How to Use the Firefish MCP in LangChain

Q: How do I set up the Firefish integration in LangChain?

Install the adapter using pip install langchain-mcp-adapters langgraph. Then, initialize MultiServerMCPClient pointing to your Vinkius endpoint, fetch the tools, and pass them to your agent.

Q: Can a LangChain agent create records in Firefish?

Yes, the agent can call createcandidate directly during a chain run. It uses the tool schema to format the input data correctly before writing to your CRM.

Q: Can I limit which Firefish tools my LangChain agent can access?

Yes, you can filter the tool list returned by gettools() before passing them to your createagent function. This prevents the agent from running write operations if you only want it to read data.

Run multi-step recruitment chains in LangChain using live CRM data from the Firefish MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Firefish MCP to LangChain

Create your Vinkius account to connect Firefish 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 Firefish with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain candidate discovery directly to hiring pipelines

Stop copying resumes manually. This LangChain setup lets your ReAct agent fetch raw records with `list_candidates` and immediately feed them into the next chain step to match open roles. You build the pipeline, and the agent decides when to pull details using `get_candidate` based on real-time feedback from your LangSmith traces. Because LangChain handles state through custom runnables, you can pass the output of `list_jobs` directly into a prompt template that evaluates candidate fit. No intermediate glue code is needed to bridge your Firefish workspace and your LLM decision chains.

Trace LangChain agent actions in LangSmith

Debugging agentic hiring loops is a nightmare without visibility. When your LangChain agent calls `list_actions` or updates records with `create_candidate`, every single token and tool input is logged in your LangSmith dashboard. You see exactly why an agent chose a specific contact or why it flagged a placement. This transparency lets you refine your prompts without guessing. If the agent fails to fetch the right company details using `get_company`, the trace shows whether the issue was the tool schema or the agent's reasoning chain.

Aggregate multiple MCP servers for client onboarding

Hiring doesn't happen in a vacuum. By using the `MultiServerMCPClient` in LangChain, you can combine this Firefish integration with your email or calendar servers. Your agent can run `list_placements` to find new hires, then immediately trigger a separate server to draft onboarding emails. It makes complex recruitment workflows feel like a single cohesive system. The MCP Server acts as the central coordinator, pulling from `get_contact` to ensure the right people get notified at the right step of the hiring sequence.

Setup guide

Set up Firefish 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 Firefish 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({
    "firefish-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 Firefish 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 Firefish. 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 Firefish 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 Firefish MCP in LangChain

Install the adapter using `pip install langchain-mcp-adapters langgraph`. Then, initialize `MultiServerMCPClient` pointing to your Vinkius endpoint, fetch the tools, and pass them to your agent.

Yes, the agent can call `create_candidate` directly during a chain run. It uses the tool schema to format the input data correctly before writing to your CRM.

By default, the connection is stateless. If you need to maintain conversational context across multiple candidate searches, use `client.session()` to keep the session active.

Yes, you can filter the tool list returned by `get_tools()` before passing them to your `create_agent` function. This prevents the agent from running write operations if you only want it to read data.

Your candidate profiles, job descriptions, and placement records stay inside Vinkius's secure V8 sandbox. LangChain only receives the specific data payloads returned by tools like `get_candidate` or `list_placements` over an encrypted connection, keeping your CRM credentials completely hidden.

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