AI agents use save_run_digest 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.
Without a description, confidence is reduced, but the name and sibling patterns strongly suggest data creation/modification. 'Digest' likely refers to a summary artifact being stored. This is reversible (write) rather than destructive, and does not execute arbitrary code or move money. Medium severity reflects the potential for unwanted modifications to user coaching/training data if called with incorrect arguments.
From the tool's definition Tool name 'save_run_digest' combined with server context (coaching/progress tracking) and sibling tools like 'add_coaching_feedback', 'add_plan_comment', 'add_plan_run', and 'add_run_note' indicate this creates or modifies data.
Documented attack patterns abuse exactly the kind of access save_run_digest 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 save_run_digest:
{
"version": "1",
"default": "deny",
"tools": {
"save_run_digest": {
"limits": [
{
"counter": "save_run_digest_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}save_run_digest 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.
save_run_digest. 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 save_run_digest: 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.
save_run_digest 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 save_run_digest 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 save_run_digest. 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.
save_run_digest 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.