search_comments
AI agents call search_comments to retrieve information from Firebase DAM MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The server is explicitly described as read-only, and all sibling tools are search/read operations. 'search_comments' aligns with the pattern of querying comment data. The empty description lowers confidence slightly, but the server context strongly implies a read-only query operation.
From the tool's definition Tool name 'search_comments' on a server described as 'read-only access' for querying 'assets, versions, and comments' via 'flexible filters'. Sibling tools are all search/query tools.
Attacks that exploit this kind of access
search_comments. It is categorised as a Read tool in the Firebase DAM MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Firebase DAM MCP Server MCP server in PolicyLayer and add a rule for search_comments: 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 Firebase DAM MCP Server. Nothing to install.
search_comments 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_comments 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_comments. 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_comments is provided by the Firebase DAM MCP Server MCP server (lt012071/dam-firebase-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 →