How to Use the Sally MCP in LangChain

Q: Can Sally handle task updates inside a LangChain chain?

Yes. The agent calls updatetask based on the logic you define. It works just like any other function call.

Connect LangChain agents to your frontline teams. Sync tasks and comments directly into your multi-step reasoning pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sally MCP to LangChain

Create your Vinkius account to connect Sally to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Sally with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain task management with LangChain

Feed `list_tasks` results directly into your agent's reasoning chain. The model evaluates current project status before deciding whether to trigger an update. Your agent parses the output of `get_task` to determine the next logical step in the pipeline. It maintains state across calls to ensure task dependencies are tracked correctly.

Automate frontline communication loops

Use `add_comment` as a final node in your LangChain execution graph. Once the agent completes a logic check, it posts updates back to the team automatically. This creates a closed-loop system where the MCP Server acts as both a data source and an output sink. You get full visibility into how the agent interacts with your workspace.

Real-time project reporting for agents

Query `get_timesheet_report` to gather data for your LangChain analysis. The agent pulls raw hours from the workspace to generate summaries without manual intervention. It handles the data aggregation internally. Your chain remains clean while the agent handles the heavy lifting of parsing complex timesheet structures.

Setup guide

Set up Sally 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 Sally 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({
    "sally-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 Sally 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 Sally. 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.