AI agents call skillsmp_discover to retrieve information from Skillsmp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool discovers or searches for skills based on conversational input. Discovery operations are read-only queries that retrieve information without modifying, executing, or deleting anything. The lack of any state-changing verbs (create, update, delete, execute) indicates this is a passive information retrieval function.
From the tool's definition Tool name contains 'discover' and description states 'AI-powered skill discovery based on conversation context' — discovery is a retrieval/query operation with no side effects.
Attacks that exploit this kind of access
AI-powered skill discovery based on conversation context. It is categorised as a Read tool in the Skillsmp MCP Server, which means it retrieves data without modifying state.
Register the Skillsmp MCP server in PolicyLayer and add a rule for skillsmp_discover: 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 Skillsmp. Nothing to install.
skillsmp_discover 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 skillsmp_discover 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 skillsmp_discover. 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.
skillsmp_discover is provided by the Skillsmp MCP server (@luckybalabalaya/skillsmp-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 →