Asset search autocompletion
AI agents call search_assets_autocomplete to retrieve information from Red Bee MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a search/query operation that retrieves autocomplete suggestions for assets (movies, TV shows, channels). It has no side effects, does not modify data, and does not execute code or trigger external operations. It is purely informational retrieval, fitting the 'Read' category.
From the tool's definition Tool name 'search_assets_autocomplete' and description 'Asset search autocompletion' indicate a read-only query operation that provides autocomplete suggestions for asset searches without modifying data.
Attacks that exploit this kind of access
Asset search autocompletion. It is categorised as a Read tool in the Red Bee MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Red Bee MCP Server MCP server in PolicyLayer and add a rule for search_assets_autocomplete: 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 Red Bee MCP Server. Nothing to install.
search_assets_autocomplete 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 search_assets_autocomplete 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 search_assets_autocomplete. 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.
search_assets_autocomplete is provided by the Red Bee MCP Server MCP server (tamsi/redbee-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 →