Retrieve the OPTIX threat intelligence feed — a paginated stream of curated,
AI agents call feed.get to retrieve information from OPTIX: Operational Platform for Threat Intelligence Exploration without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query of threat intelligence feed data with pagination. It retrieves pre-existing threat data without creating, modifying, deleting, or executing operations. No side effects or irreversible actions are possible. The low severity reflects that threat intelligence feeds are typically curated and intended for consumption by analysts without blast radius from accidental misuse.
From the tool's definition Tool name 'feed.get' and description 'Retrieve the OPTIX threat intelligence feed — a paginated stream of curated' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Retrieve the OPTIX threat intelligence feed — a paginated stream of curated,. It is categorised as a Read tool in the OPTIX: Operational Platform for Threat Intelligence Exploration MCP Server, which means it retrieves data without modifying state.
Register the OPTIX: Operational Platform for Threat Intelligence Exploration MCP server in PolicyLayer and add a rule for feed.get: 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 OPTIX: Operational Platform for Threat Intelligence Exploration. Nothing to install.
feed.get 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 feed.get 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 feed.get. 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.
feed.get is provided by the OPTIX: Operational Platform for Threat Intelligence Exploration MCP server (AdamWaldie/OPTIX-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 →