langchain-mcp-tools 0.0.12__py3-none-any.whl → 0.0.14__py3-none-any.whl

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.
Files changed (7) hide show
  1. langchain_mcp_tools/langchain_mcp_tools.py +6 -5
  2. {langchain_mcp_tools-0.0.12.dist-info → langchain_mcp_tools-0.0.14.dist-info}/METADATA +7 -6
  3. langchain_mcp_tools-0.0.14.dist-info/RECORD +8 -0
  4. langchain_mcp_tools-0.0.12.dist-info/RECORD +0 -8
  5. {langchain_mcp_tools-0.0.12.dist-info → langchain_mcp_tools-0.0.14.dist-info}/LICENSE +0 -0
  6. {langchain_mcp_tools-0.0.12.dist-info → langchain_mcp_tools-0.0.14.dist-info}/WHEEL +0 -0
  7. {langchain_mcp_tools-0.0.12.dist-info → langchain_mcp_tools-0.0.14.dist-info}/top_level.txt +0 -0
langchain_mcp_tools/langchain_mcp_tools.py CHANGED
@@ -38,13 +38,14 @@ The key aspects are:
38
38
 
39
39
  1. Core Challenge:
40
40
  - Async resources management for `stdio_client` and `ClientSession` seems
41
- to require relying exclusively on `asynccontextmanager` for cleanup with
42
- no manual cleanup options
41
+ to require relying exclusively on `asynccontextmanager` for cleanup,
42
+ with no manual cleanup options
43
43
  (based on [the mcp python-sdk impl as of Jan 14, 2025](https://github.com/modelcontextprotocol/python-sdk/tree/99727a9/src/mcp/client))
44
44
  - Initializing multiple MCP servers in parallel requires a dedicated
45
45
  `asyncio.Task` per server
46
- - Necessity of keeping sessions alive for later use after initialization
47
- - Ensuring proper cleanup later in the same task that created them
46
+ - Need to keep sessions alive for later use by different tasks
47
+ after initialization
48
+ - Need to ensure proper cleanup later in the same task that created them
48
49
 
49
50
  2. Solution Strategy:
50
51
  A key requirement for parallel initialization is that each server must be
@@ -72,7 +73,7 @@ The key aspects are:
72
73
 
73
74
  3. Task Lifecycle:
74
75
 
75
- To allow the initialization task to stay alive waiting for cleanup:
76
+ The following illustrates how to implement the above-mentioned strategy:
76
77
  ```
77
78
  [Task starts]
78
79
  ↓
{langchain_mcp_tools-0.0.12.dist-info → langchain_mcp_tools-0.0.14.dist-info}/METADATA RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.2
2
2
  Name: langchain-mcp-tools
3
- Version: 0.0.12
3
+ Version: 0.0.14
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
@@ -120,13 +120,14 @@ Any comments pointing out something I am missing would be greatly appreciated!
120
120
 
121
121
  1. Core Challenge:
122
122
  - Async resources management for `stdio_client` and `ClientSession` seems
123
- to require relying exclusively on `asynccontextmanager` for cleanup with
124
- no manual cleanup options
123
+ to require relying exclusively on `asynccontextmanager` for cleanup,
124
+ with no manual cleanup options
125
125
  (based on [the mcp python-sdk impl as of Jan 14, 2025](https://github.com/modelcontextprotocol/python-sdk/tree/99727a9/src/mcp/client))
126
126
  - Initializing multiple MCP servers in parallel requires a dedicated
127
127
  `asyncio.Task` per server
128
- - Necessity of keeping sessions alive for later use after initialization
129
- - Ensuring proper cleanup later in the same task that created them
128
+ - Need to keep sessions alive for later use by different tasks
129
+ after initialization
130
+ - Need to ensure proper cleanup later in the same task that created them
130
131
 
131
132
  2. Solution Strategy:
132
133
 
@@ -155,7 +156,7 @@ Any comments pointing out something I am missing would be greatly appreciated!
155
156
 
156
157
  3. Task Lifecycle:
157
158
 
158
- To allow the initialization task to stay alive waiting for cleanup:
159
+ The following illustrates how to implement the above-mentioned strategy:
159
160
  ```
160
161
  [Task starts]
161
162
  ↓
langchain_mcp_tools-0.0.14.dist-info/RECORD ADDED
@@ -0,0 +1,8 @@
1
+ langchain_mcp_tools/__init__.py,sha256=Xtv2VphhrWB_KlxTIofHZqtCIGtNEl0MxugnrNXTERA,94
2
+ langchain_mcp_tools/langchain_mcp_tools.py,sha256=LptcccMFDM9t9ZYPOGvNuTBW7JFPP8Nhv3JwLr0Mits,10561
3
+ langchain_mcp_tools/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
4
+ langchain_mcp_tools-0.0.14.dist-info/LICENSE,sha256=CRC91e8v116gCpnp7h49oIa6_zjhxqnHFTREeoZFJwA,1072
5
+ langchain_mcp_tools-0.0.14.dist-info/METADATA,sha256=XNhz-pzd91ROR5Av0wjJ4qvB3dGcLST_ruBUKprJhrE,6962
6
+ langchain_mcp_tools-0.0.14.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
7
+ langchain_mcp_tools-0.0.14.dist-info/top_level.txt,sha256=aR_9V2A1Yt-Bca60KmndmGLUWb2wiM5IOG-Gkaf1dxY,20
8
+ langchain_mcp_tools-0.0.14.dist-info/RECORD,,
langchain_mcp_tools-0.0.12.dist-info/RECORD DELETED
@@ -1,8 +0,0 @@
1
- langchain_mcp_tools/__init__.py,sha256=Xtv2VphhrWB_KlxTIofHZqtCIGtNEl0MxugnrNXTERA,94
2
- langchain_mcp_tools/langchain_mcp_tools.py,sha256=eCIYvlHhllbdLTOhNOVik8mbXEKxjI6ml4k5WMYyTF0,10533
3
- langchain_mcp_tools/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
4
- langchain_mcp_tools-0.0.12.dist-info/LICENSE,sha256=CRC91e8v116gCpnp7h49oIa6_zjhxqnHFTREeoZFJwA,1072
5
- langchain_mcp_tools-0.0.12.dist-info/METADATA,sha256=GEuZxj_lQBBzdCSEU6OrV-ju8bMhWXyIV9bvtp1HUio,6934
6
- langchain_mcp_tools-0.0.12.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
7
- langchain_mcp_tools-0.0.12.dist-info/top_level.txt,sha256=aR_9V2A1Yt-Bca60KmndmGLUWb2wiM5IOG-Gkaf1dxY,20
8
- langchain_mcp_tools-0.0.12.dist-info/RECORD,,