Lists all applications available in the Ilumin App Catalog. The output will include the app slug, name, description, and potentially a list of required 'env_vars' (e.g., APP_PASSWORD, APP_USER). WORKFLOW: 1. Call this tool to find the desired app. 2. Present the app details to the user, includ...
Part of the Ilumin MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call list_catalog to retrieve information from Ilumin 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 list_catalog 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:
list_catalog:
rules:
- action: allowSee the full Ilumin policy for all 13 tools.
Agents calling read-class tools like list_catalog 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.
Lists all applications available in the Ilumin App Catalog. The output will include the app slug, name, description, and potentially a list of required 'env_vars' (e.g., APP_PASSWORD, APP_USER). WORKFLOW: 1. Call this tool to find the desired app. 2. Present the app details to the user, including the URL: 'https://ilumin.app/apps?app={slug}'. 3. ASK FOR CONFIRMATION to install. 4. If the app has 'env_vars', you MUST ask the user to provide values for them (e.g., 'Please provide the password for APP_PASSWORD'). 5. Only after getting confirmation (and env vars if needed), proceed to call 'install_catalog_app'.. It is categorised as a Read tool in the Ilumin MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for list_catalog. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Ilumin MCP server.
list_catalog 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 list_catalog 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 list_catalog. 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.
list_catalog is provided by the Ilumin MCP server (ilumin-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.