langchain-mcp-tools 0.0.16__tar.gz → 0.0.17__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.2
2
2
  Name: langchain-mcp-tools
3
- Version: 0.0.16
3
+ Version: 0.0.17
4
4
  Summary: Model Context Protocol (MCP) To LangChain Tools Conversion Utility
5
5
  Project-URL: Bug Tracker, https://github.com/hideya/langchain-mcp-tools-py/issues
6
6
  Project-URL: Source Code, https://github.com/hideya/langchain-mcp-tools-py
@@ -70,11 +70,12 @@ and is expressed as a `dict`, e.g.:
70
70
  )
71
71
  ```
72
72
 
73
- The utility function initializes all specified MCP servers in parallel,
74
- and returns LangChain Tools (`List[BaseTool]`)
75
- by gathering all available MCP server tools,
76
- and by wrapping them into [LangChain Tools](https://js.langchain.com/docs/how_to/tool_calling/).
77
- It also returns a cleanup callback function (`McpServerCleanupFn`)
73
+ This utility function initializes all specified MCP servers in parallel,
74
+ and returns [LangChain Tools](https://python.langchain.com/api_reference/core/tools.html)
75
+ (`tools: List[BaseTool]`)
76
+ by gathering available MCP tools from the servers,
77
+ and by wrapping them into LangChain tools.
78
+ It also returns an async callback function (`cleanup: McpServerCleanupFn`)
78
79
  to be invoked to close all MCP server sessions when finished.
79
80
 
80
81
  The returned tools can be used with LangChain, e.g.:
@@ -155,7 +156,8 @@ Any comments pointing out something I am missing would be greatly appreciated!
155
156
 
156
157
  3. Task Lifecycle:
157
158
 
158
- The following illustrates how to implement the above-mentioned strategy:
159
+ The following task lifecyle diagram illustrates how the above strategy
160
+ was impelemented:
159
161
  ```
160
162
  [Task starts]
161
163
 
@@ -47,11 +47,12 @@ and is expressed as a `dict`, e.g.:
47
47
  )
48
48
  ```
49
49
 
50
- The utility function initializes all specified MCP servers in parallel,
51
- and returns LangChain Tools (`List[BaseTool]`)
52
- by gathering all available MCP server tools,
53
- and by wrapping them into [LangChain Tools](https://js.langchain.com/docs/how_to/tool_calling/).
54
- It also returns a cleanup callback function (`McpServerCleanupFn`)
50
+ This utility function initializes all specified MCP servers in parallel,
51
+ and returns [LangChain Tools](https://python.langchain.com/api_reference/core/tools.html)
52
+ (`tools: List[BaseTool]`)
53
+ by gathering available MCP tools from the servers,
54
+ and by wrapping them into LangChain tools.
55
+ It also returns an async callback function (`cleanup: McpServerCleanupFn`)
55
56
  to be invoked to close all MCP server sessions when finished.
56
57
 
57
58
  The returned tools can be used with LangChain, e.g.:
@@ -132,7 +133,8 @@ Any comments pointing out something I am missing would be greatly appreciated!
132
133
 
133
134
  3. Task Lifecycle:
134
135
 
135
- The following illustrates how to implement the above-mentioned strategy:
136
+ The following task lifecyle diagram illustrates how the above strategy
137
+ was impelemented:
136
138
  ```
137
139
  [Task starts]
138
140
 
@@ -46,7 +46,7 @@ The key aspects are:
46
46
  - Resources management for `stdio_client` and `ClientSession` seems
47
47
  to require relying exclusively on `asynccontextmanager` for cleanup,
48
48
  with no manual cleanup options
49
- (based on [the mcp python-sdk impl as of Jan 14, 2025](https://github.com/modelcontextprotocol/python-sdk/tree/99727a9/src/mcp/client))
49
+ (based on the mcp python-sdk impl as of Jan 14, 2025)
50
50
  - Initializing multiple MCP servers in parallel requires a dedicated
51
51
  `asyncio.Task` per server
52
52
  - Need to keep sessions alive for later use by different tasks
@@ -75,7 +75,8 @@ The key aspects are:
75
75
 
76
76
  3. Task Lifecycle:
77
77
 
78
- The following illustrates how to implement the above-mentioned strategy:
78
+ The following task lifecyle diagram illustrates how the above strategy
79
+ was impelemented:
79
80
  ```
80
81
  [Task starts]
81
82
 
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.2
2
2
  Name: langchain-mcp-tools
3
- Version: 0.0.16
3
+ Version: 0.0.17
4
4
  Summary: Model Context Protocol (MCP) To LangChain Tools Conversion Utility
5
5
  Project-URL: Bug Tracker, https://github.com/hideya/langchain-mcp-tools-py/issues
6
6
  Project-URL: Source Code, https://github.com/hideya/langchain-mcp-tools-py
@@ -70,11 +70,12 @@ and is expressed as a `dict`, e.g.:
70
70
  )
71
71
  ```
72
72
 
73
- The utility function initializes all specified MCP servers in parallel,
74
- and returns LangChain Tools (`List[BaseTool]`)
75
- by gathering all available MCP server tools,
76
- and by wrapping them into [LangChain Tools](https://js.langchain.com/docs/how_to/tool_calling/).
77
- It also returns a cleanup callback function (`McpServerCleanupFn`)
73
+ This utility function initializes all specified MCP servers in parallel,
74
+ and returns [LangChain Tools](https://python.langchain.com/api_reference/core/tools.html)
75
+ (`tools: List[BaseTool]`)
76
+ by gathering available MCP tools from the servers,
77
+ and by wrapping them into LangChain tools.
78
+ It also returns an async callback function (`cleanup: McpServerCleanupFn`)
78
79
  to be invoked to close all MCP server sessions when finished.
79
80
 
80
81
  The returned tools can be used with LangChain, e.g.:
@@ -155,7 +156,8 @@ Any comments pointing out something I am missing would be greatly appreciated!
155
156
 
156
157
  3. Task Lifecycle:
157
158
 
158
- The following illustrates how to implement the above-mentioned strategy:
159
+ The following task lifecyle diagram illustrates how the above strategy
160
+ was impelemented:
159
161
  ```
160
162
  [Task starts]
161
163
 
@@ -1,6 +1,6 @@
1
1
  [project]
2
2
  name = "langchain-mcp-tools"
3
- version = "0.0.16"
3
+ version = "0.0.17"
4
4
  description = "Model Context Protocol (MCP) To LangChain Tools Conversion Utility"
5
5
  readme = "README.md"
6
6
  requires-python = ">=3.11"