Find skills relevant to a task. Pass a plain-language query like
AI agents call search_skills to retrieve information from SkillStream MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a skill database and returns matching results without creating, modifying, deleting, or executing any operations. It is a pure information retrieval function with no side effects, fitting the 'Read' category. The low severity reflects minimal blast radius—a misused search returns irrelevant skills but cannot harm systems or data.
From the tool's definition Tool name 'search_skills' and description 'Find skills relevant to a task' indicate a retrieval operation. The phrase 'Pass a plain-language query' confirms it accepts input for searching but performs no modifications or external state changes.
Attacks that exploit this kind of access
Find skills relevant to a task. Pass a plain-language query like. It is categorised as a Read tool in the SkillStream MCP MCP Server, which means it retrieves data without modifying state.
Register the SkillStream MCP server in PolicyLayer and add a rule for 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 SkillStream MCP. Nothing to install.
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 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 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.
search_skills is provided by the SkillStream MCP server (pr-botsai/skillstream-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 →