops firing
`cueapi_resume_cue`	Resume a paused cue
`cueapi_delete_cue`	Delete a cue permanently
`cueapi_list_executions`	List historical executions, filter by cue/status
`cueapi_get_execution`	Fetch a single execution by ID, with state + outcome
`cueapi_list_claimable_executions`	List unclaimed worker executions, filter server-side by task/agent
`cueapi_claim_execution`	Atomically claim a specific execution for processing
`cueapi_claim_next_execution`	Claim the next available execution (optional task filter)
`cueapi_execution_heartbeat`	Extend the claim lease on an in-flight execution
`cueapi_report_outcome`	Report write-once outcome with evidence (external ID / URL)

Example conversation

You: Schedule a daily 9am job that posts a digest to my webhook.

Assistant (uses cueapi_create_cue): Created cue cue_abc123, first fire tomorrow at 9:00 UTC.

You: Show me the last five times it ran.

Assistant (uses cueapi_list_executions): ...

Development

bash

npm installnpm test        # vitest smoke tests for the tool surfacenpm run build   # compile TypeScript to dist/npm run dev     # run the server locally with tsx

npm installnpm test        # vitest smoke tests for the tool surfacenpm run build   # compile TypeScript to dist/npm run dev     # run the server locally with tsx

Changelog

0.4.1. Add cueapi_update_cue tool: update a cue's mutable fields (name, schedule, callback URL, timezone, payload, description). Wraps PATCH /v1/cues/{id}. Sparse update — only provided fields are sent. Closes the cross-wrapper parity gap (every other client wrapper exposed update; MCP didn't until now).
0.4.0. Add five execution-lifecycle tools — cueapi_get_execution, cueapi_list_claimable_executions, cueapi_claim_execution, cueapi_claim_next_execution, cueapi_execution_heartbeat. Closes the receive-claim-process-complete loop for MCP-host agents that want to consume worker-transport executions from in-session (e.g. Claude Desktop, Cursor, Zed). Highlights: list_claimable_executions filters server-side via task / agent query params (client-side filtering hits a known LIMIT-50 starvation bug); claim_next_execution accepts an optional task_name and internally fans out (filtered list → pick oldest → claim by ID) since the server doesn't yet support a task filter on the bare claim endpoint; execution_heartbeat sends worker_id via the X-Worker-Id request header (the server's transport for that field) and requires it in the schema so misconfigured callers fail at the wrapper instead of silently bypassing race protection. Internal: CueAPIClient.request() gains an optional extraHeaders parameter to support per-call custom headers.
0.3.0. Add cueapi_fire_cue tool: fire an existing cue immediately with an optional payload_override (and merge_strategy: 'merge' | 'replace', default 'merge'). Wraps POST /v1/cues/{id}/fire. Lets agents trigger ad-hoc one-shot executions without creating throwaway cues, and lets per-fire dynamic data flow through to webhook dispatch + worker-claim responses without mutating the stored cue.
0.1.4. Fix cueapi_pause_cue / cueapi_resume_cue to use PATCH /v1/cues/{id} with {"status": "paused" | "active"} (previously called non-existent /pause and /resume endpoints, returning a runtime 404). PR #1. This is the release that actually contains the fix; 0.1.3 was published prematurely with this note but without the merged code.
0.1.3. Premature publish, superseded by 0.1.4. No functional changes from 0.1.2.
0.1.2. Register with the Official MCP Registry.
0.1.0. Initial release: 8 tools for create / list / get / pause / resume / delete cues, list executions, report outcome.

License

Source: README.md at commit f29c97d

Tools

SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

v0.1.3LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts