Return provenance (activity) metadata for a Synapse entity, including inputs and code executed.
AI agents call get_entity_provenance to retrieve information from Synapse MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves metadata about an entity's provenance history. It is a read-only operation that accesses existing audit/activity logs without creating, modifying, executing, or deleting anything. The mention of 'code executed' refers to code that was already run in the past (whose history is being retrieved), not code this tool executes.
From the tool's definition Tool name is 'get_entity_provenance' and description states it 'Return[s] provenance (activity) metadata' — a retrieval operation with no modification or execution capability. Returns historical metadata about inputs and code, not executing code itself.
Documented attack patterns abuse exactly the kind of access get_entity_provenance gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Synapse MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_entity_provenance:
{
"version": "1",
"default": "deny",
"tools": {
"get_entity_provenance": {}
}
}get_entity_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.
Return provenance (activity) metadata for a Synapse entity, including inputs and code executed. It is categorised as a Read tool in the Synapse MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Synapse MCP Server MCP server in PolicyLayer and add a rule for get_entity_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 Synapse MCP Server. Nothing to install.
get_entity_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 get_entity_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 get_entity_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.
get_entity_provenance is provided by the Synapse MCP Server MCP server (susheel/synapse-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Synapse MCP Server, 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.
5 Synapse MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.