Update README

.dockerignore

@@ -0,0 +1,9 @@
+.git/
+.venv/
+.ruff_cache/
+__pycache__/
+*.pyc
+.env
+agent.py
+AGENTS.md
+README.md

.gitignore

@@ -0,0 +1,216 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

Dockerfile

@@ -0,0 +1,25 @@
+FROM python:3.12-slim AS builder
+
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /usr/local/bin/
+
+WORKDIR /app
+
+COPY pyproject.toml uv.lock ./
+RUN uv sync --no-dev --frozen --no-install-project
+
+COPY main.py .
+
+FROM python:3.12-slim
+
+WORKDIR /app
+
+COPY --from=builder /app /app
+
+ENV PATH="/app/.venv/bin:$PATH"
+
+# Cloud Run injects PORT (defaults to 8080)
+ENV PORT=8080
+EXPOSE ${PORT}
+
+# Shell form so ${PORT} is expanded at runtime
+CMD python main.py --transport sse --port ${PORT}

README.md

@@ -0,0 +1,87 @@
+# knowledge-search-mcp
+
+An MCP (Model Context Protocol) server that exposes a `knowledge_search` tool for semantic search over a knowledge base backed by Vertex AI Vector Search and Google Cloud Storage.
+
+## How it works
+
+1. A natural-language query is embedded using a Gemini embedding model.
+2. The embedding is sent to a Vertex AI Matching Engine index endpoint to find nearest neighbors.
+3. The matched document contents are fetched from a GCS bucket and returned to the caller.
+
+## Prerequisites
+
+- Python ≥ 3.12
+- [uv](https://docs.astral.sh/uv/) for dependency management
+- A Google Cloud project with:
+  - A Vertex AI Vector Search index and deployed endpoint
+  - A GCS bucket containing the indexed document chunks
+  - Application Default Credentials (or a service account) with appropriate permissions
+
+## Configuration
+
+Create a `.env` file (see `Settings` in `main.py` for all options):
+
+```env
+PROJECT_ID=my-gcp-project
+LOCATION=us-central1
+BUCKET=my-knowledge-bucket
+INDEX_NAME=my-index
+DEPLOYED_INDEX_ID=my-deployed-index
+ENDPOINT_NAME=projects/…/locations/…/indexEndpoints/…
+ENDPOINT_DOMAIN=123456789.us-central1-aiplatform.googleapis.com
+# optional
+EMBEDDING_MODEL=gemini-embedding-001
+SEARCH_LIMIT=10
+```
+
+## Usage
+
+### Install dependencies
+
+```bash
+uv sync
+```
+
+### Run the MCP server (stdio)
+
+```bash
+uv run python main.py
+```
+
+### Run the MCP server (SSE, e.g. for remote clients)
+
+```bash
+uv run python main.py --transport sse --port 8080
+```
+
+### Run the interactive agent (ADK)
+
+The bundled agent spawns the MCP server as a subprocess and provides a REPL:
+
+```bash
+uv run python agent.py
+```
+
+Or connect to an already-running SSE server:
+
+```bash
+uv run python agent.py --remote http://localhost:8080/sse
+```
+
+## Docker
+
+```bash
+docker build -t knowledge-search-mcp .
+docker run -p 8080:8080 --env-file .env knowledge-search-mcp
+```
+
+The container starts the server in SSE mode on the port specified by `PORT` (default `8080`).
+
+## Project structure
+
+```
+main.py          MCP server, vector search client, and GCS storage helper
+agent.py         Interactive ADK agent that consumes the MCP server
+Dockerfile       Multi-stage build for Cloud Run / containerized deployment
+pyproject.toml   Project metadata and dependencies
+```

agent.py

@@ -0,0 +1,111 @@
+# ruff: noqa: INP001
+"""ADK agent that connects to the knowledge-search MCP server."""
+
+import argparse
+import asyncio
+import os
+
+from google.adk.agents.llm_agent import LlmAgent
+from google.adk.runners import Runner
+from google.adk.sessions import InMemorySessionService
+from google.adk.tools.mcp_tool import McpToolset
+from google.adk.tools.mcp_tool.mcp_session_manager import (
+    SseConnectionParams,
+    StdioConnectionParams,
+)
+from google.genai import types
+from mcp import StdioServerParameters
+
+# ADK needs these env vars for Vertex AI; reuse the ones from .env
+os.environ.setdefault("GOOGLE_GENAI_USE_VERTEXAI", "True")
+if project := os.environ.get("PROJECT_ID"):
+    os.environ.setdefault("GOOGLE_CLOUD_PROJECT", project)
+if location := os.environ.get("LOCATION"):
+    os.environ.setdefault("GOOGLE_CLOUD_LOCATION", location)
+
+SERVER_SCRIPT = os.path.join(os.path.dirname(os.path.abspath(__file__)), "main.py")
+
+
+def _parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description="Knowledge Search Agent")
+    parser.add_argument(
+        "--remote",
+        metavar="URL",
+        help="Connect to an already-running MCP server at this SSE URL "
+        "(e.g. http://localhost:8080/sse). Without this flag the agent "
+        "spawns the server as a subprocess.",
+    )
+    return parser.parse_args()
+
+
+async def async_main() -> None:
+    args = _parse_args()
+
+    if args.remote:
+        connection_params = SseConnectionParams(url=args.remote)
+    else:
+        connection_params = StdioConnectionParams(
+            server_params=StdioServerParameters(
+                command="uv",
+                args=["run", "python", SERVER_SCRIPT],
+            ),
+        )
+
+    toolset = McpToolset(connection_params=connection_params)
+
+    agent = LlmAgent(
+        model="gemini-2.0-flash",
+        name="knowledge_agent",
+        instruction=(
+            "You are a helpful assistant with access to a knowledge base. "
+            "Use the knowledge_search tool to find relevant information "
+            "when the user asks questions. Summarize the results clearly."
+        ),
+        tools=[toolset],
+    )
+
+    session_service = InMemorySessionService()
+    session = await session_service.create_session(
+        state={},
+        app_name="knowledge_agent",
+        user_id="user",
+    )
+
+    runner = Runner(
+        app_name="knowledge_agent",
+        agent=agent,
+        session_service=session_service,
+    )
+
+    print("Knowledge Search Agent ready. Type your query (Ctrl+C to exit):")
+    try:
+        while True:
+            try:
+                query = input("\n> ").strip()
+            except EOFError:
+                break
+            if not query:
+                continue
+
+            content = types.Content(
+                role="user",
+                parts=[types.Part(text=query)],
+            )
+
+            async for event in runner.run_async(
+                session_id=session.id,
+                user_id=session.user_id,
+                new_message=content,
+            ):
+                if event.is_final_response() and event.content and event.content.parts:
+                    for part in event.content.parts:
+                        if part.text:
+                            print(part.text)
+    except KeyboardInterrupt:
+        print("\nShutting down...")
+    finally:
+        await toolset.close()
+
+
+if __name__ == "__main__":
+    asyncio.run(async_main())

main.py

@@ -1,6 +1,7 @@
 # ruff: noqa: INP001
 """Async helpers for querying Vertex AI vector search via MCP."""
 
+import argparse
 import asyncio
 import io
 import logging
@@ -244,7 +245,10 @@ class GoogleCloudVectorSearch:
             json=payload,
             headers=headers,
         ) as response:
-            response.raise_for_status()
+            if not response.ok:
+                body = await response.text()
+                msg = f"findNeighbors returned {response.status}: {body}"
+                raise RuntimeError(msg)
             data = await response.json()
 
         neighbors = data.get("nearestNeighbors", [{}])[0].get("neighbors", [])
@@ -281,6 +285,8 @@ class GoogleCloudVectorSearch:
 class Settings(BaseSettings):
     """Server configuration populated from environment variables."""
 
+    model_config = {"env_file": ".env"}
+
     project_id: str
     location: str
     bucket: str
@@ -288,7 +294,7 @@ class Settings(BaseSettings):
     deployed_index_id: str
     endpoint_name: str
     endpoint_domain: str
-    embedding_model: str = "text-embedding-005"
+    embedding_model: str = "gemini-embedding-001"
     search_limit: int = 10
 
 
@@ -330,7 +336,26 @@ async def lifespan(_server: FastMCP) -> AsyncIterator[AppContext]:
     )
 
 
-mcp = FastMCP("knowledge-search", lifespan=lifespan)
+def _parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--transport",
+        choices=["stdio", "sse"],
+        default="stdio",
+    )
+    parser.add_argument("--host", default="0.0.0.0")
+    parser.add_argument("--port", type=int, default=8080)
+    return parser.parse_args()
+
+
+_args = _parse_args()
+
+mcp = FastMCP(
+    "knowledge-search",
+    host=_args.host,
+    port=_args.port,
+    lifespan=lifespan,
+)
 
 
 @mcp.tool()
@@ -359,6 +384,7 @@ async def knowledge_search(
         contents=query,
         config=genai_types.EmbedContentConfig(
             task_type="RETRIEVAL_QUERY",
+
         ),
     )
     embedding = response.embeddings[0].values
@@ -398,4 +424,4 @@ async def knowledge_search(
 
 
 if __name__ == "__main__":
-    mcp.run()
+    mcp.run(transport=_args.transport)

pyproject.toml

@@ -16,6 +16,7 @@ dependencies = [
 
 [dependency-groups]
 dev = [
+    "google-adk>=1.25.1",
     "ruff>=0.15.2",
     "ty>=0.0.18",
 ]