langchain-mcp-tools 0.0.8__tar.gz → 0.0.10__tar.gz

{langchain_mcp_tools-0.0.8 → langchain_mcp_tools-0.0.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: langchain-mcp-tools
-Version: 0.0.8
+Version: 0.0.10
 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
@@ -27,7 +27,7 @@ server tools with LangChain / Python.
 
 It contains a utility function `convertMcpToLangchainTools()`.  
 This function handles parallel initialization of specified multiple MCP servers
-and converts their available tools into an array of
+and converts their available tools into a list of
 [LangChain-compatible tools](https://js.langchain.com/docs/how_to/tool_calling/).
 
 A typescript equivalent of this utility library is available
@@ -90,15 +90,13 @@ The returned tools can be used with LangChain, e.g.:
         tools
     )
 ```
-<!-- A simple and experimentable usage example can be found
-[here](https://github.com/hideya/langchain-mcp-tools-ts-usage/blob/main/src/index.ts) -->
+A simple and experimentable usage example can be found
+[here](https://github.com/hideya/langchain-mcp-tools-py-usage/blob/main/src/example.py)
 
-<!-- A more realistic usage example can be found
-[here](https://github.com/hideya/langchain-mcp-client-ts) -->
-
-An usage example can be found
+A more realistic usage example can be found
 [here](https://github.com/hideya/mcp-client-langchain-py)
 
+
 ## Limitations
 
 Currently, only text results of tool calls are supported.
@@ -124,10 +122,11 @@ Any comments pointing out something I am missing would be greatly appreciated!
    - Ensuring proper cleanup later in the same task that created them
 
 2. Solution Strategy:
+
    A key requirement for parallel initialization is that each server must be
-   initialized in its own dedicated task - there's no way around this if we
-   want true parallel initialization. However, this creates a challenge since
-   we also need to maintain long-lived sessions and handle cleanup properly.
+   initialized in its own dedicated task - there's no way around this as far
+   as I understand. However, this creates a challenge since we also need to
+   maintain long-lived sessions and handle cleanup properly.
 
    The key insight is to keep the initialization tasks alive throughout the
    session lifetime, rather than letting them complete after initialization.

{langchain_mcp_tools-0.0.8 → langchain_mcp_tools-0.0.10}/README.md

@@ -6,7 +6,7 @@ server tools with LangChain / Python.
 
 It contains a utility function `convertMcpToLangchainTools()`.  
 This function handles parallel initialization of specified multiple MCP servers
-and converts their available tools into an array of
+and converts their available tools into a list of
 [LangChain-compatible tools](https://js.langchain.com/docs/how_to/tool_calling/).
 
 A typescript equivalent of this utility library is available
@@ -69,15 +69,13 @@ The returned tools can be used with LangChain, e.g.:
         tools
     )
 ```
-<!-- A simple and experimentable usage example can be found
-[here](https://github.com/hideya/langchain-mcp-tools-ts-usage/blob/main/src/index.ts) -->
+A simple and experimentable usage example can be found
+[here](https://github.com/hideya/langchain-mcp-tools-py-usage/blob/main/src/example.py)
 
-<!-- A more realistic usage example can be found
-[here](https://github.com/hideya/langchain-mcp-client-ts) -->
-
-An usage example can be found
+A more realistic usage example can be found
 [here](https://github.com/hideya/mcp-client-langchain-py)
 
+
 ## Limitations
 
 Currently, only text results of tool calls are supported.
@@ -103,10 +101,11 @@ Any comments pointing out something I am missing would be greatly appreciated!
    - Ensuring proper cleanup later in the same task that created them
 
 2. Solution Strategy:
+
    A key requirement for parallel initialization is that each server must be
-   initialized in its own dedicated task - there's no way around this if we
-   want true parallel initialization. However, this creates a challenge since
-   we also need to maintain long-lived sessions and handle cleanup properly.
+   initialized in its own dedicated task - there's no way around this as far
+   as I understand. However, this creates a challenge since we also need to
+   maintain long-lived sessions and handle cleanup properly.
 
    The key insight is to keep the initialization tasks alive throughout the
    session lifetime, rather than letting them complete after initialization.

{langchain_mcp_tools-0.0.8 → langchain_mcp_tools-0.0.10}/langchain_mcp_tools/langchain_mcp_tools.py

@@ -47,9 +47,9 @@ The key aspects are:
 
 2. Solution Strategy:
    A key requirement for parallel initialization is that each server must be
-   initialized in its own dedicated task - there's no way around this if we
-   want true parallel initialization. However, this creates a challenge since
-   we also need to maintain long-lived sessions and handle cleanup properly.
+   initialized in its own dedicated task - there's no way around this as far
+   as I understand. However, this creates a challenge since we also need to
+   maintain long-lived sessions and handle cleanup properly.
 
    The key insight is to keep the initialization tasks alive throughout the
    session lifetime, rather than letting them complete after initialization.
@@ -272,16 +272,15 @@ async def convert_mcp_to_langchain_tools(
         ))
         tasks.append(task)
 
-    for ready_event in ready_event_list:
-        await ready_event.wait()
+    await asyncio.gather(*(event.wait() for event in ready_event_list))
 
     langchain_tools = [
         item for sublist in per_server_tools for item in sublist
     ]
 
     async def mcp_cleanup() -> None:
-        for cleanup_event in cleanup_event_list:
-            cleanup_event.set()
+        for event in cleanup_event_list:
+            event.set()
 
     logger.info(f'MCP servers initialized: {len(langchain_tools)} tool(s) '
                 f'available in total')

{langchain_mcp_tools-0.0.8 → langchain_mcp_tools-0.0.10}/langchain_mcp_tools.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: langchain-mcp-tools
-Version: 0.0.8
+Version: 0.0.10
 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
@@ -27,7 +27,7 @@ server tools with LangChain / Python.
 
 It contains a utility function `convertMcpToLangchainTools()`.  
 This function handles parallel initialization of specified multiple MCP servers
-and converts their available tools into an array of
+and converts their available tools into a list of
 [LangChain-compatible tools](https://js.langchain.com/docs/how_to/tool_calling/).
 
 A typescript equivalent of this utility library is available
@@ -90,15 +90,13 @@ The returned tools can be used with LangChain, e.g.:
         tools
     )
 ```
-<!-- A simple and experimentable usage example can be found
-[here](https://github.com/hideya/langchain-mcp-tools-ts-usage/blob/main/src/index.ts) -->
+A simple and experimentable usage example can be found
+[here](https://github.com/hideya/langchain-mcp-tools-py-usage/blob/main/src/example.py)
 
-<!-- A more realistic usage example can be found
-[here](https://github.com/hideya/langchain-mcp-client-ts) -->
-
-An usage example can be found
+A more realistic usage example can be found
 [here](https://github.com/hideya/mcp-client-langchain-py)
 
+
 ## Limitations
 
 Currently, only text results of tool calls are supported.
@@ -124,10 +122,11 @@ Any comments pointing out something I am missing would be greatly appreciated!
    - Ensuring proper cleanup later in the same task that created them
 
 2. Solution Strategy:
+
    A key requirement for parallel initialization is that each server must be
-   initialized in its own dedicated task - there's no way around this if we
-   want true parallel initialization. However, this creates a challenge since
-   we also need to maintain long-lived sessions and handle cleanup properly.
+   initialized in its own dedicated task - there's no way around this as far
+   as I understand. However, this creates a challenge since we also need to
+   maintain long-lived sessions and handle cleanup properly.
 
    The key insight is to keep the initialization tasks alive throughout the
    session lifetime, rather than letting them complete after initialization.

{langchain_mcp_tools-0.0.8 → langchain_mcp_tools-0.0.10}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "langchain-mcp-tools"
-version = "0.0.8"
+version = "0.0.10"
 description = "Model Context Protocol (MCP) To LangChain Tools Conversion Utility"
 readme = "README.md"
 requires-python = ">=3.11"