AI agents call get_rfc_dependencies to retrieve information from Rfcxml without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and queries information about RFC dependencies—it has no side effects, does not modify data, execute code, delete anything, or move money. It is a classic Read operation: fetching structured metadata about document relationships. The low severity reflects minimal risk even if misused, as the output is informational only.
From the tool's definition The tool 'get_rfc_dependencies' retrieves RFC reference relationships (normative/informative dependencies). It uses the verb 'Get' and the description indicates it reads or queries data about relationships between RFCs without modifying or executing anything.
Attacks that exploit this kind of access
Get RFC reference relationships (normative/informative). It is categorised as a Read tool in the Rfcxml MCP Server, which means it retrieves data without modifying state.
Register the Rfcxml MCP server in PolicyLayer and add a rule for get_rfc_dependencies: 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 Rfcxml. Nothing to install.
get_rfc_dependencies 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_rfc_dependencies 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_rfc_dependencies. 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_rfc_dependencies is provided by the Rfcxml MCP server (shuji-bonji/rfcxml-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 →