get_dispatch
AI agents call get_dispatch to retrieve information from Claude Bridge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
With no description available, confidence is reduced. However, the 'get_' prefix strongly suggests a read operation that retrieves information about previously dispatched work. The tool does not appear to execute new work, modify data, or have destructive effects based on naming convention. Classified as Read with low severity due to information gap.
From the tool's definition Tool name 'get_dispatch' with no description provided. The 'get' prefix typically indicates retrieval/query operations rather than mutation. Context suggests it retrieves status or results of dispatch operations.
Attacks that exploit this kind of access
get_dispatch. It is categorised as a Read tool in the Claude Bridge MCP Server, which means it retrieves data without modifying state.
Register the Claude Bridge MCP server in PolicyLayer and add a rule for get_dispatch: 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 Claude Bridge. Nothing to install.
get_dispatch 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_dispatch 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_dispatch. 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_dispatch is provided by the Claude Bridge MCP server (josiahsiegel/claude-bridge). 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 →