A tool that can give you freedom of using Brave search and content fetching using MCP and Langchan
Project description
Local test
Create venv
(base) ~/Documents/home_services/MCP/brave-mcp-langchain> uv sync
warning: Skipping installation of entry points (`project.scripts`) because this project is not packaged; to install entry points, set `tool.uv.package = true` or define a `build-system`
Using CPython 3.12.8 interpreter at: /home/oreo/miniconda3/python
Creating virtual environment at: .venv
Resolved 34 packages in 13ms
Installed 33 packages in 447ms
+ annotated-types==0.7.0
+ anyio==4.9.0
+ attrs==25.3.0
+ certifi==2025.6.15
+ click==8.2.1
+ colorama==0.4.6
+ h11==0.16.0
+ httpcore==1.0.9
+ httpx==0.28.1
+ httpx-sse==0.4.1
+ idna==3.10
+ jsonschema==4.24.0
+ jsonschema-specifications==2025.4.1
+ markdown-it-py==3.0.0
+ mcp==1.10.1
+ mdurl==0.1.2
+ pydantic==2.11.7
+ pydantic-core==2.33.2
+ pydantic-settings==2.10.1
+ pygments==2.19.2
+ python-dotenv==1.1.1
+ python-multipart==0.0.20
+ referencing==0.36.2
+ rich==14.0.0
+ rpds-py==0.26.0
+ shellingham==1.5.4
+ sniffio==1.3.1
+ sse-starlette==2.4.1
+ starlette==0.47.1
+ typer==0.16.0
+ typing-extensions==4.14.1
+ typing-inspection==0.4.1
+ uvicorn==0.35.0
Install package
(base) ~/Documents/home_services/MCP/brave-mcp-langchain> uv pip install -e .
Using Python 3.12.8 environment at: /home/oreo/miniconda3
Resolved 34 packages in 632ms
Built brave-mcp-langchain @ file:///home/oreo/Documents/home_services/MCP/brave-mcp-langchain
Prepared 1 package in 3.27s
Installed 1 package in 19ms
+ brave-mcp-langchain==0.1.0 (from file:///home/oreo/Documents/home_services/MCP/brave-mcp-langchain)
Add any dependency
uv add "beautifulsoup4>=4.13.3" "httpx>=0.28.1" "mcp[cli]>=1.3.0"
Run mcp inspector
mcp dev server.py
Run mcp server
uv run brave-mcp-langchain
OR
To run SSE mode
/usr/local/bin/uv run --directory /home/oreo/Documents/home_services/MCP/brave-mcp-langchain brave-mcp-langchain sse 5000
OR
To run STDIO mode
/usr/local/bin/uv run --directory /home/oreo/Documents/home_services/MCP/brave-mcp-langchain brave-mcp-langchain
Run SSE mode
python server.py sse 5000
MCP Setting
{
"mcpServers": {
"kubernetes": {
"autoApprove": [
"configuration_view",
"events_list",
"namespaces_list",
"pods_get",
"pods_log",
"pods_run"
],
"disabled": true,
"timeout": 60,
"type": "stdio",
"command": "npx",
"args": [
"-y",
"kubernetes-mcp-server@latest"
]
},
"k8s": {
"timeout": 60,
"type": "stdio",
"command": "C:\\Users\\oreo\\.local\\bin\\uv.EXE",
"args": [
"run",
"--with",
"kubernetes",
"--with",
"mcp[cli]",
"mcp",
"run",
"C:\\Users\\oreo\\dummy_sevrer.py"
]
},
"brave-mcp-langchain": {
"disabled": false,
"timeout": 60,
"type": "stdio",
"command": "C:\\Users\\oreo\\.local\\bin\\uv.EXE",
"args": [
"run",
"--directory",
"C:\\Users\\oreo\\Documents\\home_services\\MCP\\brave-mcp-langchain",
"brave-mcp-langchain"
]
}
}
}
Use installed dependencies
{
"mcpServers": {
"kubernetes": {
"autoApprove": [
"configuration_view",
"events_list",
"namespaces_list",
"pods_get",
"pods_log",
"pods_run"
],
"disabled": true,
"timeout": 60,
"type": "stdio",
"command": "npx",
"args": [
"-y",
"kubernetes-mcp-server@latest"
]
},
"k8s": {
"timeout": 60,
"type": "stdio",
"command": "C:\\Users\\oreo\\.local\\bin\\uv.EXE",
"args": [
"run",
"--with",
"kubernetes",
"--with",
"mcp[cli]",
"mcp",
"run",
"C:\\Users\\oreo\\dummy_sevrer.py"
]
},
"brave-mcp-langchain": {
"disabled": false,
"timeout": 60,
"type": "stdio",
"command": "C:\\Users\\oreo\\.local\\bin\\uv.EXE",
"args": [
"run",
"brave-mcp-langchain"
]
}
}
}
Use with Langchain
It can also be used as Langchain tool. Try below code to try
import httpx
import asyncio
from langchain.tools import Tool
from brave_mcp_langchain import brave_tool
async def test_search():
result = await brave_tool.search_tool.ainvoke({"query": "LangGraph overview", "max_results": 10})
print(result)
result = await brave_tool.fetch_content_tool.ainvoke({
"url": "https://iamatulsingh.github.io"
})
print(result)
asyncio.run(test_search())
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
brave_mcp_langchain-0.1.0.tar.gz
(47.8 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file brave_mcp_langchain-0.1.0.tar.gz.
File metadata
- Download URL: brave_mcp_langchain-0.1.0.tar.gz
- Upload date:
- Size: 47.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.8
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d3f81128cbc0211514497b9c1cbdd62341f74da3e2db24ed0250850dcec318e9
|
|
| MD5 |
2895058a8f9fb23282451addd44a6087
|
|
| BLAKE2b-256 |
5148c089756461209c49a6a9ceef2042b888fd386ef7b237521b3ebf41e3e394
|
File details
Details for the file brave_mcp_langchain-0.1.0-py3-none-any.whl.
File metadata
- Download URL: brave_mcp_langchain-0.1.0-py3-none-any.whl
- Upload date:
- Size: 7.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.8
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
853ac0e4b2cbd7f3be291dc6878d00332d713744046cffe586c88eb7c24cea07
|
|
| MD5 |
9c212ed1fdb31b316c6f9324f2edcdf0
|
|
| BLAKE2b-256 |
389d204284713912b0e4da664ede49718e36acfd4be400bbd310f734122ebaef
|