diff --git a/docs/webui.md b/docs/webui.md
index f6efd3e0..ab9e0adc 100644
--- a/docs/webui.md
+++ b/docs/webui.md
@@ -187,6 +187,11 @@ extraction tools without requiring an API key. This does not replace nanobot's
 built-in web search provider; mention the Firecrawl MCP preset with `@` when a
 turn needs Firecrawl's richer web data tools.
 
+The Parallel Search preset connects to the free, anonymous Parallel Search MCP
+endpoint and exposes `web_search` and `web_fetch` without requiring an API key.
+It is an optional integration and does not replace nanobot's built-in web search
+provider; mention `@parallel-search` when a turn should use it.
+
 After an App or integration is available, mention it from the composer with
 `@` to attach that tool to the next message.
 
diff --git a/nanobot/webui/mcp_presets_api.py b/nanobot/webui/mcp_presets_api.py
index 5c3f31b8..0521848f 100644
--- a/nanobot/webui/mcp_presets_api.py
+++ b/nanobot/webui/mcp_presets_api.py
@@ -188,6 +188,25 @@ MCP_PRESETS: tuple[McpPreset, ...] = (
             "the built-in preset; use a custom MCP server URL if you want account-specific limits."
         ),
     ),
+    McpPreset(
+        name="parallel-search",
+        display_name="Parallel Search",
+        category="web",
+        description="Search the web and fetch relevant page content through Parallel's hosted MCP server.",
+        docs_url="https://docs.parallel.ai/integrations/mcp/search-mcp",
+        transport="streamableHttp",
+        install_supported=True,
+        brand_domain="parallel.ai",
+        brand_color="#111827",
+        requires="Network access",
+        server=MCPServerConfig(
+            type="streamableHttp",
+            url="https://search.parallel.ai/mcp",
+            tool_timeout=60,
+            enabled_tools=["web_search", "web_fetch"],
+        ),
+        note="Free anonymous access for light use; no API key is required.",
+    ),
     McpPreset(
         name="exa",
         display_name="Exa",
diff --git a/tests/webui/test_mcp_presets_api.py b/tests/webui/test_mcp_presets_api.py
index f1bd12e0..e2a2a668 100644
--- a/tests/webui/test_mcp_presets_api.py
+++ b/tests/webui/test_mcp_presets_api.py
@@ -32,6 +32,7 @@ def test_mcp_presets_payload_lists_supported_cards(tmp_path, monkeypatch: pytest
         "figma",
         "context7",
         "firecrawl",
+        "parallel-search",
         "exa",
         "microsoft-learn",
         "aws-docs",
@@ -136,11 +137,13 @@ def test_enable_no_auth_remote_presets_write_url(tmp_path, monkeypatch: pytest.M
     mcp_presets_action("enable", {"name": ["microsoft-learn"]})
     mcp_presets_action("enable", {"name": ["exa"]})
     mcp_presets_action("enable", {"name": ["firecrawl"]})
+    mcp_presets_action("enable", {"name": ["parallel-search"]})
 
     config = load_config()
     assert config.tools.mcp_servers["microsoft-learn"].url == "https://learn.microsoft.com/api/mcp"
     assert config.tools.mcp_servers["exa"].url == "https://mcp.exa.ai/mcp"
     assert config.tools.mcp_servers["firecrawl"].url == "https://mcp.firecrawl.dev/v2/mcp"
+    assert config.tools.mcp_servers["parallel-search"].url == "https://search.parallel.ai/mcp"
 
 
 def test_firecrawl_preset_is_keyless(tmp_path, monkeypatch: pytest.MonkeyPatch) -> None:
@@ -160,6 +163,28 @@ def test_firecrawl_preset_is_keyless(tmp_path, monkeypatch: pytest.MonkeyPatch)
     assert config.tools.mcp_servers["firecrawl"].env == {}
 
 
+def test_parallel_search_preset_is_keyless_and_tool_limited(
+    tmp_path,
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    _use_config(tmp_path, monkeypatch)
+
+    payload = mcp_presets_action("enable", {"name": ["parallel-search"]})
+
+    row = next(item for item in payload["presets"] if item["name"] == "parallel-search")
+    assert row["transport"] == "streamableHttp"
+    assert row["requires"] == "Network access"
+    assert row["required_fields"] == []
+    assert row["configured"] is True
+    assert "no API key" in row["note"]
+    config = load_config()
+    server = config.tools.mcp_servers["parallel-search"]
+    assert server.type == "streamableHttp"
+    assert server.url == "https://search.parallel.ai/mcp"
+    assert server.enabled_tools == ["web_search", "web_fetch"]
+    assert server.headers == {}
+
+
 def test_remove_mcp_preset_updates_config(tmp_path, monkeypatch: pytest.MonkeyPatch) -> None:
     _use_config(tmp_path, monkeypatch)
     mcp_presets_action("enable", {"name": ["playwright"]})