List the source documents available in the knowledge base.
AI agents call kb_sources to retrieve information from Halyard Knowledge Base MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a query-only action to enumerate available documentation sources. It retrieves metadata about what documents exist in the knowledge base without modifying, deleting, executing code, or performing financial operations. The minimal blast radius of misuse is an attacker learning what documentation is available—a read-only concern.
From the tool's definition Tool name 'kb_sources' and description 'List the source documents available in the knowledge base' indicate a retrieval/listing operation with no side effects.
Attacks that exploit this kind of access
List the source documents available in the knowledge base. It is categorised as a Read tool in the Halyard Knowledge Base MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Halyard Knowledge Base MCP Server MCP server in PolicyLayer and add a rule for kb_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 Halyard Knowledge Base MCP Server. Nothing to install.
kb_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 kb_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 kb_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.
kb_sources is provided by the Halyard Knowledge Base MCP Server MCP server (mqfarooqi1/agentic-rag-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 →