Retrieve direct/private messages. Optionally filter to a conversation with a specific user.
AI agents call zulip_get_direct_messages to retrieve information from Zulip 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 or queries existing direct messages without modifying, deleting, or executing any operations. It is a read-only operation that falls squarely into the Read category. Severity is low because unauthorized message retrieval, while a privacy concern, does not have destructive or financial consequences at the operational level.
From the tool's definition Tool name 'zulip_get_direct_messages' and description 'Retrieve direct/private messages' indicate data retrieval with no side effects.
Attacks that exploit this kind of access
Retrieve direct/private messages. Optionally filter to a conversation with a specific user. It is categorised as a Read tool in the Zulip MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Zulip MCP Server MCP server in PolicyLayer and add a rule for zulip_get_direct_messages: 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 Zulip MCP Server. Nothing to install.
zulip_get_direct_messages 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 zulip_get_direct_messages 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 zulip_get_direct_messages. 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.
zulip_get_direct_messages is provided by the Zulip MCP Server MCP server (prixite/zulip-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 →