查询任务的上下游依赖关系。返回依赖图，包含每个关联任务的状态和依赖类型。
AI agents call get_task_dependencies to retrieve information from Agent-Comm-Hub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns information about task dependencies without modifying, executing, or deleting any data. It is a pure read operation that provides visibility into task relationship metadata. Low severity because reading dependency information poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name is 'get_task_dependencies' and description states '查询任务的上下游依赖关系' (queries task upstream/downstream dependencies). Returns dependency graph with associated task statuses and dependency types.
Attacks that exploit this kind of access
查询任务的上下游依赖关系。返回依赖图，包含每个关联任务的状态和依赖类型。. It is categorised as a Read tool in the Agent-Comm-Hub MCP Server, which means it retrieves data without modifying state.
Register the Agent-Comm-Hub MCP server in PolicyLayer and add a rule for get_task_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 Agent-Comm-Hub. Nothing to install.
get_task_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 get_task_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 get_task_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.
get_task_dependencies is provided by the Agent-Comm-Hub MCP server (liuboacean/agent-comm-hub). 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 →