langchain-mcp-tools 0.2.0__tar.gz → 0.2.2__tar.gz

{langchain_mcp_tools-0.2.0/src/langchain_mcp_tools.egg-info → langchain_mcp_tools-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: langchain-mcp-tools
-Version: 0.2.0
+Version: 0.2.2
 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
@@ -30,11 +30,14 @@ This package is intended to simplify the use of
 server tools with LangChain / Python.
 
 [Model Context Protocol (MCP)](https://modelcontextprotocol.io/),
-an open source technology
+an open standard
 [announced by Anthropic](https://www.anthropic.com/news/model-context-protocol),
 dramatically expands LLM’s scope
 by enabling external tool and resource integration, including
-Google Drive, Slack, Notion, Spotify, Docker, PostgreSQL, and more…
+GitHub, Google Drive, Slack, Notion, Spotify, Docker, PostgreSQL, and more…
+
+MCP is likely to become the de facto industry standard as 
+[OpenAI has announced its adoption](https://techcrunch.com/2025/03/26/openai-adopts-rival-anthropics-standard-for-connecting-ai-models-to-data).
 
 Over 2000 functional components available as MCP servers:
 
@@ -66,6 +69,9 @@ pip install langchain-mcp-tools
 
 ## Quick Start
 
+A minimal but complete working usage example can be found
+[in this example in the langchain-mcp-tools-py-usage repo](https://github.com/hideya/langchain-mcp-tools-py-usage/blob/main/src/example.py)
+
 `convert_mcp_to_langchain_tools()` utility function accepts MCP server configurations
 that follow the same structure as
 [Claude for Desktop](https://modelcontextprotocol.io/quickstart/user),
@@ -102,8 +108,8 @@ 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-3-7-sonnet-latest',
-    model_provider='anthropic'
+    model="claude-3-7-sonnet-latest",
+    model_provider="anthropic"
 )
 
 # from langgraph.prebuilt import create_react_agent
@@ -113,9 +119,6 @@ agent = create_react_agent(
 )
 ```
 
-Find complete, minimal working usage examples
-[here](https://github.com/hideya/langchain-mcp-tools-py-usage/blob/main/src/example.py)
-
 For hands-on experimentation with MCP server integration,
 try [this LangChain application built with the utility](https://github.com/hideya/mcp-client-langchain-py)
 
@@ -138,14 +141,32 @@ For detailed information on how to use this library, please refer to the followi
     },
 ```
 
-Note that the key name `"url"` may be changed in the future to match
+Note that the key `"url"` may be changed in the future to match
 the MCP server configurations used by Claude for Desktop once
 it introduces remote server support.
 
+A usage example can be found [here](https://github.com/hideya/langchain-mcp-tools-py-usage/blob/cf96ddc43750708ef3b244bad95714f0f2fe1d28/src/example.py#L43-L54)
+
+### Passing HTTP Headers to SSE Connection
+
+A new key `"headers"` has been introduced to pass HTTP headers to the SSE (Server-Sent Events) connection.  
+It takes  `dict[str, str]` and is primarily intended to support SSE MCP servers
+that require authentication via bearer tokens or other custom headers.
+
+```python
+    "sse-server-name": {
+        "url": f"http://{sse_server_host}:{sse_server_port}/..."
+        "headers": {"Authorization": f"Bearer {bearer_token}"}
+    },
+```
+
+The key name `header` is derived from the Python SDK
+[`sse_client()`](https://github.com/modelcontextprotocol/python-sdk/blob/babb477dffa33f46cdc886bc885eb1d521151430/src/mcp/client/sse.py#L24) argument name.
+
 ### Working Directory Configuration for Local MCP Servers
 
-The working directory that is used when spawning a local MCP server
-can be specified with the `cwd` key as follows:
+The working directory that is used when spawning a local (stdio) MCP server
+can be specified with the `"cwd"` key as follows:
 
 ```python
     "local-server-name": {
@@ -155,10 +176,13 @@ can be specified with the `cwd` key as follows:
     },
 ```
 
-### Configuration for MCP Server stderr Redirection
+The key name `cwd` is derived from
+Python SDK's [`StdioServerParameters`](https://github.com/modelcontextprotocol/python-sdk/blob/babb477dffa33f46cdc886bc885eb1d521151430/src/mcp/client/stdio/__init__.py#L76-L77).
+
+### Configuration for Local MCP Server `stderr` Redirection
 
-A new key `errlog` has been introduced in to specify a file-like object
-to which MCP server's stderr is redirected.
+A new key `"errlog"` has been introduced to specify a file-like object
+to which local (stdio) MCP server's stderr is redirected.
 
 ```python
     log_path = f"mcp-server-{server_name}.log"
@@ -166,18 +190,22 @@ to which MCP server's stderr is redirected.
     mcp_servers[server_name]["errlog"] = log_file
 ```
 
-**NOTE: Why the key name `errlog` for `server_config` was chosen:**  
+A usage example can be found [here](
+https://github.com/hideya/langchain-mcp-tools-py-usage/blob/cf96ddc43750708ef3b244bad95714f0f2fe1d28/src/example.py#L91-L108)
+
+**NOTE: Why the key name `errlog` was chosen:**  
 Unlike TypeScript SDK's `StdioServerParameters`, the Python
-SDK's `StdioServerParameters` doesn't include `stderr: int`.
-Instead, it calls `stdio_client()` with a separate argument
-`errlog: TextIO`.  I once included `stderr: int` for
+SDK's `StdioServerParameters` doesn't include `stderr: int`.  
+Instead, it calls [`stdio_client()` with a separate argument
+`errlog: TextIO`](https://github.com/modelcontextprotocol/python-sdk/blob/babb477dffa33f46cdc886bc885eb1d521151430/src/mcp/client/stdio/__init__.py#L96).  
+I once included `stderr: int` for
 compatibility with the TypeScript version, but decided to
 follow the Python SDK more closely.
 
 ## Limitations
 
 - Currently, only text results of tool calls are supported.
-- Fatures other than [Tools](https://modelcontextprotocol.io/docs/concepts/tools) are not supported.
+- MCP features other than [Tools](https://modelcontextprotocol.io/docs/concepts/tools) are not supported.
 
 ## Change Log
 

{langchain_mcp_tools-0.2.0 → langchain_mcp_tools-0.2.2}/README.md

@@ -5,11 +5,14 @@ This package is intended to simplify the use of
 server tools with LangChain / Python.
 
 [Model Context Protocol (MCP)](https://modelcontextprotocol.io/),
-an open source technology
+an open standard
 [announced by Anthropic](https://www.anthropic.com/news/model-context-protocol),
 dramatically expands LLM’s scope
 by enabling external tool and resource integration, including
-Google Drive, Slack, Notion, Spotify, Docker, PostgreSQL, and more…
+GitHub, Google Drive, Slack, Notion, Spotify, Docker, PostgreSQL, and more…
+
+MCP is likely to become the de facto industry standard as 
+[OpenAI has announced its adoption](https://techcrunch.com/2025/03/26/openai-adopts-rival-anthropics-standard-for-connecting-ai-models-to-data).
 
 Over 2000 functional components available as MCP servers:
 
@@ -41,6 +44,9 @@ pip install langchain-mcp-tools
 
 ## Quick Start
 
+A minimal but complete working usage example can be found
+[in this example in the langchain-mcp-tools-py-usage repo](https://github.com/hideya/langchain-mcp-tools-py-usage/blob/main/src/example.py)
+
 `convert_mcp_to_langchain_tools()` utility function accepts MCP server configurations
 that follow the same structure as
 [Claude for Desktop](https://modelcontextprotocol.io/quickstart/user),
@@ -77,8 +83,8 @@ 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-3-7-sonnet-latest',
-    model_provider='anthropic'
+    model="claude-3-7-sonnet-latest",
+    model_provider="anthropic"
 )
 
 # from langgraph.prebuilt import create_react_agent
@@ -88,9 +94,6 @@ agent = create_react_agent(
 )
 ```
 
-Find complete, minimal working usage examples
-[here](https://github.com/hideya/langchain-mcp-tools-py-usage/blob/main/src/example.py)
-
 For hands-on experimentation with MCP server integration,
 try [this LangChain application built with the utility](https://github.com/hideya/mcp-client-langchain-py)
 
@@ -113,14 +116,32 @@ For detailed information on how to use this library, please refer to the followi
     },
 ```
 
-Note that the key name `"url"` may be changed in the future to match
+Note that the key `"url"` may be changed in the future to match
 the MCP server configurations used by Claude for Desktop once
 it introduces remote server support.
 
+A usage example can be found [here](https://github.com/hideya/langchain-mcp-tools-py-usage/blob/cf96ddc43750708ef3b244bad95714f0f2fe1d28/src/example.py#L43-L54)
+
+### Passing HTTP Headers to SSE Connection
+
+A new key `"headers"` has been introduced to pass HTTP headers to the SSE (Server-Sent Events) connection.  
+It takes  `dict[str, str]` and is primarily intended to support SSE MCP servers
+that require authentication via bearer tokens or other custom headers.
+
+```python
+    "sse-server-name": {
+        "url": f"http://{sse_server_host}:{sse_server_port}/..."
+        "headers": {"Authorization": f"Bearer {bearer_token}"}
+    },
+```
+
+The key name `header` is derived from the Python SDK
+[`sse_client()`](https://github.com/modelcontextprotocol/python-sdk/blob/babb477dffa33f46cdc886bc885eb1d521151430/src/mcp/client/sse.py#L24) argument name.
+
 ### Working Directory Configuration for Local MCP Servers
 
-The working directory that is used when spawning a local MCP server
-can be specified with the `cwd` key as follows:
+The working directory that is used when spawning a local (stdio) MCP server
+can be specified with the `"cwd"` key as follows:
 
 ```python
     "local-server-name": {
@@ -130,10 +151,13 @@ can be specified with the `cwd` key as follows:
     },
 ```
 
-### Configuration for MCP Server stderr Redirection
+The key name `cwd` is derived from
+Python SDK's [`StdioServerParameters`](https://github.com/modelcontextprotocol/python-sdk/blob/babb477dffa33f46cdc886bc885eb1d521151430/src/mcp/client/stdio/__init__.py#L76-L77).
+
+### Configuration for Local MCP Server `stderr` Redirection
 
-A new key `errlog` has been introduced in to specify a file-like object
-to which MCP server's stderr is redirected.
+A new key `"errlog"` has been introduced to specify a file-like object
+to which local (stdio) MCP server's stderr is redirected.
 
 ```python
     log_path = f"mcp-server-{server_name}.log"
@@ -141,18 +165,22 @@ to which MCP server's stderr is redirected.
     mcp_servers[server_name]["errlog"] = log_file
 ```
 
-**NOTE: Why the key name `errlog` for `server_config` was chosen:**  
+A usage example can be found [here](
+https://github.com/hideya/langchain-mcp-tools-py-usage/blob/cf96ddc43750708ef3b244bad95714f0f2fe1d28/src/example.py#L91-L108)
+
+**NOTE: Why the key name `errlog` was chosen:**  
 Unlike TypeScript SDK's `StdioServerParameters`, the Python
-SDK's `StdioServerParameters` doesn't include `stderr: int`.
-Instead, it calls `stdio_client()` with a separate argument
-`errlog: TextIO`.  I once included `stderr: int` for
+SDK's `StdioServerParameters` doesn't include `stderr: int`.  
+Instead, it calls [`stdio_client()` with a separate argument
+`errlog: TextIO`](https://github.com/modelcontextprotocol/python-sdk/blob/babb477dffa33f46cdc886bc885eb1d521151430/src/mcp/client/stdio/__init__.py#L96).  
+I once included `stderr: int` for
 compatibility with the TypeScript version, but decided to
 follow the Python SDK more closely.
 
 ## Limitations
 
 - Currently, only text results of tool calls are supported.
-- Fatures other than [Tools](https://modelcontextprotocol.io/docs/concepts/tools) are not supported.
+- MCP features other than [Tools](https://modelcontextprotocol.io/docs/concepts/tools) are not supported.
 
 ## Change Log
 

{langchain_mcp_tools-0.2.0 → langchain_mcp_tools-0.2.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "langchain-mcp-tools"
-version = "0.2.0"
+version = "0.2.2"
 description = "Model Context Protocol (MCP) To LangChain Tools Conversion Utility"
 keywords = [
     "modelcontextprotocol",

{langchain_mcp_tools-0.2.0 → langchain_mcp_tools-0.2.2}/src/langchain_mcp_tools/langchain_mcp_tools.py

@@ -40,17 +40,14 @@ except ImportError as e:
 class McpServerCommandBasedConfig(TypedDict):
     command: str
     args: NotRequired[list[str] | None]
-    env:  NotRequired[dict[str, str] | None]
+    env: NotRequired[dict[str, str] | None]
     cwd: NotRequired[str | None]
     errlog: NotRequired[TextIO | None]
 
 
 class McpServerUrlBasedConfig(TypedDict):
     url: str
-    args: NotRequired[list[str] | None]
-    env:  NotRequired[dict[str, str] | None]
-    cwd: NotRequired[str | None]
-    errlog: NotRequired[TextIO | None]
+    headers: NotRequired[dict[str, str] | None]
 
 
 McpServerConfig = McpServerCommandBasedConfig | McpServerUrlBasedConfig
@@ -103,12 +100,13 @@ async def spawn_mcp_server_and_get_transport(
                     f'initializing with: {server_config}')
 
         url_str = str(server_config.get('url'))  # None becomes 'None'
+        headers = server_config.get("headers", None)
         # no exception thrown even for a malformed URL
         url_scheme = urlparse(url_str).scheme
 
         if url_scheme in ('http', 'https'):
             transport = await exit_stack.enter_async_context(
-                sse_client(url_str)
+                sse_client(url_str, headers=headers)
             )
 
         elif url_scheme in ('ws', 'wss'):

{langchain_mcp_tools-0.2.0 → langchain_mcp_tools-0.2.2/src/langchain_mcp_tools.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: langchain-mcp-tools
-Version: 0.2.0
+Version: 0.2.2
 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
@@ -30,11 +30,14 @@ This package is intended to simplify the use of
 server tools with LangChain / Python.
 
 [Model Context Protocol (MCP)](https://modelcontextprotocol.io/),
-an open source technology
+an open standard
 [announced by Anthropic](https://www.anthropic.com/news/model-context-protocol),
 dramatically expands LLM’s scope
 by enabling external tool and resource integration, including
-Google Drive, Slack, Notion, Spotify, Docker, PostgreSQL, and more…
+GitHub, Google Drive, Slack, Notion, Spotify, Docker, PostgreSQL, and more…
+
+MCP is likely to become the de facto industry standard as 
+[OpenAI has announced its adoption](https://techcrunch.com/2025/03/26/openai-adopts-rival-anthropics-standard-for-connecting-ai-models-to-data).
 
 Over 2000 functional components available as MCP servers:
 
@@ -66,6 +69,9 @@ pip install langchain-mcp-tools
 
 ## Quick Start
 
+A minimal but complete working usage example can be found
+[in this example in the langchain-mcp-tools-py-usage repo](https://github.com/hideya/langchain-mcp-tools-py-usage/blob/main/src/example.py)
+
 `convert_mcp_to_langchain_tools()` utility function accepts MCP server configurations
 that follow the same structure as
 [Claude for Desktop](https://modelcontextprotocol.io/quickstart/user),
@@ -102,8 +108,8 @@ 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-3-7-sonnet-latest',
-    model_provider='anthropic'
+    model="claude-3-7-sonnet-latest",
+    model_provider="anthropic"
 )
 
 # from langgraph.prebuilt import create_react_agent
@@ -113,9 +119,6 @@ agent = create_react_agent(
 )
 ```
 
-Find complete, minimal working usage examples
-[here](https://github.com/hideya/langchain-mcp-tools-py-usage/blob/main/src/example.py)
-
 For hands-on experimentation with MCP server integration,
 try [this LangChain application built with the utility](https://github.com/hideya/mcp-client-langchain-py)
 
@@ -138,14 +141,32 @@ For detailed information on how to use this library, please refer to the followi
     },
 ```
 
-Note that the key name `"url"` may be changed in the future to match
+Note that the key `"url"` may be changed in the future to match
 the MCP server configurations used by Claude for Desktop once
 it introduces remote server support.
 
+A usage example can be found [here](https://github.com/hideya/langchain-mcp-tools-py-usage/blob/cf96ddc43750708ef3b244bad95714f0f2fe1d28/src/example.py#L43-L54)
+
+### Passing HTTP Headers to SSE Connection
+
+A new key `"headers"` has been introduced to pass HTTP headers to the SSE (Server-Sent Events) connection.  
+It takes  `dict[str, str]` and is primarily intended to support SSE MCP servers
+that require authentication via bearer tokens or other custom headers.
+
+```python
+    "sse-server-name": {
+        "url": f"http://{sse_server_host}:{sse_server_port}/..."
+        "headers": {"Authorization": f"Bearer {bearer_token}"}
+    },
+```
+
+The key name `header` is derived from the Python SDK
+[`sse_client()`](https://github.com/modelcontextprotocol/python-sdk/blob/babb477dffa33f46cdc886bc885eb1d521151430/src/mcp/client/sse.py#L24) argument name.
+
 ### Working Directory Configuration for Local MCP Servers
 
-The working directory that is used when spawning a local MCP server
-can be specified with the `cwd` key as follows:
+The working directory that is used when spawning a local (stdio) MCP server
+can be specified with the `"cwd"` key as follows:
 
 ```python
     "local-server-name": {
@@ -155,10 +176,13 @@ can be specified with the `cwd` key as follows:
     },
 ```
 
-### Configuration for MCP Server stderr Redirection
+The key name `cwd` is derived from
+Python SDK's [`StdioServerParameters`](https://github.com/modelcontextprotocol/python-sdk/blob/babb477dffa33f46cdc886bc885eb1d521151430/src/mcp/client/stdio/__init__.py#L76-L77).
+
+### Configuration for Local MCP Server `stderr` Redirection
 
-A new key `errlog` has been introduced in to specify a file-like object
-to which MCP server's stderr is redirected.
+A new key `"errlog"` has been introduced to specify a file-like object
+to which local (stdio) MCP server's stderr is redirected.
 
 ```python
     log_path = f"mcp-server-{server_name}.log"
@@ -166,18 +190,22 @@ to which MCP server's stderr is redirected.
     mcp_servers[server_name]["errlog"] = log_file
 ```
 
-**NOTE: Why the key name `errlog` for `server_config` was chosen:**  
+A usage example can be found [here](
+https://github.com/hideya/langchain-mcp-tools-py-usage/blob/cf96ddc43750708ef3b244bad95714f0f2fe1d28/src/example.py#L91-L108)
+
+**NOTE: Why the key name `errlog` was chosen:**  
 Unlike TypeScript SDK's `StdioServerParameters`, the Python
-SDK's `StdioServerParameters` doesn't include `stderr: int`.
-Instead, it calls `stdio_client()` with a separate argument
-`errlog: TextIO`.  I once included `stderr: int` for
+SDK's `StdioServerParameters` doesn't include `stderr: int`.  
+Instead, it calls [`stdio_client()` with a separate argument
+`errlog: TextIO`](https://github.com/modelcontextprotocol/python-sdk/blob/babb477dffa33f46cdc886bc885eb1d521151430/src/mcp/client/stdio/__init__.py#L96).  
+I once included `stderr: int` for
 compatibility with the TypeScript version, but decided to
 follow the Python SDK more closely.
 
 ## Limitations
 
 - Currently, only text results of tool calls are supported.
-- Fatures other than [Tools](https://modelcontextprotocol.io/docs/concepts/tools) are not supported.
+- MCP features other than [Tools](https://modelcontextprotocol.io/docs/concepts/tools) are not supported.
 
 ## Change Log