langchain-mcp-tools 0.0.16__py3-none-any.whl → 0.1.0__py3-none-any.whl

langchain_mcp_tools/langchain_mcp_tools.py

@@ -36,7 +36,7 @@ This code implements a specific pattern for managing async resources that
 require context managers while enabling parallel initialization.
 The key aspects are:
 
-1. Core Challenge:
+1. Challenge:
 
    A key requirement for parallel initialization is that each server must be
    initialized in its own dedicated task - there's no way around this as far as
@@ -46,14 +46,13 @@ The key aspects are:
    - Resources management for `stdio_client` and `ClientSession` seems
      to require relying exclusively on `asynccontextmanager` for cleanup,
      with no manual cleanup options
-     (based on [the mcp python-sdk impl as of Jan 14, 2025](https://github.com/modelcontextprotocol/python-sdk/tree/99727a9/src/mcp/client))
+     (based on the mcp python-sdk impl as of Jan 14, 2025)
    - Initializing multiple MCP servers in parallel requires a dedicated
      `asyncio.Task` per server
-   - Need to keep sessions alive for later use by different tasks
-     after initialization
-   - Need to ensure proper cleanup later in the same task that created them
+   - Server cleanup can be initiated later by a task other than the one that
+     initialized the resources
 
-2. Solution Strategy:
+2. Solution:
 
    The key insight is to keep the initialization tasks alive throughout the
    session lifetime, rather than letting them complete after initialization.
@@ -75,7 +74,8 @@ The key aspects are:
 
 3. Task Lifecycle:
 
-   The following illustrates how to implement the above-mentioned strategy:
+   The following task lifecyle diagram illustrates how the above strategy
+   was impelemented:
    ```
    [Task starts]
      ↓

{langchain_mcp_tools-0.0.16.dist-info → langchain_mcp_tools-0.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: langchain-mcp-tools
-Version: 0.0.16
+Version: 0.1.0
 Summary: Model Context Protocol (MCP) To LangChain Tools Conversion Utility
 Project-URL: Bug Tracker, https://github.com/hideya/langchain-mcp-tools-py/issues
 Project-URL: Source Code, https://github.com/hideya/langchain-mcp-tools-py
@@ -8,7 +8,6 @@ Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: jsonschema-pydantic>=0.6
-Requires-Dist: langchain-core>=0.3.29
 Requires-Dist: langchain>=0.3.14
 Requires-Dist: langchain-anthropic>=0.3.1
 Requires-Dist: langchain-groq>=0.2.3
@@ -19,7 +18,8 @@ Requires-Dist: pyjson5>=1.6.8
 Requires-Dist: pympler>=1.1
 Requires-Dist: python-dotenv>=1.0.1
 Provides-Extra: dev
-Requires-Dist: twine>=6.0.1; extra == "dev"
+Requires-Dist: pytest>=8.3.4; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.25.2; extra == "dev"
 
 # MCP To LangChain Tools Conversion Utility [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://github.com/hideya/langchain-mcp-tools-py/blob/main/LICENSE) [![pypi version](https://img.shields.io/pypi/v/langchain-mcp-tools.svg)](https://pypi.org/project/langchain-mcp-tools/)
 
@@ -29,8 +29,7 @@ server tools with LangChain / Python.
 
 It contains a utility function `convert_mcp_to_langchain_tools()`.  
 This function handles parallel initialization of specified multiple MCP servers
-and converts their available tools into a list of
-[LangChain-compatible tools](https://js.langchain.com/docs/how_to/tool_calling/).
+and converts their available tools into a list of LangChain-compatible tools.
 
 A typescript equivalent of this utility library is available
 [here](https://www.npmjs.com/package/@h1deya/langchain-mcp-tools)
@@ -54,43 +53,44 @@ but only the contents of the `mcpServers` property,
 and is expressed as a `dict`, e.g.:
 
 ```python
-    mcp_configs = {
-        'filesystem': {
-            'command': 'npx',
-            'args': ['-y', '@modelcontextprotocol/server-filesystem', '.']
-        },
-        'fetch': {
-            'command': 'uvx',
-            'args': ['mcp-server-fetch']
-        }
+mcp_configs = {
+    'filesystem': {
+        'command': 'npx',
+        'args': ['-y', '@modelcontextprotocol/server-filesystem', '.']
+    },
+    'fetch': {
+        'command': 'uvx',
+        'args': ['mcp-server-fetch']
     }
+}
 
-    tools, cleanup = await convert_mcp_to_langchain_tools(
-        mcp_configs
-    )
+tools, cleanup = await convert_mcp_to_langchain_tools(
+    mcp_configs
+)
 ```
 
-The utility function initializes all specified MCP servers in parallel,
-and returns LangChain Tools (`List[BaseTool]`)
-by gathering all available MCP server tools,
-and by wrapping them into [LangChain Tools](https://js.langchain.com/docs/how_to/tool_calling/).
-It also returns a cleanup callback function (`McpServerCleanupFn`)
+This utility function initializes all specified MCP servers in parallel,
+and returns LangChain Tools
+([`tools: List[BaseTool]`](https://python.langchain.com/api_reference/core/tools/langchain_core.tools.base.BaseTool.html#langchain_core.tools.base.BaseTool))
+by gathering available MCP tools from the servers,
+and by wrapping them into LangChain tools.
+It also returns an async callback function (`cleanup: McpServerCleanupFn`)
 to be invoked to close all MCP server sessions when finished.
 
 The returned tools can be used with LangChain, e.g.:
 
 ```python
-    # from langchain.chat_models import init_chat_model
-    llm = init_chat_model(
-        model='claude-3-5-haiku-latest',
-        model_provider='anthropic'
-    )
-
-    # from langgraph.prebuilt import create_react_agent
-    agent = create_react_agent(
-        llm,
-        tools
-    )
+# from langchain.chat_models import init_chat_model
+llm = init_chat_model(
+    model='claude-3-5-haiku-latest',
+    model_provider='anthropic'
+)
+
+# from langgraph.prebuilt import create_react_agent
+agent = create_react_agent(
+    llm,
+    tools
+)
 ```
 A simple and experimentable usage example can be found
 [here](https://github.com/hideya/langchain-mcp-tools-py-usage/blob/main/src/example.py)
@@ -112,11 +112,11 @@ I'm new to Python, so it is very possible that my ignorance is playing
 a big role here...  
 I'll summarize the difficulties I faced below.
 The source code is available
-[here](https://github.com/hideya/langchain-mcp-tools-py/blob/main/langchain_mcp_tools/langchain_mcp_tools.py).  
+[here](https://github.com/hideya/langchain-mcp-tools-py/blob/main/src/langchain_mcp_tools/langchain_mcp_tools.py).  
 Any comments pointing out something I am missing would be greatly appreciated!
 [(comment here)](https://github.com/hideya/langchain-mcp-tools-ts/issues)
 
-1. Core Challenge:
+1. Challenge:
 
    A key requirement for parallel initialization is that each server must be
    initialized in its own dedicated task - there's no way around this as far as
@@ -129,11 +129,10 @@ Any comments pointing out something I am missing would be greatly appreciated!
      (based on [the mcp python-sdk impl as of Jan 14, 2025](https://github.com/modelcontextprotocol/python-sdk/tree/99727a9/src/mcp/client))
    - Initializing multiple MCP servers in parallel requires a dedicated
      `asyncio.Task` per server
-   - Need to keep sessions alive for later use by different tasks
-     after initialization
-   - Need to ensure proper cleanup later in the same task that created them
+   - Server cleanup can be initiated later by a task other than the one
+     that initialized the resources
 
-2. Solution Strategy:
+2. Solution:
 
    The key insight is to keep the initialization tasks alive throughout the
    session lifetime, rather than letting them complete after initialization.
@@ -155,7 +154,8 @@ Any comments pointing out something I am missing would be greatly appreciated!
 
 3. Task Lifecycle:
 
-   The following illustrates how to implement the above-mentioned strategy:
+   The following task lifecyle diagram illustrates how the above strategy
+   was impelemented:
    ```
    [Task starts]
      ↓
@@ -176,5 +176,5 @@ It usually means I'm doing something very worng...
 I think it is a natural assumption that MCP SDK is designed with consideration
 for parallel server initialization.
 I'm not sure what I'm missing...
-(FYI, with the TypeScript MCP SDK, parallel initialization was 
+(FYI, with the TypeScript MCP SDK, parallel initialization was
 [pretty straightforward](https://github.com/hideya/langchain-mcp-tools-ts/blob/main/src/langchain-mcp-tools.ts))

langchain_mcp_tools-0.1.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+langchain_mcp_tools/__init__.py,sha256=Xtv2VphhrWB_KlxTIofHZqtCIGtNEl0MxugnrNXTERA,94
+langchain_mcp_tools/langchain_mcp_tools.py,sha256=PxkOAwQ8WUd12N-hZNfy2u5hawvhlEQhs0CsyPTWch0,10374
+langchain_mcp_tools/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+langchain_mcp_tools-0.1.0.dist-info/LICENSE,sha256=CRC91e8v116gCpnp7h49oIa6_zjhxqnHFTREeoZFJwA,1072
+langchain_mcp_tools-0.1.0.dist-info/METADATA,sha256=FuNglrw844NXdrNWNgkK7WNIUIIdW7a1sdJKRSmdT4o,6794
+langchain_mcp_tools-0.1.0.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+langchain_mcp_tools-0.1.0.dist-info/top_level.txt,sha256=aR_9V2A1Yt-Bca60KmndmGLUWb2wiM5IOG-Gkaf1dxY,20
+langchain_mcp_tools-0.1.0.dist-info/RECORD,,

langchain_mcp_tools-0.0.16.dist-info/RECORD

@@ -1,8 +0,0 @@
-langchain_mcp_tools/__init__.py,sha256=Xtv2VphhrWB_KlxTIofHZqtCIGtNEl0MxugnrNXTERA,94
-langchain_mcp_tools/langchain_mcp_tools.py,sha256=EJgm28o2M3mBsFkeDtpw6hooSE1oWwjFJYhRfirxCgE,10511
-langchain_mcp_tools/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-langchain_mcp_tools-0.0.16.dist-info/LICENSE,sha256=CRC91e8v116gCpnp7h49oIa6_zjhxqnHFTREeoZFJwA,1072
-langchain_mcp_tools-0.0.16.dist-info/METADATA,sha256=S7Ii62KuH2HTe1eg3eqSqfpUWWagTKz0diIn3Wdc-Ns,6876
-langchain_mcp_tools-0.0.16.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-langchain_mcp_tools-0.0.16.dist-info/top_level.txt,sha256=aR_9V2A1Yt-Bca60KmndmGLUWb2wiM5IOG-Gkaf1dxY,20
-langchain_mcp_tools-0.0.16.dist-info/RECORD,,