Get all contact information for Srikanth
AI agents call get_contact_info to retrieve information from Portfolio MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves contact information without creating, modifying, deleting, or executing anything. It is a straightforward read operation on stored portfolio data. The severity is low because contact information exposure, while a privacy concern, is not an operational risk from AI misuse (no blast radius from unintended invocation). Confidence is high given the explicit 'get' verb and retrieval-only nature.
From the tool's definition Tool name 'get_contact_info' and description 'Get all contact information' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Get all contact information for Srikanth. It is categorised as a Read tool in the Portfolio MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Portfolio MCP Server MCP server in PolicyLayer and add a rule for get_contact_info: 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 Portfolio MCP Server. Nothing to install.
get_contact_info 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_contact_info 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_contact_info. 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_contact_info is provided by the Portfolio MCP Server MCP server (srikanth-karthi/mcp-portfolio). 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 →