start_remote_task
[SUPPORT] 32d3d5de — Launch a long-running job on a remote host (e.g. a rented GPU pod) over a short-lived SSH connection used ONLY to start it, never held open: the command runs fully detached (nohup+setsid), so it survives the launching connection dropping for any reason. Returns quickly (a few...
This record as markdown: /tools/io-github-ajc3xc-meridian/start-remote-task.md
What start_remote_task does on Meridian
AI agents invoke start_remote_task to trigger actions in Meridian. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
host | string | Yes | SSH destination: hostname, user@host, or a configured ssh-config alias. |
command | string | Yes | Shell command to run on the remote host. Opaque — pipes/redirects/env assignments are all valid. |
project_id | string | — | |
session_id | string | Yes | |
ttl_seconds | integer | — | Optional caller-declared time-to-live; validated but not yet enforced (no background poller in v1). |
project_name | string | — | Project name — an alternative to project_id; resolved to the id internally. project_id wins if both are given. |
sprint_item_id | string | — | Optional sprint item this job is doing work for. |
Parameters from the server's own tool schema.
Why start_remote_task is rated High
start_remote_task triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsAccepts URL/endpoint input (host)
Attacks that exploit this kind of access
The rule that runs start_remote_task safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Meridian, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For start_remote_task, this is the rule to start with:
start_remote_task stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Meridian, apply this rule, and every start_remote_task call is checked against it from then on.
Questions about start_remote_task
[SUPPORT] 32d3d5de — Launch a long-running job on a remote host (e.g. a rented GPU pod) over a short-lived SSH connection used ONLY to start it, never held open: the command runs fully detached (nohup+setsid), so it survives the launching connection dropping for any reason. Returns quickly (a few hundred ms) with a job_id regardless of how long the underlying job takes — poll get_remote_task_status separately to check on it. Do not include credentials in command; use env vars already set on the remote host instead. Persistent-state disclosure: on hosted Meridian, supplied text and project/session metadata -- including task log entries, pinned decisions, sprint items, notes, handoff/goal state, and HITL queue items -- are sent to and stored in Meridian's service, in an isolated per-tenant Postgres database (Neon); self-hosted deployments keep the same categories in the configured local SQLite/Postgres database. This data is visible in the dashboard and API, and may resurface in later project context or handoffs. Notes and pinned decisions can be deleted individually; task log entries and sprint items can be deleted via the dashboard/API (not exposed as an agent-facing tool); HITL queue items and handoff state have no per-record delete. Full removal of any of this data is available via project or account deletion, using the documented controls. Do not include secrets. It is categorised as a Execute tool in the Meridian MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
start_remote_task accepts 7 parameters: host, command, project_id, session_id, ttl_seconds, project_name, sprint_item_id. Required: host, command, session_id. The full parameter table on this page comes from the server's own tool schema.
Register the Meridian MCP server in PolicyLayer and add a rule for start_remote_task: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Meridian. Nothing to install.
start_remote_task is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the start_remote_task rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for start_remote_task. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
start_remote_task is provided by the Meridian MCP server (@meridianmcp/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Meridian, and thousands of servers like it.
Across the catalogue