Get contacts for task sharing.
AI agents call get_contacts to retrieve information from RTM 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 for the purpose of task sharing. It performs no creation, modification, deletion, or external execution. The operation is a simple data query with no side effects, which aligns with the Read category. Severity is low because contact lists are typically non-sensitive metadata in task management systems, and retrieval alone poses minimal risk even if misused by an agent.
From the tool's definition Tool name is 'get_contacts' and description states 'Get contacts for task sharing' — the verb 'Get' and the retrieval nature indicate a read-only operation that queries existing contact data without modification.
Attacks that exploit this kind of access
Get contacts for task sharing. It is categorised as a Read tool in the RTM MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RTM MCP Server MCP server in PolicyLayer and add a rule for get_contacts: 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 RTM MCP Server. Nothing to install.
get_contacts 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_contacts 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_contacts. 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_contacts is provided by the RTM MCP Server MCP server (ljadach/rtm-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 →