Personalized skill search that automatically excludes already-installed skills and applies your preferences. Returns a JSON object with results array (each skill has slug, name, description, type, quality_score, stars, security_score, install_command), total count, and personalization metadata sh...
Accepts freeform code/query input (query)
Part of the Loaditout MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call smart_search to retrieve information from Loaditout without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though smart_search only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
smart_search:
rules:
- action: allowSee the full Loaditout policy for all 21 tools.
Agents calling read-class tools like smart_search have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Personalized skill search that automatically excludes already-installed skills and applies your preferences. Returns a JSON object with results array (each skill has slug, name, description, type, quality_score, stars, security_score, install_command), total count, and personalization metadata showing how many installed skills were excluded. This is the preferred search tool for most use cases. Use search_skills only when you need unfiltered results or specific type/agent filters.. It is categorised as a Read tool in the Loaditout MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for smart_search. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Loaditout MCP server.
smart_search 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 smart_search rule in your Intercept 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 Intercept policy for smart_search. 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.
smart_search is provided by the Loaditout MCP server (loaditout-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept