docs: adds a subsection for mcp guardrails

docs/enterprise/guardrails.mdx

@@ -114,7 +114,7 @@ Both targets also expose `headers`, `virtual_key`, `customer`, `team`, and `user
 
 ### Architecture
 
-The following diagram illustrates how Rules and Profiles work together for the LLM target. MCP rules use the same rule/profile evaluation around tool execution: input guardrails run before the tool and output guardrails run after the result.
+The following diagram illustrates how Rules and Profiles work together for the LLM target. For tool execution, see [MCP Guardrails](#mcp-guardrails).
 
 ```mermaid
 flowchart TB
@@ -174,6 +174,38 @@ flowchart TB
 
 ---
 
+## MCP Guardrails
+
+MCP guardrails protect the actual tool-execution boundary, not merely the tool call proposed by an LLM.
+
+After the rule's CEL expression matches, Bifrost applies the selected phase:
+
+| Apply on | Flow |
+|----------|------|
+| **Before tool call** (`input`) | Inspect arguments → allow or redact and execute; **block → stop before execution** |
+| **After tool result** (`output`) | Execute tool → inspect a successful text-bearing result → allow or redact and return; **block → do not return the result** |
+| **Both** (`both`) | Run the input flow; if allowed, execute the tool and run the output flow. A block at either boundary stops processing |
+
+<Frame>
+  <img src="/media/guardrails/ui-mcp-guardrail-rule.png" alt="MCP guardrail rule editor showing the MCP target, before and after execution phases, a linked profile, and MCP client and tool conditions" />
+</Frame>
+
+### Choose Which Tool Calls to Guard
+
+- **MCP Client** is populated from configured clients that are enabled.
+- **MCP Tool** is populated from their currently discovered tools.
+- **Tool Argument** shows a searchable dropdown of top-level string, number, and boolean input-schema fields when one MCP tool is selected with the `=` operator. You can also enter an argument name manually.
+
+MCP rules can additionally use the shared identity fields listed under [Guardrail Targets](#guardrail-targets).
+
+<Note>
+All supported guardrail providers can be linked to MCP rules without separate MCP-specific provider setup. Provider capabilities still apply: only providers listed in [Guardrail Redaction](/enterprise/guardrails/redaction) support Bifrost-managed redaction, while other providers may detect, block, or return provider-managed transformations.
+</Note>
+
+MCP rules use the same linked profiles, sampling, and timeout settings as LLM rules. See [Creating Rules](#creating-rules) for configuration and [CEL Expression Examples](#cel-expression-examples) for targeting examples.
+
+---
+
 ## Streaming Output Guardrails
 
 Streaming delivery depends on what the matched output guardrails can do: