AI agents use update_plan_run to create or update resources in MCPacer — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCPacer environment.
The tool modifies coaching plan run data (update_plan_run), which is a reversible write operation. It lacks destructive intent (no delete/purge language) and doesn't execute arbitrary commands or move money. Severity is medium because misuse could corrupt a user's training plan, but changes are typically reversible and impact is localized to one user's coaching data.
From the tool's definition Tool name 'update_plan_run' indicates modification of training plan run data. Sibling tools show this server manages Strava fitness data and coaching plans. The 'update' prefix signals a reversible write operation on plan run records.
Documented attack patterns abuse exactly the kind of access update_plan_run gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCPacer, and nothing reaches the server without passing your rules. This is the rule we recommend for update_plan_run:
{
"version": "1",
"default": "deny",
"tools": {
"update_plan_run": {
"limits": [
{
"counter": "update_plan_run_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_plan_run stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
update_plan_run. It is categorised as a Write tool in the MCPacer MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCPacer MCP server in PolicyLayer and add a rule for update_plan_run: 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 MCPacer. Nothing to install.
update_plan_run is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_plan_run 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 update_plan_run. 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.
update_plan_run is provided by the MCPacer MCP server (wernerpe/mcpacer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCPacer, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
32 MCPacer tools catalogued and risk-classified — across an index of 43,000+ MCP servers.