Use this when you want to compare two CONTAM .sim result files with simcomp.
AI agents call compare_contam_sim_results to retrieve information from CONTAM MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes data from simulation result files without modifying, deleting, or executing external commands. The comparison function is a read-only operation that examines pre-existing simulation outputs.
From the tool's definition Tool compares two CONTAM .sim result files using simcomp; no modification, deletion, or execution of arbitrary code—purely comparative analysis of existing simulation outputs.
Attacks that exploit this kind of access
Use this when you want to compare two CONTAM .sim result files with simcomp. It is categorised as a Read tool in the CONTAM MCP MCP Server, which means it retrieves data without modifying state.
Register the CONTAM MCP server in PolicyLayer and add a rule for compare_contam_sim_results: 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 CONTAM MCP. Nothing to install.
compare_contam_sim_results 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 compare_contam_sim_results 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 compare_contam_sim_results. 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.
compare_contam_sim_results is provided by the CONTAM MCP server (summer521521/contam_plugin). 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 →