AI agents call blame to retrieve information from Selvedge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'blame' tool is a read-only query operation commonly used in version control systems to attribute code changes to specific commits and authors. It retrieves historical metadata without modifying any data. While the tool description is empty, the naming convention and peer tools (diff, history, changeset, search) all indicate query/retrieval semantics.
From the tool's definition Tool named 'blame' with sibling tools including 'changeset', 'diff', 'history', 'log_change', and 'search'. Server context describes it as part of a change tracking and querying interface.
Documented attack patterns abuse exactly the kind of access blame 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 blame:
{
"version": "1",
"default": "deny",
"tools": {
"blame": {}
}
}blame is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
blame. It is categorised as a Read tool in the Selvedge MCP Server, which means it retrieves data without modifying state.
Register the Selvedge MCP server in PolicyLayer and add a rule for blame: 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.
blame is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the blame 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 blame. 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.
blame 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.