Search for tensors based on a text query, optionally specifying fields to search.
AI agents call search_tensors to retrieve information from Tensorus MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and queries data from the Tensorus tensor database without modifying, deleting, or executing any operations. It is a pure read operation that retrieves tensors matching specified search criteria. The absence of keywords like 'create', 'delete', 'update', 'execute', or 'run' confirms this is a benign data retrieval function with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'search_tensors' and description 'Search for tensors based on a text query' explicitly indicate a retrieval operation with no mention of modification, deletion, or execution of external code.
Attacks that exploit this kind of access
Search for tensors based on a text query, optionally specifying fields to search. It is categorised as a Read tool in the Tensorus MCP MCP Server, which means it retrieves data without modifying state.
Register the Tensorus MCP server in PolicyLayer and add a rule for search_tensors: 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 Tensorus MCP. Nothing to install.
search_tensors 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 search_tensors 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 search_tensors. 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.
search_tensors is provided by the Tensorus MCP server (tensorus/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 →