Get one role in full, including its evidence bank and approved resume bullets.
AI agents call get_role to retrieve information from Nima Career without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a single role record with its associated metadata (evidence bank, resume bullets) without modifying, deleting, or executing any operations. It is a straightforward data query over non-sensitive, intentionally published career information. No side effects or external operations are triggered.
From the tool's definition Tool name 'get_role' and description 'Get one role in full' indicate retrieval of pre-existing data. The server description emphasizes 'public-safe career history' and 'pre-approved material', confirming read-only access to curated professional information.
Attacks that exploit this kind of access
Get one role in full, including its evidence bank and approved resume bullets. It is categorised as a Read tool in the Nima Career MCP Server, which means it retrieves data without modifying state.
Register the Nima Career MCP server in PolicyLayer and add a rule for get_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 Nima Career. Nothing to install.
get_role 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 get_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 get_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.
get_role is provided by the Nima Career MCP server (nima-karami/nima-career-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 →