AI agents call get_sources to retrieve information from Mcp Nexus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves previously cached search results using a session identifier. It performs a read-only query operation with no capability to modify, delete, execute code, or trigger external operations. The low severity reflects minimal blast radius — an AI agent misusing this would only access cached search metadata, not sensitive data creation or destruction.
From the tool's definition Tool name 'get_sources' with description 'Fetch source list cached from a previous web_search call' — uses 'Fetch' and retrieves already-cached data without modification or side effects.
Attacks that exploit this kind of access
Fetch source list cached from a previous web_search call using session_id. It is categorised as a Read tool in the Mcp Nexus MCP Server, which means it retrieves data without modifying state.
Register the Mcp Nexus MCP server in PolicyLayer and add a rule for get_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 Mcp Nexus. Nothing to install.
get_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 get_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 get_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.
get_sources is provided by the Mcp Nexus MCP server (xydong-web/mcp-nexus). 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 →