All servers / AI / Syndic MCP server
Syndic MCP server
MCP server for orchestrating external AI CLI engines with sentinel-file completion detection
Tested by ConnectATDScore 86 out of 100. Tested 2026-11-19 on package version 0.8.12. Package: syndic-mcp · source
Score breakdown
| Runs | 18 / 20 | |
|---|---|---|
| Tool descriptions | 20 / 20 | |
| Package safety | 20 / 20 | |
| Maintenance | 20 / 20 | |
| Adoption | 8 / 20 |
What we saw
- Starts and answers the MCP handshake: yes (2.7 seconds including download)
- Tools offered: 3
- Last published: 2026-11-16
- Weekly downloads (npm): 540
- License: MIT · Direct dependencies: 3
Want this server set up for your team?
ConnectATD builds AI automation and wires up MCP servers like this one. Tell us what you are trying to do.
Talk to ConnectATDTools and how they are described
Agents choose tools from these descriptions. Under each name you can see how many of its parameters are explained.
syndic_run16 of 16 parameters describedSpawn an external AI CLI engine to execute a task. For Claude/Codex critiques, reviews, and read-only design consultations, use mode=review and yolo=false; syndic saves the final response. OpenCode also supports mode=review, but its helper tools cannot be hidden: the prompt forbids them and a review that calls one is rejected. Default mode requires the engine to write output and completion files; a response-only exit is a failure. Default: returns task_id immediately (async). Set wait=true to block until done.
syndic_status1 of 1 parameter describedCheck the status of a syndic task. Returns result content if the task has completed.
syndic_cancel1 of 1 parameter describedStop the task process job and wait for termination evidence. Returns termination state; unknown is not stopped.
Tested in a sandbox with an empty environment: no API keys, a throwaway folder, nothing from a real account. A passing test shows the server runs and responds. It is not a security audit.