Atomically append a single action_log entry to STATE.json.
AI agents use mureo_state_action_log_append to create or update resources in Mureo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mureo environment.
This tool writes/appends data to a local STATE.json file. It is a reversible write operation (appending a log entry), not destructive (no deletion or overwrite of existing data).
From the tool's definition Atomically append a single action_log entry to STATE.json
Documented attack patterns abuse exactly the kind of access mureo_state_action_log_append gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mureo, and nothing reaches the server without passing your rules. This is the rule we recommend for mureo_state_action_log_append:
{
"version": "1",
"default": "deny",
"tools": {
"mureo_state_action_log_append": {
"limits": [
{
"counter": "mureo_state_action_log_append_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}mureo_state_action_log_append 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.
Atomically append a single action_log entry to STATE.json. It is categorised as a Write tool in the Mureo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mureo MCP server in PolicyLayer and add a rule for mureo_state_action_log_append: 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 Mureo. Nothing to install.
mureo_state_action_log_append 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 mureo_state_action_log_append 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 mureo_state_action_log_append. 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.
mureo_state_action_log_append is provided by the Mureo MCP server (logly/mureo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mureo, 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.
185 Mureo tools catalogued and risk-classified — across an index of 43,000+ MCP servers.