Compare multiple runs
AI agents call compare_runs to retrieve information from MCP DS Toolkit Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and compares existing experiment run data for analysis purposes. Comparing runs is a read operation that queries historical experiment metadata and results without creating, modifying, or deleting anything. Even if an AI agent uses it without restriction, it only exposes information about completed experiments—no destructive or side effects occur.
From the tool's definition Tool name 'compare_runs' and description 'Compare multiple runs' indicate querying and analyzing experiment runs without modification.
Attacks that exploit this kind of access
Compare multiple runs. It is categorised as a Read tool in the MCP DS Toolkit Server MCP Server, which means it retrieves data without modifying state.
Register the MCP DS Toolkit Server MCP server in PolicyLayer and add a rule for compare_runs: 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 MCP DS Toolkit Server. Nothing to install.
compare_runs 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_runs 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_runs. 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_runs is provided by the MCP DS Toolkit Server MCP server (yasserelhaddar/mcp-ds-toolkit-server). 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 →