Set the active role for this MCP session.
AI agents use set_role to create or update resources in FinRAG-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FinRAG-MCP environment.
This tool creates/modifies session state that controls access permissions. While not directly creating persistent data, it reversibly changes the active authorization context, enabling or restricting visibility to sensitive department-specific documents. Misuse could allow an AI agent to escalate privileges or switch to unauthorized roles to access restricted Finance, HR, or Engineering data.
From the tool's definition set_role updates the active role context for the MCP session, which modifies the authorization state and determines what data subsequent queries can access across Engineering, Finance, HR, and Marketing departments.
Attacks that exploit this kind of access
Set the active role for this MCP session. It is categorised as a Write tool in the FinRAG-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the FinRAG- MCP server in PolicyLayer and add a rule for set_role: 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 FinRAG-MCP. Nothing to install.
set_role is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_role 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 set_role. 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.
set_role is provided by the FinRAG- MCP server (nithishkaranam2002/finrag--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 →