AI agents call blame_symbol to retrieve information from Srclight without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to retrieve git blame information for a symbol, which is a read-only operation that queries historical attribution without modifying code or executing arbitrary operations. The empty description lowers confidence slightly, but the naming and server context strongly indicate a safe read operation for code analysis.
From the tool's definition Tool name 'blame_symbol' combined with server purpose (code indexing, git history tracking) indicates retrieval of blame/annotation data.
Documented attack patterns abuse exactly the kind of access blame_symbol gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Srclight, and nothing reaches the server without passing your rules. This is the rule we recommend for blame_symbol:
{
"version": "1",
"default": "deny",
"tools": {
"blame_symbol": {}
}
}blame_symbol 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_symbol. It is categorised as a Read tool in the Srclight MCP Server, which means it retrieves data without modifying state.
Register the Srclight MCP server in PolicyLayer and add a rule for blame_symbol: 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 Srclight. Nothing to install.
blame_symbol 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_symbol 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_symbol. 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_symbol is provided by the Srclight MCP server (srclight/srclight). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 42 Srclight tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
42 Srclight tools catalogued and risk-classified — across an index of 42,500+ MCP servers.