DISABLED pending AST-aware rewrite — returns a structured error explaining the limitation. The previous regex-based implementation produced unparseable code on non-trivial inputs (outer-scope identifiers misclassified as parameters; enclosing function headers spliced into the new helper body). Fi...
AI agents call extract_function to retrieve information from Trace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though extract_function only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Documented attack patterns abuse exactly the kind of access extract_function gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Trace, and nothing reaches the server without passing your rules. This is the rule we recommend for extract_function:
{
"version": "1",
"default": "deny",
"tools": {
"extract_function": {}
}
}extract_function 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.
DISABLED pending AST-aware rewrite — returns a structured error explaining the limitation. The previous regex-based implementation produced unparseable code on non-trivial inputs (outer-scope identifiers misclassified as parameters; enclosing function headers spliced into the new helper body). File-existence and line-range validation still run first so obviously malformed inputs keep their familiar errors. Tracking issue: extract_function-ast-rewrite. It is categorised as a Read tool in the Trace MCP Server, which means it retrieves data without modifying state.
Register the Trace MCP server in PolicyLayer and add a rule for extract_function: 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 Trace. Nothing to install.
extract_function 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 extract_function 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 extract_function. 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.
extract_function is provided by the Trace MCP server (nikolai-vysotskyi/trace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 178 Trace tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
178 Trace tools catalogued and risk-classified — across an index of 42,500+ MCP servers.