List library entities (projects, collections, resources, lineage, brand_kits). **Entity Types:** - projects: User's projects with stats and metadata - collections: Collections within a project - resources: Media resources (images, videos, audio) - lineage: Resource derivation history - brand_kit...
High parameter count (25 properties)
Part of the Soundside-ai MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call lib_list to retrieve information from Soundside-ai 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 lib_list 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:
lib_list:
rules:
- action: allowSee the full Soundside-ai policy for all 12 tools.
Agents calling read-class tools like lib_list 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.
List library entities (projects, collections, resources, lineage, brand_kits). **Entity Types:** - projects: User's projects with stats and metadata - collections: Collections within a project - resources: Media resources (images, videos, audio) - lineage: Resource derivation history - brand_kits: User's brand kits for artifact styling **Common Parameters:** - project_id: Filter by project UUID - collection_id: Filter by collection UUID - include_stats: Include counts and sizes (default: true) - limit/offset: Pagination - sort_by: Field to sort by (created_at, name, size_bytes) **Example (list resources in collection):** ```json { "entity_type": "resources", "collection_id": "collection-uuid", "mime_type_prefix": "video/", "limit": 50 } ``` **Example (list project collections):** ```json { "entity_type": "collections", "project_id": "project-uuid", "include_resources": true } ``` **Example (search resources by tag):** ```json { "entity_type": "resources", "project_id": "project-uuid", "tags": ["storyboard", "scene-1"] } ```. It is categorised as a Read tool in the Soundside-ai MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for lib_list. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Soundside-ai MCP server.
lib_list 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 lib_list 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 lib_list. 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.
lib_list is provided by the Soundside-ai MCP server (kangaroo-Ifly/soundside-ai). 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.