feasible_now
AI agents call feasible_now to retrieve information from Procurement Graph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name suggests checking whether an artifact is feasible at the current time. Given the server's purpose (dependency graph navigation and impact analysis) and the pattern of sibling tools that are all Read operations (get_analysis, get_artifact_example, get_deliverable, get_dependencies, get_dependents, get_engagement_context, get_phase, list_analyses), this tool most likely retrieves or evaluates feasibility…
From the tool's definition Tool name 'feasible_now' with empty description; inferred from server context as a query/navigation function similar to sibling tools (get_*, list_*) that likely checks feasibility status of procurement artifacts.
Attacks that exploit this kind of access
feasible_now. It is categorised as a Read tool in the Procurement Graph MCP Server, which means it retrieves data without modifying state.
Register the Procurement Graph MCP server in PolicyLayer and add a rule for feasible_now: 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 Procurement Graph. Nothing to install.
feasible_now 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 feasible_now 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 feasible_now. 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.
feasible_now is provided by the Procurement Graph MCP server (mfbaig35r/procurement-graph). 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 →