Log the outcome of an action that has already executed. Use this when you don
AI agents use sidclaw_record to create or update resources in Sdk — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sdk environment.
This tool creates or modifies audit log entries, which is a write operation. The severity is medium rather than high because it operates on audit records after actions complete (no direct impact on primary systems), but the incomplete description and its role in a governance proxy system (where tampering with logs could hide misconduct) warrant moderate concern.
From the tool's definition 'Log the outcome of an action that has already executed' — the tool writes records/logs to a system. The description is incomplete ('Use this when you don') but the core function is recording/writing audit trail data.
Documented attack patterns abuse exactly the kind of access sidclaw_record gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Sdk, and nothing reaches the server without passing your rules. This is the rule we recommend for sidclaw_record:
{
"version": "1",
"default": "deny",
"tools": {
"sidclaw_record": {
"limits": [
{
"counter": "sidclaw_record_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}sidclaw_record 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.
Log the outcome of an action that has already executed. Use this when you don. It is categorised as a Write tool in the Sdk MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sdk MCP server in PolicyLayer and add a rule for sidclaw_record: 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 Sdk. Nothing to install.
sidclaw_record 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 sidclaw_record 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 sidclaw_record. 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.
sidclaw_record is provided by the Sdk MCP server (@sidclaw/sdk). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Sdk, 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.
10 Sdk tools catalogued and risk-classified — across an index of 43,000+ MCP servers.