Находит внешние зависимости: HTTP, БД, Redis, Kafka, файлы, subprocess
AI agents call external_deps to retrieve information from Booster MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists information about external dependencies in a codebase. It performs analysis and enumeration without creating, modifying, deleting, or executing anything. The dependencies it identifies (HTTP calls, database connections, Redis, Kafka, files, subprocesses) are already present in the codebase; the tool merely discovers and reports them.
From the tool's definition Tool name 'external_deps' and description indicate it 'finds external dependencies: HTTP, DB, Redis, Kafka, files, subprocess' — purely informational/discovery action with no modification or execution capability.
Attacks that exploit this kind of access
Находит внешние зависимости: HTTP, БД, Redis, Kafka, файлы, subprocess. It is categorised as a Read tool in the Booster MCP MCP Server, which means it retrieves data without modifying state.
Register the Booster MCP server in PolicyLayer and add a rule for external_deps: 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 Booster MCP. Nothing to install.
external_deps 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 external_deps 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 external_deps. 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.
external_deps is provided by the Booster MCP server (neuroghostdev/booster_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 →