AI agents call list_evaluation_submissions 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.
The tool performs a list/query operation to retrieve submissions from an Evaluation entity. It does not create, modify, delete, execute commands, or involve financial transactions. The sibling tools on this server (get_*, list_*, check_*) are predominantly read-only accessors, consistent with this classification.
From the tool's definition Tool name is 'list_evaluation_submissions' and description states 'List submissions to an Evaluation' — this is a read-only operation that retrieves/queries evaluation submission data without modification or side effects.
Attacks that exploit this kind of access
List submissions to 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_submissions: 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_submissions 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_submissions 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_submissions. 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_submissions 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 →