AI agents call get_submission 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 a submission object by its identifier. The verb 'Get' combined with the retrieval-focused description and the pattern of sibling tools (all read operations like get_entity_acl, get_entity_annotations, get_entity_schema) confirms this is a read-only query operation with no side effects.
From the tool's definition Tool name and description indicate a retrieval operation: 'Get a Synapse Submission by its ID' uses the verb 'Get' which retrieves data without modification. No side effects, destructive actions, code execution, or financial operations are described.
Attacks that exploit this kind of access
Get a Synapse Submission by its ID. 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_submission: 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_submission 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_submission 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_submission. 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_submission 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 →