How to Use the Documo MCP in LangChain

Q: How do I configure a LangChain agent to find specific Documo faxes?

You pass the searchfaxesbyrecipient tool to your LangChain agent inside the MultiServerMCPClient setup. The agent uses the recipient's phone number as an input argument to locate the exact transmission records from your mFax history.

Q: Can LangChain track failed Documo transmissions automatically?

Yes, your agent uses listfailedfaxdeliveries to spot errors inside a LangGraph loop. It checks the failure logs and then runs getfaxdetails to diagnose why the transmission did not go through.

Q: How does LangChain handle Documo user management?

Your agent calls listdocumousers to pull the active directory of users in your organization. You can chain this output to verify permission levels before routing incoming faxes to specific team members.

Q: How do I get a list of active fax numbers in my pipeline?

The agent calls listassignedfaxnumbers to get all numbers linked to your account. This lets your agent verify that an incoming request targets a valid, active number before processing.

Run multi-step Documo digital fax chains with your LangChain agents to verify transmissions and audit volume without manual work.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Documo MCP to LangChain

Create your Vinkius account to connect Documo 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 Documo with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step fax routing chains in LangChain

Your LangChain agent starts by using `list_received_digital_faxes` to catch incoming files and automatically feeds those outputs into subsequent chain links. The agent inspects the transmission details, parses the metadata, and routes the document to the right internal system without human intervention. Since LangChain chains are stateless by default, you configure this MCP Server to run these checks in sequence. You get clear LangSmith traces for every tool execution, showing you exactly when and why the agent triggered a specific fax run.

Audit transmission failures with LangChain agents

We use `list_failed_fax_deliveries` to identify transmission errors and feed those failures directly into LangChain decision loops. The agent evaluates the failure reason, checks the original recipient details, and schedules a retry or alerts your team. This setup eliminates the need for manual queue monitoring. Your agent handles the logic of checking `get_fax_details` on problematic transmissions and logs the outcome directly to your database.

Monitor account limits via this MCP Server

The `get_documo_account_metadata` tool provides your LangChain pipeline with immediate access to your current usage limits and account status. Your agent checks these numbers before executing high-volume operations to prevent API rate limit issues. By combining this MCP Server with LangChain's multi-server aggregation, you build a control loop that pauses transmissions if your limits are near capacity. You get structured, traceable metadata updates without writing custom API polling code.

Setup guide

Set up Documo 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 Documo 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({
    "documo-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 Documo 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 Documo. 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 Documo 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 Documo MCP in LangChain

You pass the `search_faxes_by_recipient` tool to your LangChain agent inside the MultiServerMCPClient setup. The agent uses the recipient's phone number as an input argument to locate the exact transmission records from your mFax history.

Yes, your agent uses `list_failed_fax_deliveries` to spot errors inside a LangGraph loop. It checks the failure logs and then runs `get_fax_details` to diagnose why the transmission did not go through.

Your agent calls `list_documo_users` to pull the active directory of users in your organization. You can chain this output to verify permission levels before routing incoming faxes to specific team members.

The agent calls `list_assigned_fax_numbers` to get all numbers linked to your account. This lets your agent verify that an incoming request targets a valid, active number before processing.

Absolutely. This server runs in an isolated V8 sandbox on Vinkius, meaning your transmission metadata and recipient numbers are processed in an ephemeral container. No fax files or recipient phone numbers are ever stored or cached on our servers.

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