Return one structured reaction step.
AI agents call get_reaction_step to retrieve information from Scifinder Route without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns a structured reaction step from the SciFinder synthesis route database. It performs a simple query operation with no side effects, data modification, or code execution. The verb 'Return' confirms it is a read-only retrieval operation. Severity is low because retrieving individual records poses minimal risk even if misused by an agent.
From the tool's definition Tool name 'get_reaction_step' and description 'Return one structured reaction step' indicate retrieval of a single data record without modification or execution of operations.
Attacks that exploit this kind of access
Return one structured reaction step. It is categorised as a Read tool in the Scifinder Route MCP Server, which means it retrieves data without modifying state.
Register the Scifinder Route MCP server in PolicyLayer and add a rule for get_reaction_step: 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 Scifinder Route. Nothing to install.
get_reaction_step 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_reaction_step 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_reaction_step. 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_reaction_step is provided by the Scifinder Route MCP server (kettly1260/scifinder-route-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 →