Read-only. Traverses typed incoming and outgoing task relationships around one task. Returns nodes, edges, lifecycle validity, and unresolved references.
AI agents call task_graph to retrieve information from Agentic Task System without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and traverses existing task graph data without creating, modifying, or deleting anything. It is a pure query/retrieval operation with no irreversible effects or external operations triggered. The explicit 'Read-only' designation confirms this classification.
From the tool's definition Tool description explicitly states 'Read-only' and the function is to traverse and return task relationships, nodes, edges, and metadata—no modification or side effects.
Attacks that exploit this kind of access
Read-only. Traverses typed incoming and outgoing task relationships around one task. Returns nodes, edges, lifecycle validity, and unresolved references. It is categorised as a Read tool in the Agentic Task System MCP Server, which means it retrieves data without modifying state.
Register the Agentic Task System MCP server in PolicyLayer and add a rule for task_graph: 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 Agentic Task System. Nothing to install.
task_graph 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 task_graph 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 task_graph. 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.
task_graph is provided by the Agentic Task System MCP server (renezander030/agentic-task-system). 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 →