discover_sources
AI agents call discover_sources to retrieve information from Asset Aware without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'discover_sources' most naturally suggests searching, listing, or querying available sources within the knowledge graph or document repository. Despite the empty description reducing confidence slightly, the server context (asset retrieval, knowledge graph integration, and sibling tools that are read-like) strongly indicates this performs read-only data discovery without modification, deletion, or…
From the tool's definition Tool name 'discover_sources' combined with server purpose of 'retrieve and analyze PDF assets' and 'knowledge graph integration' indicates a discovery/retrieval function. No description provided.
Attacks that exploit this kind of access
discover_sources. It is categorised as a Read tool in the Asset Aware MCP Server, which means it retrieves data without modifying state.
Register the Asset Aware MCP server in PolicyLayer and add a rule for discover_sources: 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 Asset Aware. Nothing to install.
discover_sources 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 discover_sources 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 discover_sources. 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.
discover_sources is provided by the Asset Aware MCP server (u9401066/asset-aware-mcp). 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 →