AI agents call get_entity_permissions 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 permission metadata for the current user on a given entity. It performs a query operation that returns information without modifying, deleting, or executing anything. While permissions information could be sensitive, the tool itself only reads and returns existing data, making it a Read category tool.
From the tool's definition Tool name is 'get_entity_permissions' and description states 'Get current user's permissions on a Synapse entity' — the verb 'Get' and the read-only nature of querying permissions indicate this is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get current user's permissions on 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_permissions: 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_permissions 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_permissions 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_permissions. 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_permissions 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 →