langchain-mcp-tools 0.0.11__tar.gz → 0.0.12__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.
Files changed (14) hide show
  1. {langchain_mcp_tools-0.0.11 → langchain_mcp_tools-0.0.12}/PKG-INFO +8 -5
  2. {langchain_mcp_tools-0.0.11 → langchain_mcp_tools-0.0.12}/README.md +7 -4
  3. {langchain_mcp_tools-0.0.11 → langchain_mcp_tools-0.0.12}/langchain_mcp_tools/langchain_mcp_tools.py +3 -2
  4. {langchain_mcp_tools-0.0.11 → langchain_mcp_tools-0.0.12}/langchain_mcp_tools.egg-info/PKG-INFO +8 -5
  5. {langchain_mcp_tools-0.0.11 → langchain_mcp_tools-0.0.12}/pyproject.toml +1 -1
  6. {langchain_mcp_tools-0.0.11 → langchain_mcp_tools-0.0.12}/LICENSE +0 -0
  7. {langchain_mcp_tools-0.0.11 → langchain_mcp_tools-0.0.12}/langchain_mcp_tools/__init__.py +0 -0
  8. {langchain_mcp_tools-0.0.11 → langchain_mcp_tools-0.0.12}/langchain_mcp_tools/py.typed +0 -0
  9. {langchain_mcp_tools-0.0.11 → langchain_mcp_tools-0.0.12}/langchain_mcp_tools.egg-info/SOURCES.txt +0 -0
  10. {langchain_mcp_tools-0.0.11 → langchain_mcp_tools-0.0.12}/langchain_mcp_tools.egg-info/dependency_links.txt +0 -0
  11. {langchain_mcp_tools-0.0.11 → langchain_mcp_tools-0.0.12}/langchain_mcp_tools.egg-info/requires.txt +0 -0
  12. {langchain_mcp_tools-0.0.11 → langchain_mcp_tools-0.0.12}/langchain_mcp_tools.egg-info/top_level.txt +0 -0
  13. {langchain_mcp_tools-0.0.11 → langchain_mcp_tools-0.0.12}/setup.cfg +0 -0
  14. {langchain_mcp_tools-0.0.11 → langchain_mcp_tools-0.0.12}/tests/test_langchain_mcp_tools.py +0 -0
{langchain_mcp_tools-0.0.11 → langchain_mcp_tools-0.0.12}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.2
2
2
  Name: langchain-mcp-tools
3
- Version: 0.0.11
3
+ Version: 0.0.12
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
@@ -29,7 +29,7 @@ This package is intended to simplify the use of
29
29
  [Model Context Protocol (MCP)](https://modelcontextprotocol.io/)
30
30
  server tools with LangChain / Python.
31
31
 
32
- It contains a utility function `convertMcpToLangchainTools()`.
32
+ It contains a utility function `convert_mcp_to_langchain_tools()`.
33
33
  This function handles parallel initialization of specified multiple MCP servers
34
34
  and converts their available tools into a list of
35
35
  [LangChain-compatible tools](https://js.langchain.com/docs/how_to/tool_calling/).
@@ -112,14 +112,17 @@ to work successfully...
112
112
 
113
113
  I'm new to Python, so it is very possible that my ignorance is playing
114
114
  a big role here...
115
- I'll summarize the difficulties I faced below.
115
+ I'll summarize the difficulties I faced below.
116
+ The source code is available
117
+ [here](https://github.com/hideya/langchain-mcp-tools-py/blob/main/langchain_mcp_tools/langchain_mcp_tools.py).
116
118
  Any comments pointing out something I am missing would be greatly appreciated!
117
119
  [(comment here)](https://github.com/hideya/langchain-mcp-tools-ts/issues)
118
120
 
119
121
  1. Core Challenge:
120
122
  - Async resources management for `stdio_client` and `ClientSession` seems
121
- to rely exclusively on `asynccontextmanager` for cleanup with no manual
122
- cleanup options (based on the mcp python-sdk impl as of Jan 14, 2025)
123
+ to require relying exclusively on `asynccontextmanager` for cleanup with
124
+ no manual cleanup options
125
+ (based on [the mcp python-sdk impl as of Jan 14, 2025](https://github.com/modelcontextprotocol/python-sdk/tree/99727a9/src/mcp/client))
123
126
  - Initializing multiple MCP servers in parallel requires a dedicated
124
127
  `asyncio.Task` per server
125
128
  - Necessity of keeping sessions alive for later use after initialization
{langchain_mcp_tools-0.0.11 → langchain_mcp_tools-0.0.12}/README.md RENAMED
@@ -4,7 +4,7 @@ This package is intended to simplify the use of
4
4
  [Model Context Protocol (MCP)](https://modelcontextprotocol.io/)
5
5
  server tools with LangChain / Python.
6
6
 
7
- It contains a utility function `convertMcpToLangchainTools()`.
7
+ It contains a utility function `convert_mcp_to_langchain_tools()`.
8
8
  This function handles parallel initialization of specified multiple MCP servers
9
9
  and converts their available tools into a list of
10
10
  [LangChain-compatible tools](https://js.langchain.com/docs/how_to/tool_calling/).
@@ -87,14 +87,17 @@ to work successfully...
87
87
 
88
88
  I'm new to Python, so it is very possible that my ignorance is playing
89
89
  a big role here...
90
- I'll summarize the difficulties I faced below.
90
+ I'll summarize the difficulties I faced below.
91
+ The source code is available
92
+ [here](https://github.com/hideya/langchain-mcp-tools-py/blob/main/langchain_mcp_tools/langchain_mcp_tools.py).
91
93
  Any comments pointing out something I am missing would be greatly appreciated!
92
94
  [(comment here)](https://github.com/hideya/langchain-mcp-tools-ts/issues)
93
95
 
94
96
  1. Core Challenge:
95
97
  - Async resources management for `stdio_client` and `ClientSession` seems
96
- to rely exclusively on `asynccontextmanager` for cleanup with no manual
97
- cleanup options (based on the mcp python-sdk impl as of Jan 14, 2025)
98
+ to require relying exclusively on `asynccontextmanager` for cleanup with
99
+ no manual cleanup options
100
+ (based on [the mcp python-sdk impl as of Jan 14, 2025](https://github.com/modelcontextprotocol/python-sdk/tree/99727a9/src/mcp/client))
98
101
  - Initializing multiple MCP servers in parallel requires a dedicated
99
102
  `asyncio.Task` per server
100
103
  - Necessity of keeping sessions alive for later use after initialization
{langchain_mcp_tools-0.0.11 → langchain_mcp_tools-0.0.12}/langchain_mcp_tools/langchain_mcp_tools.py RENAMED
@@ -38,8 +38,9 @@ The key aspects are:
38
38
 
39
39
  1. Core Challenge:
40
40
  - Async resources management for `stdio_client` and `ClientSession` seems
41
- to rely exclusively on `asynccontextmanager` for cleanup with no manual
42
- cleanup options (based on the mcp python-sdk impl as of Jan 14, 2025)
41
+ to require relying exclusively on `asynccontextmanager` for cleanup with
42
+ no manual cleanup options
43
+ (based on [the mcp python-sdk impl as of Jan 14, 2025](https://github.com/modelcontextprotocol/python-sdk/tree/99727a9/src/mcp/client))
43
44
  - Initializing multiple MCP servers in parallel requires a dedicated
44
45
  `asyncio.Task` per server
45
46
  - Necessity of keeping sessions alive for later use after initialization
{langchain_mcp_tools-0.0.11 → langchain_mcp_tools-0.0.12}/langchain_mcp_tools.egg-info/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.2
2
2
  Name: langchain-mcp-tools
3
- Version: 0.0.11
3
+ Version: 0.0.12
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
@@ -29,7 +29,7 @@ This package is intended to simplify the use of
29
29
  [Model Context Protocol (MCP)](https://modelcontextprotocol.io/)
30
30
  server tools with LangChain / Python.
31
31
 
32
- It contains a utility function `convertMcpToLangchainTools()`.
32
+ It contains a utility function `convert_mcp_to_langchain_tools()`.
33
33
  This function handles parallel initialization of specified multiple MCP servers
34
34
  and converts their available tools into a list of
35
35
  [LangChain-compatible tools](https://js.langchain.com/docs/how_to/tool_calling/).
@@ -112,14 +112,17 @@ to work successfully...
112
112
 
113
113
  I'm new to Python, so it is very possible that my ignorance is playing
114
114
  a big role here...
115
- I'll summarize the difficulties I faced below.
115
+ I'll summarize the difficulties I faced below.
116
+ The source code is available
117
+ [here](https://github.com/hideya/langchain-mcp-tools-py/blob/main/langchain_mcp_tools/langchain_mcp_tools.py).
116
118
  Any comments pointing out something I am missing would be greatly appreciated!
117
119
  [(comment here)](https://github.com/hideya/langchain-mcp-tools-ts/issues)
118
120
 
119
121
  1. Core Challenge:
120
122
  - Async resources management for `stdio_client` and `ClientSession` seems
121
- to rely exclusively on `asynccontextmanager` for cleanup with no manual
122
- cleanup options (based on the mcp python-sdk impl as of Jan 14, 2025)
123
+ to require relying exclusively on `asynccontextmanager` for cleanup with
124
+ no manual cleanup options
125
+ (based on [the mcp python-sdk impl as of Jan 14, 2025](https://github.com/modelcontextprotocol/python-sdk/tree/99727a9/src/mcp/client))
123
126
  - Initializing multiple MCP servers in parallel requires a dedicated
124
127
  `asyncio.Task` per server
125
128
  - Necessity of keeping sessions alive for later use after initialization
{langchain_mcp_tools-0.0.11 → langchain_mcp_tools-0.0.12}/pyproject.toml RENAMED
@@ -1,6 +1,6 @@
1
1
  [project]
2
2
  name = "langchain-mcp-tools"
3
- version = "0.0.11"
3
+ version = "0.0.12"
4
4
  description = "Model Context Protocol (MCP) To LangChain Tools Conversion Utility"
5
5
  readme = "README.md"
6
6
  requires-python = ">=3.11"