brave-mcp-langchain
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@brave-mcp-langchain search for LangGraph overview and fetch its content"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
brave-mcp-langchain
Create venv
uv syncRelated MCP server: Tagny MCP Server
Install package
uv pip install brave-mcp-langchainRun MCP server in STDIO mode
uvx brave-mcp-langchainTo run MCP server in SSE mode
uvx brave-mcp-langchain sse 5003MCP Setting
{
"mcpServers": {
"brave-mcp-langchain": {
"disabled": false,
"timeout": 60,
"type": "stdio",
"command": "uvx",
"args": [
"brave-mcp-langchain"
]
}
}
}Use as Langchain tool
It can also be used as Langchain tool. Below is how to validate tool.
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())Use with langchain example
import asyncio
from langchain.agents import initialize_agent
from langchain.agents.agent_types import AgentType
from langchain_ollama import ChatOllama
from brave_mcp_langchain import brave_tool
llm = ChatOllama(model="llama3.1:8b")
tools = [
brave_tool.search_tool,
brave_tool.fetch_content_tool
]
agent = initialize_agent(
tools=[brave_tool.search_tool, brave_tool.fetch_content_tool],
llm=llm,
agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION,
verbose=True
)
async def run_agent_query():
response = await agent.ainvoke(
"Search for 'iamatulsingh' overview, then fetch content from https://iamatulsingh.github.io"
)
print("\nAgent Response:")
print(response)
asyncio.run(run_agent_query())🧠Inspiration & Attribution
This project, brave-mcp-langchain, was inspired by and partially based on the excellent work in duckduckgo-mcp-server by @nickclyde. That project laid the groundwork for integrating DuckDuckGo search and content fetching into the MCP ecosystem.
While brave-mcp-langchain extends the concept to support Brave Search and LangChain workflows, several architectural ideas and implementation patterns were adapted from duckduckgo-mcp-server, which is licensed under the MIT License.
I'm grateful for the open-source community and contributors who make projects like this possible. If you’re interested in DuckDuckGo-based search tools, definitely check out the original repository!
Available Tools
2 toolsfetch_contentA
Fetch and parse content from a webpage URL.
Args:
url: The webpage URL to fetch content from
ctx: MCP context for logging
Inputs: url (required). Returns: result
searchC
Search Brave and return formatted results.
Args:
query: The search query string
max_results: Maximum number of results to return (default: 10)
ctx: MCP context for logging
Inputs: query (required), max_results. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools are completely distinct: one performs web searches, the other fetches webpage content. There is no overlap or confusion between their purposes.
Both names are verb-based and clear, but 'search' is a single verb while 'fetch_content' follows a verb_noun pattern, showing a minor inconsistency in naming convention.
With only 2 tools, the server feels thin for a search-related service. While these two cover the basic search-and-fetch workflow, the count is on the low end of the borderline range.
The core functionality of searching and fetching content is covered, but there are minor gaps such as lack of search result filtering options or pagination controls. Overall, the surface is adequate for simple search tasks.
Related MCP Connectors
Scrape, crawl and search the web for AI agents via MCP.
Web scraping, browser automation, screenshots and AI data extraction for AI agents via MCP.
Brave Search MCP — independent web index (no Google/Bing dependency)
Official Exa MCP for web search, content fetching, and multi-step research.
Related MCP Servers
AlicenseAqualityBmaintenanceAn MCP implementation that integrates the Brave Search API, providing comprehensive search capabilities including web, local business, image, video, news searches, and AI-powered summarization.949,475 npm1,583MIT- AlicenseNot gradedqualityDmaintenanceEnables web browsing capabilities for locally served LLMs through URL text fetching, link extraction, and web search using Brave and DuckDuckGo engines. Designed to enhance LLMs with real-time web access through the MCP protocol.MIT
- FlicenseBqualityDmaintenanceEnables web search capabilities through the Brave Search API, including web search, local POI lookups, and rich search results retrieval for MCP-compatible clients.4-
- FlicenseAqualityDmaintenanceEnables Brave Search via MCP, deployed on Railway for seamless integration with AI agents.6-