Verify that LLM-generated code is grounded in the provided context. Uses BIPT (Byte-level Information Provenance Tracer) to measure how much of each identifier in the generated code originates from the context. Returns an Identifier Provenance Deficit (IPD) score: IPD = 0.0 → fully grounded (all ...
AI agents call verify_provenance to retrieve information from Entroly Context Engine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
verify_provenance is a purely analytical tool that inspects and measures properties of LLM-generated code against provided context. It reads code artifacts and context data to compute a provenance score, returning that measurement to the user for decision-making. This is a classic Read operation: data retrieval with no mutations, executions, or side effects.
From the tool's definition Tool description states it 'Verify[ies]' and 'measure[s]' provenance, 'Returns an Identifier Provenance Deficit (IPD) score'.
Documented attack patterns abuse exactly the kind of access verify_provenance gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Entroly Context Engine, and nothing reaches the server without passing your rules. This is the rule we recommend for verify_provenance:
{
"version": "1",
"default": "deny",
"tools": {
"verify_provenance": {}
}
}verify_provenance 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.
Verify that LLM-generated code is grounded in the provided context. Uses BIPT (Byte-level Information Provenance Tracer) to measure how much of each identifier in the generated code originates from the context. Returns an Identifier Provenance Deficit (IPD) score: IPD = 0.0 → fully grounded (all identifiers come from context) IPD = 1.0 → fully invented (no identifiers match context) Use this after an LLM generates code to check for hallucinated APIs, invented function names, or fabricated imports before accepting output. Args: code: The LLM-generated code to verify context: The repository context that was provided to the LLM. It is categorised as a Read tool in the Entroly Context Engine MCP Server, which means it retrieves data without modifying state.
Register the Entroly Context Engine MCP server in PolicyLayer and add a rule for verify_provenance: 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 Entroly Context Engine. Nothing to install.
verify_provenance 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 verify_provenance 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 verify_provenance. 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.
verify_provenance is provided by the Entroly Context Engine MCP server (juyterman1000/entroly). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Entroly Context Engine, 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.
52 Entroly Context Engine tools catalogued and risk-classified — across an index of 43,000+ MCP servers.