search_archives
AI agents call search_archives to retrieve information from SkyFi MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'search_archives' tool almost certainly performs a read/query operation on archived satellite imagery, consistent with the SkyFi server's purpose. No description creates some ambiguity, but the naming convention and sibling tools provide strong contextual evidence. Search operations are typically non-destructive reads with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'search_archives' indicates a query/search operation. Description is empty, limiting certainty. Sibling tools like 'osm_forward_geocode', 'osm_search_businesses', and 'skyfi_analyze_capture_feasibility' are all read operations on geospatial data.
Attacks that exploit this kind of access
search_archives. It is categorised as a Read tool in the SkyFi MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SkyFi MCP Server MCP server in PolicyLayer and add a rule for search_archives: 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 SkyFi MCP Server. Nothing to install.
search_archives 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_archives 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_archives. 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_archives is provided by the SkyFi MCP Server MCP server (pskinnertech/skyfi-mcp-server). 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 →