diff --git a/strix/agents/prompts/system_prompt.jinja b/strix/agents/prompts/system_prompt.jinja
index 9ea8121a..b1a574bc 100644
--- a/strix/agents/prompts/system_prompt.jinja
+++ b/strix/agents/prompts/system_prompt.jinja
@@ -78,6 +78,13 @@ AUTHORIZED TARGETS:
 {% if system_prompt_context and system_prompt_context.mcp_available %}
 MCP CONNECTIONS (available this run):
 - The user connected one or more MCP (Model Context Protocol) servers — external tool providers you can reach on demand. Their individual tools do NOT appear in your tool list; three dispatch tools are the only way in.
+{% if system_prompt_context.mcp_connections %}
+- Connected this run (call describe_mcp on one to see its tools):
+{% for connection in system_prompt_context.mcp_connections %}
+  - {{ connection.name }} ({{ connection.tool_count }} tools){% if connection.purpose %}: {{ connection.purpose }}{% endif %}
+{% endfor %}
+{% endif %}
+- Reach for a connection whenever the target itself cannot give you information a connection could: its database schema and access policies, real deployment or infrastructure configuration, known issues or prior findings, or server logs. In those cases call list_mcps early to see what is available, and prefer a connection's authoritative data over inferring from the target's responses. Do not wait to be told a connection exists.
   1. Call list_mcps() to discover the available connections.
   2. Call describe_mcp(connection="<name>") to inspect one connection's tools, each with its name, description, and JSON input schema.
   3. Call call_mcp(connection="<name>", tool="<tool>", arguments={...}) to run one, passing an arguments object that matches the schema (omit arguments for a tool that takes none).
diff --git a/strix/core/runner.py b/strix/core/runner.py
index fd347f24..6b79b91a 100644
--- a/strix/core/runner.py
+++ b/strix/core/runner.py
@@ -370,13 +370,21 @@ async def run_strix_scan(
                 _record_mcp_connections(connections)
                 if connections:
                     report(_mcp_startup_summary(connections))
-                    # Flag that MCP is reachable so both the root context and the
-                    # child factory's context (both derive from scope_context)
-                    # render the static three-tool guidance. Set only when a
-                    # connection exists, so a run with no MCP leaves the prompt
-                    # context unchanged. The connections themselves are discovered
-                    # at run time via list_mcps, not listed in the prompt.
+                    # Name the connected servers in the prompt so every agent
+                    # (root and children, both deriving from scope_context) sees
+                    # what is available at the start; they can still re-list or
+                    # inspect them at run time via list_mcps / describe_mcp. Set
+                    # only when a connection exists, so a run with no MCP leaves
+                    # the prompt context unchanged.
                     scope_context["mcp_available"] = bool(mcp_registry)
+                    scope_context["mcp_connections"] = [
+                        {
+                            "name": summary.name,
+                            "purpose": summary.purpose,
+                            "tool_count": summary.tool_count,
+                        }
+                        for summary in mcp_registry.summaries()
+                    ]
         except Exception:
             logger.exception("Failed to connect user MCP servers; continuing without them")
 
diff --git a/tests/test_mcp_client.py b/tests/test_mcp_client.py
index 7b7919e9..069b9604 100644
--- a/tests/test_mcp_client.py
+++ b/tests/test_mcp_client.py
@@ -648,21 +648,36 @@ def test_prompt_has_no_mcp_section_without_availability() -> None:
     assert "MCP CONNECTIONS" not in render_system_prompt(system_prompt_context={})
 
 
-def test_prompt_no_longer_renders_a_per_connection_inventory() -> None:
-    """The old inventory loop read ``mcp_connections`` and listed each connection
-    with its purpose. That data no longer drives the prompt; only the boolean
-    ``mcp_available`` does, so a legacy ``mcp_connections`` list renders nothing."""
+def test_prompt_renders_named_connection_inventory() -> None:
+    """With mcp_available set, the prompt names each connected server (name, tool
+    count, purpose) so every agent sees what is available at the start, alongside
+    the three dispatch tools for re-listing and inspecting them at run time."""
     prompt = render_system_prompt(
         system_prompt_context={
+            "mcp_available": True,
             "mcp_connections": [
-                {"name": "secret-conn", "purpose": "should not appear", "tool_count": 3}
-            ]
+                {"name": "supabase", "purpose": "read the app's schema", "tool_count": 13}
+            ],
+        }
+    )
+
+    assert "MCP CONNECTIONS" in prompt
+    assert "supabase" in prompt
+    assert "13 tools" in prompt
+    assert "read the app's schema" in prompt
+
+
+def test_prompt_inventory_is_gated_on_availability() -> None:
+    """The block is gated on ``mcp_available``; an ``mcp_connections`` payload
+    without it renders nothing, so a stale or spoofed list cannot leak names."""
+    prompt = render_system_prompt(
+        system_prompt_context={
+            "mcp_connections": [{"name": "secret-conn", "purpose": "x", "tool_count": 3}]
         }
     )
 
     assert "MCP CONNECTIONS" not in prompt
     assert "secret-conn" not in prompt
-    assert "should not appear" not in prompt
 
 
 # --- loader ------------------------------------------------------------------
diff --git a/tests/test_runner_root_prompt.py b/tests/test_runner_root_prompt.py
index e33bf254..1bea19c2 100644
--- a/tests/test_runner_root_prompt.py
+++ b/tests/test_runner_root_prompt.py
@@ -187,9 +187,10 @@ async def test_mcp_available_flag_set_when_a_connection_attaches(
     monkeypatch: pytest.MonkeyPatch,
     tmp_path: Any,
 ) -> None:
-    """When at least one MCP connection attaches, the runner sets the boolean
-    ``mcp_available`` (not a per-connection inventory) into the scan context that
-    reaches every agent."""
+    """When at least one MCP connection attaches, the runner sets ``mcp_available``
+    plus a named ``mcp_connections`` inventory into the scan context that reaches
+    every agent, so each agent sees which connections exist at the start while
+    still being able to re-list them at run time via list_mcps."""
     scope_context: dict[str, Any] = {"scope": "built-in"}
     captured = _patch_engine_scaffold(monkeypatch, tmp_path, scope_context)
 
@@ -217,8 +218,10 @@ async def test_mcp_available_flag_set_when_a_connection_attaches(
 
     kwargs = captured["kwargs"]
     assert kwargs["system_prompt_context"]["mcp_available"] is True
-    # The old per-connection inventory key is gone entirely.
-    assert "mcp_connections" not in kwargs["system_prompt_context"]
+    # The named inventory names each connected server for the prompt.
+    assert kwargs["system_prompt_context"]["mcp_connections"] == [
+        {"name": "fs", "purpose": "local files", "tool_count": 2}
+    ]
 
 
 @pytest.mark.asyncio