AI agents call list_my_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.
This tool retrieves information about the current user's submissions without creating, modifying, deleting, or executing any operations. It is a simple data retrieval function analogous to 'list' or 'get' operations, which are characteristic of the Read category. The scope is limited to the current user's own data, further reducing risk.
From the tool's definition Tool name 'list_my_submissions' and description 'List current user's submissions' indicate a query/retrieval operation with no modification or deletion of data.
Attacks that exploit this kind of access
List current user's submissions. 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_my_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_my_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_my_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_my_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_my_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 →