AI agents call tm_analyse_capture to retrieve information from Tm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the tool name and server context, 'analyse_capture' most likely retrieves and examines existing captured traffic data without modifying it. However, confidence is moderate (0.6) due to missing description. If the tool performed arbitrary code execution on capture data, it could be Execute, but the name and triage context suggest passive analysis.
From the tool's definition Tool name 'tm_analyse_capture' suggests reading and analyzing captured network traffic data. The server description mentions 'CI-failure triage' and 'load-testing', indicating analytical use.
Attacks that exploit this kind of access
tm_analyse_capture. It is categorised as a Read tool in the Tm MCP Server, which means it retrieves data without modifying state.
Register the Tm MCP server in PolicyLayer and add a rule for tm_analyse_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_analyse_capture 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 tm_analyse_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_analyse_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_analyse_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 →