AI agents call get_curation_task 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 a curation task using an ID parameter. It performs a read-only query operation without creating, modifying, deleting, or executing any external operations. The verb 'Get' combined with the retrieval pattern (fetch by ID) confirms this is a Read category tool. Severity is low because retrieval of task metadata poses minimal risk even if accessed by an unauthorized agent.
From the tool's definition Tool name 'get_curation_task' and description 'Get a specific curation task by its task ID' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get a specific curation task by its task 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_curation_task: 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_curation_task 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_curation_task 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_curation_task. 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_curation_task 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 →