AI agents use log_change to create or update resources in Selvedge — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Selvedge environment.
The tool name 'log_change' combined with the server description explicitly stating AI agents call it to 'log structured change events' strongly implies this tool writes/creates records in a change-tracking system. This is a reversible write operation (logging), not destructive.
From the tool's definition Tool name 'log_change' on a server described as 'log structured change events (entity + diff + reasoning)' — sibling tools include blame, diff, history suggesting this is the write/logging counterpart
Documented attack patterns abuse exactly the kind of access log_change gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Selvedge, and nothing reaches the server without passing your rules. This is the rule we recommend for log_change:
{
"version": "1",
"default": "deny",
"tools": {
"log_change": {
"limits": [
{
"counter": "log_change_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}log_change 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_change. It is categorised as a Write tool in the Selvedge MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Selvedge MCP server in PolicyLayer and add a rule for log_change: 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 Selvedge. Nothing to install.
log_change 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 log_change 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 log_change. 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.
log_change is provided by the Selvedge MCP server (masondelan/selvedge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Selvedge, 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.
7 Selvedge tools catalogued and risk-classified — across an index of 43,000+ MCP servers.