Consolidated citation evidence entrypoint.
AI agents call evidence to retrieve information from Asset Aware without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to fetch or aggregate citation evidence from the knowledge graph and PDF assets without creating, modifying, executing external operations, or deleting data. The word 'entrypoint' implies it serves as a retrieval interface. While the description is somewhat terse, the broader server purpose (asset analysis and research) and naming convention are consistent with a Read operation.
From the tool's definition Tool name 'evidence' described as 'Consolidated citation evidence entrypoint' suggests retrieval and aggregation of existing citation data for medical research analysis.
Attacks that exploit this kind of access
Consolidated citation evidence entrypoint. It is categorised as a Read tool in the Asset Aware MCP Server, which means it retrieves data without modifying state.
Register the Asset Aware MCP server in PolicyLayer and add a rule for evidence: 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 Asset Aware. Nothing to install.
evidence 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 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. 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 is provided by the Asset Aware MCP server (u9401066/asset-aware-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →