Returns either the full graph JSON or a narrow neighborhood view.
AI agents call atp_read_graph to retrieve information from ATP Librarian MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves graph data (task dependency graph) without creating, modifying, deleting, or executing operations. It is a pure read operation with minimal blast radius—an agent cannot misuse it to cause irreversible harm, financial loss, or unintended execution.
From the tool's definition Tool name 'atp_read_graph' and description 'Returns either the full graph JSON or a narrow neighborhood view' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Returns either the full graph JSON or a narrow neighborhood view. It is categorised as a Read tool in the ATP Librarian MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ATP Librarian MCP Server MCP server in PolicyLayer and add a rule for atp_read_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 ATP Librarian MCP Server. Nothing to install.
atp_read_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 atp_read_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 atp_read_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.
atp_read_graph is provided by the ATP Librarian MCP Server MCP server (manuelcecchetto/atp-mcp-server). 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 →