How to Use the Join MCP in LlamaIndex

Q: How do I load Join recruiting tools into a LlamaIndex agent?

First, install llama-index-tools-mcp and initialize the basic MCP client. Then, wrap it in a McpToolSpec and call totoollistasync() to pass the tools directly into your FunctionAgent.

Q: Can LlamaIndex index the outputs of Join applications automatically?

Yes, you can configure your pipeline to run listapplications on a schedule and load the resulting text documents into a vector index. This keeps your search index updated with the latest applicant statuses and screening answers.

Q: How does LlamaIndex prevent hallucinations when querying Join data?

By feeding the actual JSON response from getcandidate directly into the LLM's context window, the framework forces the model to synthesize answers using only the provided candidate profile. This eliminates guesswork.

Q: Does this setup support filtering by specific departments?

You can use listdepartments to retrieve active teams and apply those names as metadata filters in your LlamaIndex vector store. This lets you restrict your search queries to engineering or sales candidates specifically.

Index your Join job descriptions and candidate profiles into LlamaIndex to run deep semantic searches across your pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Join MCP to LlamaIndex

Create your Vinkius account to connect Join to LlamaIndex 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 Join with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Join MCP Server outputs for semantic RAG search

Stop scrolling through endless resumes to find the right fit. LlamaIndex takes the live recruiting data returned by `list_candidates` and indexes the outputs of this MCP Server directly into your vector store, turning raw candidate profiles into a searchable knowledge base. When you search for specific skills, the system queries this index instead of making constant API calls. Your agent combines historical candidate data with live job requirements retrieved via `get_job` to find the best match based on actual experience rather than simple keyword matches.

Ground your hiring decisions in real application data

Hallucinations ruin recruiting pipelines. By using `get_application` to feed candidate answers and internal notes directly into your LlamaIndex query engine, you ensure that every summary your agent generates is grounded in actual facts. The framework uses the tool outputs as context documents for the LLM. If an agent claims a candidate has specific engineering experience, you can trace that claim directly back to the raw text returned by `list_departments` and `get_candidate`.

Query hiring managers and locations dynamically

Keeping track of who is hiring where gets complicated fast. LlamaIndex lets your agent run structured queries over your organizational structure by calling `list_users` and `list_locations` to map out active hiring teams. The engine parses these lists into structured index nodes. You can ask your agent which hiring managers are assigned to specific offices, and it will resolve the relationships instantly by combining the indexed metadata.

Setup guide

Set up Join MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Join MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Join tools.",
)
response = await agent.run("List recent Join data")

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 JOIN. 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 Join 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 Join MCP in LlamaIndex

First, install `llama-index-tools-mcp` and initialize the basic MCP client. Then, wrap it in a `McpToolSpec` and call `to_tool_list_async()` to pass the tools directly into your `FunctionAgent`.

Yes, you can configure your pipeline to run `list_applications` on a schedule and load the resulting text documents into a vector index. This keeps your search index updated with the latest applicant statuses and screening answers.

By feeding the actual JSON response from `get_candidate` directly into the LLM's context window, the framework forces the model to synthesize answers using only the provided candidate profile. This eliminates guesswork.

You can use `list_departments` to retrieve active teams and apply those names as metadata filters in your LlamaIndex vector store. This lets you restrict your search queries to engineering or sales candidates specifically.

All candidate contact details and application notes retrieved by this MCP server remain inside your local runtime environment. Vinkius secures the connection using isolated sandboxes, ensuring your sensitive candidate profiles are never exposed to external logs.

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