AI-based effort estimation for work items
AI agents call getPredictiveEffortEstimation to retrieve information from Azure Devops without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads work item data and returns computed effort estimates. While it performs analysis, it has no side effects—it doesn't create, modify, delete, or execute external operations. The output is informational/advisory rather than actionable on systems. Misuse (e.g., unreliable estimates) has low blast radius since estimates are typically reviewed before decisions are made based on them.
From the tool's definition The tool provides 'AI-based effort estimation for work items' which is a predictive analysis function that retrieves or computes estimates without modifying work item state, triggering external operations, or creating financial obligations.
Documented attack patterns abuse exactly the kind of access getPredictiveEffortEstimation gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Azure Devops, and nothing reaches the server without passing your rules. This is the rule we recommend for getPredictiveEffortEstimation:
{
"version": "1",
"default": "deny",
"tools": {
"getPredictiveEffortEstimation": {}
}
}getPredictiveEffortEstimation is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
AI-based effort estimation for work items. It is categorised as a Read tool in the Azure Devops MCP Server, which means it retrieves data without modifying state.
Register the Azure Devops MCP server in PolicyLayer and add a rule for getPredictiveEffortEstimation: 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 Azure Devops. Nothing to install.
getPredictiveEffortEstimation 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 getPredictiveEffortEstimation 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 getPredictiveEffortEstimation. 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.
getPredictiveEffortEstimation is provided by the Azure Devops MCP server (ryancardin15/azuredevops-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 97 Azure Devops tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
97 Azure Devops tools catalogued and risk-classified — across an index of 42,500+ MCP servers.