AI agents call list_evaluation_submission_bundles 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 and displays existing submission bundles associated with an evaluation in Synapse. It performs no data modification, deletion, or execution of external operations. The action is purely informational and has no blast radius if misused by an AI agent—it can only expose data the agent already has permission to access.
From the tool's definition Tool name 'list_evaluation_submission_bundles' and description 'List submission bundles for an Evaluation' indicate a retrieval operation with no side effects. The verb 'list' is a classic read-only query pattern.
Attacks that exploit this kind of access
List submission bundles for an Evaluation. 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 list_evaluation_submission_bundles: 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.
list_evaluation_submission_bundles 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 list_evaluation_submission_bundles 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 list_evaluation_submission_bundles. 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.
list_evaluation_submission_bundles 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 →