find_hard_coded_inputs
AI agents call find_hard_coded_inputs to retrieve information from ModelRisk MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to scan or query the workbook to identify hard-coded input values, likely for audit or transparency purposes. No description is provided, which slightly lowers confidence, but the naming convention and peer tools strongly suggest a read-only analysis function. If it were Execute or Write, it would more likely be named 'replace_hard_coded_inputs' or similar.
From the tool's definition Tool name 'find_hard_coded_inputs' suggests inspection/detection of values within a workbook; the prefix 'find_' and the verb form indicate a search or discovery action rather than modification.
Attacks that exploit this kind of access
find_hard_coded_inputs. It is categorised as a Read tool in the ModelRisk MCP MCP Server, which means it retrieves data without modifying state.
Register the ModelRisk MCP server in PolicyLayer and add a rule for find_hard_coded_inputs: 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 ModelRisk MCP. Nothing to install.
find_hard_coded_inputs 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 find_hard_coded_inputs 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 find_hard_coded_inputs. 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.
find_hard_coded_inputs is provided by the ModelRisk MCP server (vosesoftware/modelrisk-mcp). 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 →