AI agents call social_chat_dms to retrieve information from Logiqical without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or lists data (direct message conversations) with no side effects—a pure read operation. The verb 'list' and the absence of any modification, deletion, or execution capability clearly place it in the Read category. Severity is low because retrieving message metadata has minimal blast radius; the tool does not modify data, execute code, or create financial obligations.
From the tool's definition Tool name 'social_chat_dms' with description 'List direct message conversations' indicates a retrieval operation that queries and returns existing direct message data without modification.
Attacks that exploit this kind of access
List direct message conversations. It is categorised as a Read tool in the Logiqical MCP Server, which means it retrieves data without modifying state.
Register the Logiqical MCP server in PolicyLayer and add a rule for social_chat_dms: 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 Logiqical. Nothing to install.
social_chat_dms 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 social_chat_dms 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 social_chat_dms. 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.
social_chat_dms is provided by the Logiqical MCP server (logiqical-mcp-server). 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 →