View event log / audit trail for a project.
AI agents call get_provenance to retrieve information from Writbase without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical event and audit information for a project. Viewing logs and audit trails is a read-only operation that does not modify state, execute code, or trigger external actions. The low severity reflects minimal risk: an agent could access potentially sensitive audit data, but cannot change, delete, or execute anything via this tool.
From the tool's definition Tool name is 'get_provenance' and description states 'View event log / audit trail for a project' — both indicate data retrieval with no modification or side effects.
Documented attack patterns abuse exactly the kind of access get_provenance gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Writbase, and nothing reaches the server without passing your rules. This is the rule we recommend for get_provenance:
{
"version": "1",
"default": "deny",
"tools": {
"get_provenance": {}
}
}get_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.
View event log / audit trail for a project. It is categorised as a Read tool in the Writbase MCP Server, which means it retrieves data without modifying state.
Register the Writbase MCP server in PolicyLayer and add a rule for get_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 Writbase. Nothing to install.
get_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_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_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_provenance is provided by the Writbase MCP server (https://{PROJECT_REF}.supabase.co/functions/v1/mcp-server/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Writbase, 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.
13 Writbase tools catalogued and risk-classified — across an index of 43,000+ MCP servers.