Compare current project state against baseline to identify schedule, duration, and cost variances with severity classification
AI agents call compare_baseline to retrieve information from Project Management AI Analysis without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and analyzes project data to generate variance reports. It performs a comparison operation that produces insights but does not create, modify, delete, or execute any actions. The 'severity classification' mentioned is output classification, not a dangerous capability.
From the tool's definition Tool description states it 'Compare[s] current project state against baseline to identify schedule, duration, and cost variances' — a comparison and analysis operation with no modification, deletion, or execution of external processes.
Attacks that exploit this kind of access
Compare current project state against baseline to identify schedule, duration, and cost variances with severity classification. It is categorised as a Read tool in the Project Management AI Analysis MCP Server, which means it retrieves data without modifying state.
Register the Project Management AI Analysis MCP server in PolicyLayer and add a rule for compare_baseline: 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 Project Management AI Analysis. Nothing to install.
compare_baseline 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_baseline 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_baseline. 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_baseline is provided by the Project Management AI Analysis MCP server (pm-mcp-servers). 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 →