snowdrop_search_skills
AI agents call snowdrop_search_skills to retrieve information from Snowdrop MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search operations typically retrieve and query data without side effects. The empty description reduces confidence slightly, but the clear 'search' verb in the name and analogy to 'list_skills' (a sibling) strongly suggest read-only data retrieval. No indication of data modification, execution, deletion, or financial impact.
From the tool's definition Tool name 'snowdrop_search_skills' indicates a search/query operation. Description is empty, limiting definitive classification. Based on naming convention and the sibling tool 'snowdrop_list_skills', this appears to be a read-only discovery/search operation.
Attacks that exploit this kind of access
snowdrop_search_skills. It is categorised as a Read tool in the Snowdrop MCP MCP Server, which means it retrieves data without modifying state.
Register the Snowdrop MCP server in PolicyLayer and add a rule for snowdrop_search_skills: 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 Snowdrop MCP. Nothing to install.
snowdrop_search_skills 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 snowdrop_search_skills 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 snowdrop_search_skills. 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.
snowdrop_search_skills is provided by the Snowdrop MCP server (stonewater-digital/snowdrop-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 →