Fetch the full text of a single chunk by its chunk_id (e.g. 'faq.md#1').
AI agents call kb_fetch 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.
kb_fetch retrieves and returns existing documentation content by chunk_id. It performs a query operation with no ability to create, modify, delete, or execute code. The blast radius of misuse is minimal—an agent could only over-fetch or enumerate chunks, not cause data loss or execute arbitrary operations. This is a straightforward Read operation.
From the tool's definition Tool description states 'Fetch the full text of a single chunk' — a retrieval operation with no modification or side effects. Sibling tools (kb_search, kb_sources) confirm this is part of a read-only RAG pipeline.
Attacks that exploit this kind of access
Fetch the full text of a single chunk by its chunk_id (e.g. 'faq.md#1'). 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_fetch: 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_fetch 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_fetch 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_fetch. 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_fetch 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 →