diff --git a/backend/app/core/config.py b/backend/app/core/config.py
index 8fd6e4a8..f1b0edc2 100644
--- a/backend/app/core/config.py
+++ b/backend/app/core/config.py
@@ -84,6 +84,9 @@ class Settings(BaseSettings):
     AI_MODEL_GEMINI: str = "gemini-2.5-flash"
     AI_MODEL_ANTHROPIC: str = "claude-haiku-4-5-20251001"
 
+    # MCP (Model Context Protocol) integrations
+    ENABLE_MCP_MICROSOFT_LEARN: bool = True
+
     # Embedding / RAG
     VOYAGE_API_KEY: Optional[str] = None
     EMBEDDING_MODEL: str = "voyage-3.5"
diff --git a/backend/app/services/assistant_chat_service.py b/backend/app/services/assistant_chat_service.py
index 275db947..20160cea 100644
--- a/backend/app/services/assistant_chat_service.py
+++ b/backend/app/services/assistant_chat_service.py
@@ -7,6 +7,9 @@ Uses Anthropic prompt caching to reduce cost on multi-turn conversations:
 - The static system prompt is cached (ephemeral, 5-min TTL)
 - The conversation history prefix is cached via a breakpoint on the
   last existing message before the new user input
+
+Optionally connects to Microsoft Learn via Anthropic's MCP connector
+for real-time documentation lookups (controlled by ENABLE_MCP_MICROSOFT_LEARN).
 """
 import logging
 from typing import Any
@@ -21,20 +24,49 @@ from app.services.rag_service import search as rag_search, build_rag_context, ex
 
 logger = logging.getLogger(__name__)
 
-ASSISTANT_SYSTEM_PROMPT = """You are a Senior Systems and Network Engineer with 15+ years of experience working in Managed Service Provider (MSP) environments. You specialize in:
-- Windows Server, Active Directory, Group Policy, and Hybrid Identity (Entra ID)
-- Networking (TCP/IP, DNS, DHCP, VPN, firewall troubleshooting, Cisco/Fortinet)
-- Virtualization (VMware, Hyper-V) and cloud platforms (Azure, AWS, M365)
-- Endpoint management, RMM tools, and PSA platforms (ConnectWise, Datto, Kaseya)
-- PowerShell scripting and automation
+ASSISTANT_SYSTEM_PROMPT = """\
+You are ResolutionFlow Assistant — an expert IT systems engineer embedded in a \
+troubleshooting platform built for Managed Service Provider (MSP) teams.
 
-When answering:
-- Be direct and actionable — MSP engineers need fast, practical answers
-- Include specific commands, paths, and config values when relevant
-- Mention potential risks or gotchas before suggesting changes
-- If a relevant troubleshooting flow exists in the team's library, reference it
-- Keep responses concise but thorough — prefer bullet points and code blocks
-- Format code with proper markdown code blocks
+## Your Role
+You are a senior peer helping fellow MSP engineers solve problems fast. You have \
+deep expertise across the MSP technology stack:
+- Windows Server, Active Directory, Group Policy, Hybrid Identity (Entra ID / Azure AD)
+- Networking: TCP/IP, DNS, DHCP, VPN, firewalls (Cisco, Fortinet, Meraki, SonicWall)
+- Virtualization: VMware vSphere, Hyper-V, Proxmox
+- Cloud platforms: Microsoft 365, Azure, AWS
+- Endpoint management, RMM tools, and PSA platforms (ConnectWise, Datto, Kaseya, NinjaRMM)
+- PowerShell scripting and automation
+- Security: MFA, Conditional Access, EDR, backup/DR
+
+## How to Answer
+- **Be direct and actionable.** Engineers are mid-ticket — give them the answer, \
+not a lecture. Lead with the fix, then explain why.
+- **Include specifics.** Exact commands, registry paths, config values, port numbers. \
+Vague advice wastes time.
+- **Warn before you wreck.** If a step could cause downtime, data loss, or a lockout, \
+say so upfront — before the command.
+- **Use structured formatting.** Bullet points for steps, code blocks for commands, \
+bold for key terms. Engineers scan, they don't read essays.
+- **Say when you're unsure.** If you don't know the exact answer, say so. Suggest \
+where to verify (vendor docs, a specific KB article) rather than guessing.
+
+## Using the Team's Flow Library
+Your team has built troubleshooting flows in ResolutionFlow. When relevant flows \
+appear in the context below, reference them by name so the engineer can launch them \
+directly. Prefer the team's proven flows over ad-hoc instructions when they exist.
+
+## Using Microsoft Learn Documentation
+You have access to Microsoft's official documentation via Microsoft Learn. Use it when:
+- The question involves exact cmdlet syntax, API parameters, or configuration steps
+- You need to verify current Microsoft/Azure behavior or requirements
+- No team flow covers the topic and vendor-specific detail would help
+Do NOT use Microsoft Learn for every question — only when official docs add real value.
+
+## Boundaries
+- Stay focused on IT infrastructure, systems administration, and MSP operations.
+- If a question is clearly outside your domain, say so briefly and redirect.
+- Never fabricate error codes, KB article numbers, or CLI flags. If unsure, say so.
 """
 
 
@@ -81,7 +113,8 @@ async def _call_anthropic_cached(
     """Call Anthropic with prompt caching on system prompt and history.
 
     Uses structured system blocks so the static base prompt is cached
-    independently from the per-query RAG context.
+    independently from the per-query RAG context. Optionally connects
+    to Microsoft Learn via MCP for real-time documentation lookups.
     """
     import anthropic
 
@@ -126,18 +159,55 @@ async def _call_anthropic_cached(
     # Add the new user message (uncached — it's new each turn)
     messages.append({"role": "user", "content": new_message})
 
-    response = await client.messages.create(
+    # MCP server config (optional — controlled by settings)
+    mcp_servers = anthropic.NOT_GIVEN
+    tools = anthropic.NOT_GIVEN
+
+    if settings.ENABLE_MCP_MICROSOFT_LEARN:
+        mcp_servers = [
+            {
+                "type": "url",
+                "url": "https://learn.microsoft.com/api/mcp",
+                "name": "microsoft-learn",
+            }
+        ]
+        tools = [
+            {
+                "type": "mcp_toolset",
+                "mcp_server_name": "microsoft-learn",
+            }
+        ]
+
+    response = await client.beta.messages.create(
         model=settings.AI_MODEL_ANTHROPIC,
         max_tokens=max_tokens,
         system=system_blocks,
         messages=messages,
+        mcp_servers=mcp_servers,
+        tools=tools,
+        betas=["mcp-client-2025-11-20"],
     )
 
-    text = response.content[0].text
+    # Extract text from response — MCP responses can have multiple block
+    # types (text, mcp_tool_use, mcp_tool_result). We join all text blocks.
+    text_parts = []
+    mcp_tools_used = []
+    for block in response.content:
+        if hasattr(block, "text"):
+            text_parts.append(block.text)
+        if getattr(block, "type", None) == "mcp_tool_use":
+            mcp_tools_used.append(getattr(block, "name", "unknown"))
+
+    text = "\n".join(text_parts) if text_parts else ""
+
     usage = response.usage
     input_tokens = usage.input_tokens
     output_tokens = usage.output_tokens
 
+    # Log MCP tool usage
+    if mcp_tools_used:
+        logger.info("MCP tools used: %s", ", ".join(mcp_tools_used))
+
     # Log cache performance
     cache_read = getattr(usage, "cache_read_input_tokens", 0) or 0
     cache_creation = getattr(usage, "cache_creation_input_tokens", 0) or 0