Patch usage metadata for a given tensor descriptor.
AI agents use patch_usage_metadata to create or update resources in Tensorus MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tensorus MCP environment.
This tool modifies metadata associated with a tensor descriptor but does not delete, execute code, move money, or trigger external operations. Patching metadata is a reversible write operation.
From the tool's definition Tool name 'patch_usage_metadata' indicates modification of metadata. Description explicitly states 'Patch usage metadata for a given tensor descriptor,' confirming it updates/modifies existing data (a metadata patch operation).
Attacks that exploit this kind of access
Patch usage metadata for a given tensor descriptor. It is categorised as a Write tool in the Tensorus MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tensorus MCP server in PolicyLayer and add a rule for patch_usage_metadata: 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.
patch_usage_metadata is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the patch_usage_metadata 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 patch_usage_metadata. 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.
patch_usage_metadata 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 →