AI agents call doc88_check_dependencies to retrieve information from GBMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a diagnostic check of existing local dependencies—a read-only operation that queries system state and reports findings. There is no modification, deletion, execution of external commands, or financial transaction. The context (Doc88 document downloads) further confirms this is a preparatory utility to inspect prerequisites before other actions.
From the tool's definition Tool name 'check_dependencies' and description 'Check local dependencies' indicate a query/inspection operation. The verb 'check' is intrinsically non-destructive and retrieves status information without modifying system state.
Attacks that exploit this kind of access
Check local dependencies for Doc88 high-fidelity downloads. It is categorised as a Read tool in the GBMCP MCP Server, which means it retrieves data without modifying state.
Register the GB MCP server in PolicyLayer and add a rule for doc88_check_dependencies: 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 GBMCP. Nothing to install.
doc88_check_dependencies 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 doc88_check_dependencies 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 doc88_check_dependencies. 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.
doc88_check_dependencies is provided by the GB MCP server (loydgik/gbmcp). 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 →