AI agents call view_run to retrieve information from THOUGHT without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays data from a knowledge base using a saved view definition. It has no capability to create, modify, delete, or execute arbitrary operations - it only reads and presents existing data. The blast radius of misuse is minimal, as it can only expose information already stored in the system. This fits the 'Read' category of tools that query or retrieve data without side effects.
From the tool's definition Tool description states 'Run a saved view; rows are pull-evaluated against the live KB' - this is a query/retrieval operation that evaluates and returns data without modifying it.
Attacks that exploit this kind of access
Run a saved view; rows are pull-evaluated against the live KB. It is categorised as a Read tool in the THOUGHT MCP Server, which means it retrieves data without modifying state.
Register the THOUGHT MCP server in PolicyLayer and add a rule for view_run: 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 THOUGHT. Nothing to install.
view_run 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 view_run 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 view_run. 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.
view_run is provided by the THOUGHT MCP server (rnbbarrett/thought-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 →