Skip to content

MCP Client MRTR Conformance (inputRequests Provenance Boundary and the resultType Default)

mcp-client-mrtr-conformance is a high severity check in the ai category, written in python. Its source is templates/ai/mcp/client-conformance/mcp-client-mrtr-conformance.py in cert-x-gen-templates.

ACTIVE check. Drives an MCP CLIENT against one benign synthetic MCP server and proves, by observation, that it fails two 2026-07-28 client MUSTs - it lets a server-supplied inputRequests prompt cross into its own context or its own actions with nothing naming where the text came from, and it does not treat a result with an absent resultType as "complete".

Field Value
Id mcp-client-mrtr-conformance
Severity high
Language python
Category ai
Author Bugb Research
Template version 1.0.0
Confidence 90
CVSS 8.2
Weakness CWE-346, CWE-1289
Tags mcp, ai, agent, mcp-client, mcp-client-conformance, agent-posture, mrtr, input-requests, elicitation, prompt-injection, provenance, result-type, behavioural, active, intrusive, cwe-346, cwe-1289
Target kind cli
Oracle property, diff

Declared in the header. cxg parses @references and then discards it, and nothing at scan time reads it, so this is the only place the links a template cites are surfaced.

To see what the copy on your machine says about itself, and to confirm it is installed at all:

Terminal window
cxg template info mcp-client-mrtr-conformance

The id it prints is the one to pass anywhere a template is selected. See cxg template for the rest of the subcommand, Scan a target for running a scan, and A match is not a finding for how to read what comes back.