Get the trust propagation graph for an agent (2 hops).
AI agents call mt_get_swarm_graph to retrieve information from MolTrust MCP Server 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 data about trust propagation relationships without modifying state, executing code, deleting data, or affecting financial systems. It is a read-only operation with minimal blast radius if misused by an AI agent—at worst, information disclosure or graph traversal to discover trust relationships, but no reversible or irreversible changes to the system.
From the tool's definition Tool name 'mt_get_swarm_graph' and description 'Get the trust propagation graph for an agent (2 hops)' indicate a retrieval operation.
Attacks that exploit this kind of access
Get the trust propagation graph for an agent (2 hops). It is categorised as a Read tool in the MolTrust MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MolTrust MCP Server MCP server in PolicyLayer and add a rule for mt_get_swarm_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 MolTrust MCP Server. Nothing to install.
mt_get_swarm_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 mt_get_swarm_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 mt_get_swarm_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.
mt_get_swarm_graph is provided by the MolTrust MCP Server MCP server (pypi:moltrust-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 →