AI agents use tm_import_capture to create or update resources in Tm — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tm environment.
Without a description, confidence is reduced. The tool likely creates or modifies capture data (reversibly), placing it in Write rather than Read or Execute. Given the load-testing context (tm_analyse_capture, tm_compare_runs), an import operation could affect test datasets but is probably not irreversible or code-execution. Severity is medium due to potential to pollute test data and influence downstream analysis.
From the tool's definition Tool name 'tm_import_capture' suggests data ingestion/upload; the description is empty. Sibling tools include profile/variables set creation and deletion, indicating this server manages mutable state.
Attacks that exploit this kind of access
tm_import_capture. It is categorised as a Write tool in the Tm MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tm MCP server in PolicyLayer and add a rule for tm_import_capture: 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 Tm. Nothing to install.
tm_import_capture 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 tm_import_capture 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 tm_import_capture. 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.
tm_import_capture is provided by the Tm MCP server (trafficmorph-gif/tm-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 →