AI agents call tru8_get_result_raw to retrieve information from Tru8 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to fetch results from the Tru8 Evidence Research service. Given the naming pattern ('get_result_raw' vs likely 'tru8_get_result'), this is most consistent with a Read operation that queries and retrieves previously-generated evidence data. The 'raw' suffix suggests returning unprocessed output.
From the tool's definition Tool name contains 'get_result' suggesting data retrieval; empty description limits certainty. Sibling context (tru8_check, tru8_get_result) implies this retrieves already-computed evidence results without modification.
Attacks that exploit this kind of access
tru8_get_result_raw. It is categorised as a Read tool in the Tru8 MCP Server, which means it retrieves data without modifying state.
Register the Tru8 MCP server in PolicyLayer and add a rule for tru8_get_result_raw: 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 Tru8. Nothing to install.
tru8_get_result_raw 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 tru8_get_result_raw 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 tru8_get_result_raw. 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.
tru8_get_result_raw is provided by the Tru8 MCP server (samyatessmith/tru8-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 →