How to Use the Fibery MCP in LangChain

Q: How do I pass Fibery tools to a LangChain agent?

Install langchain-mcp-adapters and langgraph via pip. Initialize the MultiServerMCPClient with your Vinkius HTTP endpoint, call client.gettools(), and pass those tools directly to your createagent function.

Q: How does LangChain handle complex Fibery schemas?

The agent runs getschema first to understand your custom fields and databases. LangChain then uses this schema context to format its tool inputs, preventing validation errors when calling updateentity.

Run multi-step chains that query your Fibery workspace and update entities dynamically using LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fibery MCP to LangChain

Create your Vinkius account to connect Fibery 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 Fibery with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step Fibery chains with LangChain

This setup uses `get_schema` and `list_apps` to map out your workspace databases before kicking off any updates. Your chain reads the current structure, detects custom fields, and passes that exact context down to the next link. You do not have to hardcode database mappings because your agent figures out where the data belongs on the fly. LangSmith tracks every single tool call in the sequence, showing you the exact inputs and outputs of `query_entities`. If a chain fails to update a task, you can pinpoint whether the error occurred during the initial search or the final payload delivery. This transparency makes debugging complex multi-step MCP agent runs straightforward.

Auto-assign and comment on work items

The agent uses `list_users` to find the right team member and immediately applies `add_comment` to the target entity. This matches incoming bug reports or feature requests to active developers based on their current workload. Instead of manual triage, your agent handles the assignment and writes a detailed log directly inside the discussion thread. You can combine this toolset with external databases or Slack integrations using LangChain's vast ecosystem to combine MCP tools with communication channels. For instance, an incoming customer ticket can trigger a search across past workspace comments via `get_comments` before updating the status of a bug. It links your internal database operations with your external communication channels in a single runtime loop.

Self-correcting workspace updates

Your agent calls `update_entity` after validating the target's current state with `get_entity`. If the initial update fails due to a mismatched field type, the LangChain agent catches the API error, inspects the schema, and corrects its own payload. This self-correcting loop keeps your project management board clean without human intervention. You configure this using the `MultiServerMCPClient` with the Vinkius endpoint, allowing your agent to talk to this MCP server alongside other data sources. It lets you build a highly resilient pipeline where data integrity is checked at every step of the execution chain.

Setup guide

Set up Fibery 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 Fibery 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({
    "fibery-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 Fibery 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 Fibery. 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 Fibery 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 Fibery MCP in LangChain

Install `langchain-mcp-adapters` and `langgraph` via pip. Initialize the `MultiServerMCPClient` with your Vinkius HTTP endpoint, call `client.get_tools()`, and pass those tools directly to your `create_agent` function.

Yes, you can trace everything using LangSmith. Every call to `query_entities` or `create_entity` is logged with exact latency, token counts, and payloads.

The agent runs `get_schema` first to understand your custom fields and databases. LangChain then uses this schema context to format its tool inputs, preventing validation errors when calling `update_entity`.

The agent catches the error inside the chain. You can design a fallback path in your LangGraph workflow to inspect the error message, run a search with `search_entities`, and try the update again.

The server runs in a secure, zero-trust V8 sandbox on Vinkius. It only accesses your workspace schema and entity comments when your agent explicitly invokes tools like `get_schema` or `get_comments`, keeping your credentials and data isolated.

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