evidence.search
Generate a category-aware, rights-governed acquisition query plan.
This record as markdown: /tools/visionmcp/evidence.search.md
What evidence.search does on Visionmcp
AI agents call evidence.search 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.search is rated Low
This tool generates a query plan for acquiring data (search/query operation) rather than executing it, modifying data, or triggering external effects. The emphasis on 'rights-governed' suggests access control but not side effects. This is a read-category operation with low blast radius — misuse would retrieve data a user shouldn't access, but cannot delete, execute code, or cause financial harm.
From the tool's definition Tool name contains 'search' and description states 'Generate a category-aware, rights-governed acquisition query plan' — both indicate data retrieval and query planning with no modification or execution of external systems.
Attacks that exploit this kind of access
The rule that runs evidence.search 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.search, this is the rule to start with:
evidence.search 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.search call is checked against it from then on.
Questions about evidence.search
Generate a category-aware, rights-governed acquisition query plan. 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.search: 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.search 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.search 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.search. 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.search 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