evidence.audit
Audit source provenance and rights-ledger completeness.
This record as markdown: /tools/visionmcp/evidence.audit.md
What evidence.audit does on Visionmcp
AI agents call evidence.audit to retrieve information from Visionmcp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why evidence.audit is rated Low
Auditing and checking provenance/ledger completeness are read-only operations that query and retrieve information about data lineage and compliance status. No evidence suggests this tool creates, modifies, deletes, executes code, or performs financial operations. The blast radius of misuse is minimal since the tool only inspects existing state.
From the tool's definition Tool name is 'evidence.audit' and description states it audits 'source provenance and rights-ledger completeness' — these are inspection and verification operations with no indication of data modification, deletion, or external side effects.
Attacks that exploit this kind of access
The rule that runs evidence.audit safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Visionmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For evidence.audit, this is the rule to start with:
evidence.audit is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Visionmcp, apply this rule, and every evidence.audit call is checked against it from then on.
Questions about evidence.audit
Audit source provenance and rights-ledger completeness. It is categorised as a Read tool in the Visionmcp MCP Server, which means it retrieves data without modifying state.
Register the Vision MCP server in PolicyLayer and add a rule for evidence.audit: 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 Visionmcp. Nothing to install.
evidence.audit 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 evidence.audit 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 evidence.audit. 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.
evidence.audit is provided by the Vision MCP server (joshuahickscorp/visionmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Vision, and thousands of servers like it.
This server
Across the catalogue