Implementing MCP sse/http transport (#12)

* [refactor] separateing tools

* adding SSE and HTTP transports

* [REF] separating box tools

* [REF] fix reported problems (types, unused, etc)

* [REF] output dict in box search tool

* [REF] output dict in several tools

* [REF] separate tools generic and search + integration testing

* [REF] separate tools AI + integration testing

* [REF] separate tools docgen + MISSING integration testing

* [REF] separate tools files+folders + integration testing

* [REF] Ruff linting

* version 0.1.1

* updating read.me

Author: barduinor

.vscode/settings.json

@@ -5,7 +5,10 @@
     "python.testing.unittestEnabled": false,
     "python.testing.pytestEnabled": true,
     "cSpell.words": [
+        "Airbyte",
+        "docgen",
         "dotenv",
-        "fastmcp"
+        "fastmcp",
+        "streamable"
     ]
 }

README.md

@@ -10,11 +10,11 @@ The Model Context Protocol (MCP) is a framework designed to standardize the way
 
 ### Box API Tools
 
-#### `box_who_am_i`
+### `box_who_am_i`
 Get your current user information and check connection status.
 - **Returns:** User information string
 
-#### `box_authorize_app_tool`
+### `box_authorize_app_tool`
 Start the Box application authorization process.
 - **Returns:** Authorization status message
 
@@ -27,7 +27,7 @@ Search for files in Box.
   - `ancestor_folder_ids` (List[str], optional): List of folder IDs in which to search.
 - **Returns:** The search results as a newline‑separated list of file names and IDs.
 
-#### `box_read_tool`
+### `box_read_tool`
 Read the text content of a Box file.
 
 **Parameters:**
@@ -305,14 +305,20 @@ List all Doc Gen jobs that used a specific template.
 
 ### Running the MCP Server
 
-To start the MCP server, run the following command:
+The MCP server supports four transport methods: **stdio** (default), **SSE** (Server-Sent Events), **HTTP** (StreamableHttp), and **FastAPI**.
+
+#### Running with stdio transport (default)
 
 ```sh
-uv --directory /Users/anovotny/Desktop/mcp-server-box run src/mcp_server_box.py
+uv --directory /path/to/mcp-server-box run src/mcp_server_box.py
 ```
 
+
+
 ### Using Claude as the client
 
+#### For stdio transport (recommended for Claude Desktop)
+
 1. Edit your `claude_desktop_config.json`:
 
     ```sh
@@ -328,7 +334,7 @@ uv --directory /Users/anovotny/Desktop/mcp-server-box run src/mcp_server_box.py
                 "command": "uv",
                 "args": [
                     "--directory",
-                    "/Users/anovotny/Desktop/mcp-server-box",
+                    "/path/to/mcp-server-box",
                     "run",
                     "src/mcp_server_box.py"
                 ]
@@ -339,8 +345,11 @@ uv --directory /Users/anovotny/Desktop/mcp-server-box run src/mcp_server_box.py
 
 3. Restart Claude if it is running.
 
+
 ### Using Cursor as the client
 
+#### For stdio transport
+
 1. Open your IDE with Cursor.
 2. In settings, select `Cursor settings`.
 3. In the left nav, select `MCP`.
@@ -354,7 +363,7 @@ uv --directory /Users/anovotny/Desktop/mcp-server-box run src/mcp_server_box.py
           "command": "uv",
           "args": [
             "--directory",
-            "/Users/shurrey/local/mcp-server-box",
+            "/path/to/mcp-server-box",
             "run",
             "src/mcp_server_box.py"
           ]
@@ -365,6 +374,7 @@ uv --directory /Users/anovotny/Desktop/mcp-server-box run src/mcp_server_box.py
 
 6. Save and close the mcp.json file, and restart if necessary.
 
+
 ## Running Tests
 
 The project includes a suite of tests to verify Box API functionality. Before running the tests, update the file and folder IDs in the test files to match those in your Box account.
@@ -395,15 +405,6 @@ pytest -v
 pytest -v -s
 ```
 
-### Available Test Suites
-
-- `test_box_auth.py`: Tests authentication functionality.
-- `test_box_api_basic.py`: Basic Box API tests.
-- `test_box_api_read.py`: Tests file reading capabilities.
-- `test_box_api_search.py`: Tests search functionality.
-- `test_box_api_ai.py`: Tests AI-based features.
-- `test_box_api_file_ops.py`: Tests file upload and download operations.
-- Additional tests cover folder operations and Doc Gen features.
 
 ## Troubleshooting
 

pyproject.toml

@@ -1,15 +1,18 @@
 [project]
 name = "mcp-server-box"
-version = "0.1.0"
+version = "0.1.1"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.13"
 dependencies = [
     "box-ai-agents-toolkit>=0.0.42",
-    "box-sdk-gen>=1.13.0",
-    "mcp[cli]>=1.6.0",
-    "python-dotenv>=1.1.0",
+    "fastapi>=0.115.14",
+    "mcp[cli]>=1.10.1",
+    "python-dotenv>=1.1.1",
 ]
 
 [dependency-groups]
 dev = ["pytest>=8.3.5", "pytest-asyncio>=0.26.0", "pytest-cov>=6.1.0"]
+
+[tool.pytest.ini_options]
+pythonpath = [".", "src"]

src/box_tools_ai.py

@@ -0,0 +1,122 @@
+from typing import List
+
+from box_ai_agents_toolkit import (
+    box_file_ai_ask,
+    box_file_ai_extract,
+    box_hubs_ai_ask,
+    box_multi_file_ai_ask,
+    box_multi_file_ai_extract,
+)
+from mcp.server.fastmcp import Context
+
+from box_tools_generic import get_box_client
+
+
+async def box_ask_ai_tool(ctx: Context, file_id: str, prompt: str) -> dict:
+    """
+    Ask box ai about a file in Box.
+
+    Args:
+        file_id (str): The ID of the file to read.
+        prompt (str): The prompt to ask the AI.
+    return:
+        dict: The text content of the file.
+    """
+    # check if file id isn't a string and convert to a string
+    if not isinstance(file_id, str):
+        file_id = str(file_id)
+
+    box_client = get_box_client(ctx)
+    response = box_file_ai_ask(box_client, file_id, prompt=prompt)
+    return response
+
+
+async def box_ask_ai_tool_multi_file(
+    ctx: Context, file_ids: List[str], prompt: str
+) -> dict:
+    """
+    Use Box AI to analyze and respond to a prompt based on the content of multiple files.
+
+    This tool allows users to query Box AI with a specific prompt, leveraging the content
+    of multiple files stored in Box. The AI processes the files and generates a response
+    based on the provided prompt.
+
+    Args:
+        ctx (Context): The context object containing the request and lifespan context.
+        file_ids (List[str]): A list of file IDs to be analyzed by the AI.
+        prompt (str): The prompt or question to ask the AI.
+
+    Returns:
+        dict: The AI-generated response based on the content of the specified files.
+
+    Raises:
+        Exception: If there is an issue with the Box client, AI agent, or file processing.
+    """
+    box_client = get_box_client(ctx)
+    response = box_multi_file_ai_ask(box_client, file_ids, prompt=prompt)
+    return response
+
+
+async def box_hubs_ask_ai_tool(ctx: Context, hubs_id: str, prompt: str) -> dict:
+    """
+    Ask box ai about a hub in Box. Currently there is no way to discover a hub
+    in Box, so you need to know the id of the hub. We will fix this in the future.
+
+    Args:
+        hubs_id (str): The ID of the hub to read.
+        prompt (str): The prompt to ask the AI.
+    return:
+        dict: The text content of the file.
+    """
+    # check if file id isn't a string and convert to a string
+    if not isinstance(hubs_id, str):
+        hubs_id = str(hubs_id)
+
+    box_client = get_box_client(ctx)
+    # ai_agent = box_claude_ai_agent_ask()
+    response = box_hubs_ai_ask(box_client, hubs_id, prompt=prompt)
+    return response
+
+
+async def box_ai_extract_tool(ctx: Context, file_id: str, fields: str) -> dict:
+    """ "
+    Extract data from a single file in Box using AI.
+
+    Args:
+        file_id (str): The ID of the file to read.
+        fields (str): The fields to extract from the file.
+    return:
+        dict: The extracted data in a json string format.
+    """
+    box_client = get_box_client(ctx)
+
+    # check if file id isn't a string and convert to a string
+    if not isinstance(file_id, str):
+        file_id = str(file_id)
+
+    response = box_file_ai_extract(box_client, file_id, fields)
+    return response
+
+
+async def box_ai_extract_tool_multi_file(
+    ctx: Context, file_ids: List[str], fields: str
+) -> dict:
+    """ "
+    Extract data from multiple files in Box using AI.
+
+    Args:
+        file_ids (List[str]): The IDs of the files to read.
+        fields (str): The fields to extract from the files.
+    return:
+        dict: The extracted data in a json string format.
+    """
+    box_client = get_box_client(ctx)
+
+    # check if file ids aren't a list of strings and convert to a list of strings
+    if not isinstance(file_ids, list):
+        file_ids = [str(file_ids)]
+    else:
+        file_ids = [str(file_id) for file_id in file_ids]
+
+    response = box_multi_file_ai_extract(box_client, file_ids, fields)
+    return response