How to Use the DevDocs MCP in LangChain

Q: How do I load the DevDocs MCP Server in LangChain?

Use MultiServerMCPClient with an HTTP transport. Call client.gettools() and pass that array directly into your createagent setup.

Q: Can LangChain track the token usage of DevDocs tools?

Yes. LangSmith automatically traces every call to searchdocs and readpage. You see exactly how many tokens the Markdown response consumed.

Build ReAct agents in LangChain that query DevDocs natively, pulling raw documentation straight into your reasoning pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DevDocs MCP to LangChain

Create your Vinkius account to connect DevDocs to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup DevDocs with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain documentation lookups in LangChain

This MCP Server hooks DevDocs directly into your LangChain reasoning pipelines. When your ReAct agent hits an unknown API, it doesn't just guess. It pauses, executes `list_libraries` to find the target framework, and moves to the next step. You get full observability through LangSmith as this happens. Watch the exact token usage spike when your agent dumps the results of `read_page` into the context window. Turning raw Markdown retrieval into a traceable node changes how you debug.

Give ReAct agents targeted search

Letting an LLM blind-search the web for syntax wastes time and tokens. Your LangGraph nodes use `search_docs` to query the exact DevDocs index for the library you actually care about. The output feeds straight into the next tool call. If the search returns a specific manual page path, the agent immediately pipes that string into the reader tool. You dictate the exact order of operations.

Feed clean Markdown to your MCP Server

Ripping HTML from standard websites destroys your token limits. The `read_page` tool bypasses that garbage by returning cleanly formatted Markdown text directly from the DevDocs API. This matters when you build multi-step chains that require deep context. Your LangChain setup stays stateless by default, processing the raw documentation fast before passing the synthesized answer to the user.

Setup guide

Set up DevDocs MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes DevDocs tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "devdocs-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent DevDocs transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by DevDocs. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect DevDocs now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about DevDocs MCP in LangChain

Use `MultiServerMCPClient` with an HTTP transport. Call `client.get_tools()` and pass that array directly into your `create_agent` setup.

Yes. LangSmith automatically traces every call to `search_docs` and `read_page`. You see exactly how many tokens the Markdown response consumed.

They figure it out. If you prompt the agent correctly, it runs `list_libraries` first to grab the exact framework slug before attempting a search query.

Speed and accuracy. This setup targets the DevDocs internal index directly, returning clean Markdown instead of bloated DOM trees.

This integration only touches your specific API search strings and the resulting public documentation. LangChain routes those plain-text queries to the DevDocs endpoint without logging your proprietary source code.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript