Fetch a local indexed section/chunk by chunk_id.
AI agents call get_doc_section to retrieve information from UserGate MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves documentation content from a local indexed corpus without any capability to modify, delete, or execute operations. It is a straightforward data retrieval function grounded in read-only access to offline documentation. The blast radius of misuse is minimal - an agent could retrieve documentation inappropriately but cannot alter system state or trigger external operations.
From the tool's definition Tool description states 'Fetch a local indexed section/chunk by chunk_id' - a retrieval operation with no modification capability. The verb 'Fetch' indicates a read-only operation on local documentation.
Attacks that exploit this kind of access
Fetch a local indexed section/chunk by chunk_id. It is categorised as a Read tool in the UserGate MCP MCP Server, which means it retrieves data without modifying state.
Register the UserGate MCP server in PolicyLayer and add a rule for get_doc_section: 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 UserGate MCP. Nothing to install.
get_doc_section 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_doc_section 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_doc_section. 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_doc_section is provided by the UserGate MCP server (neonsummit/usergate-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 →