AI agents call get_entity_acl to retrieve information from Synapse without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves authorization and access control metadata for a Synapse entity. While it performs no write, execute, or destructive actions, the severity is medium rather than low because ACL information can reveal sensitive access patterns and permissions structure that could inform privilege escalation attacks or social engineering.
From the tool's definition Tool name 'get_entity_acl' and description 'Get the ACL for a Synapse entity' indicate a retrieval operation that queries access control list information without modifying data.
Attacks that exploit this kind of access
Get the ACL for a Synapse entity. It is categorised as a Read tool in the Synapse MCP Server, which means it retrieves data without modifying state.
Register the Synapse MCP server in PolicyLayer and add a rule for get_entity_acl: 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 Synapse. Nothing to install.
get_entity_acl 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_entity_acl 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_entity_acl. 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_entity_acl is provided by the Synapse MCP server (sage-bionetworks/synapse-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 →