How to Use the Firefish MCP in LlamaIndex

Q: How do I connect LlamaIndex to the Firefish MCP Server?

Install the MCP tool package via pip install llama-index-tools-mcp. Initialize BasicMCPClient with your Vinkius URL, wrap it in McpToolSpec, and convert it using totoollistasync().

Q: Can I run semantic search over Firefish data using LlamaIndex?

Yes, you can use listcandidates to pull records, index them into a vector database, and perform semantic queries. This lets you find candidates based on skills and experience rather than exact keyword matches.

Q: How does the LlamaIndex agent decide to use the Firefish MCP Server?

The FunctionAgent evaluates user queries against the tool descriptions. If a user asks about active roles, the agent automatically triggers listjobs to fetch the necessary data.

Index live Firefish CRM data into LlamaIndex vector stores using this 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 LlamaIndex

Create your Vinkius account to connect Firefish 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 Firefish with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a queryable index of your hiring pipeline with LlamaIndex

Stop guessing which candidates fit your open roles. This LlamaIndex integration lets you pull active mandates using `list_jobs` and index them directly into your local vector store. Your RAG pipeline can then query this index to match incoming applications without manual screening. By grounding your queries in actual CRM data from `get_job`, your agent avoids making up job requirements. It searches against actual, active mandates instead of relying on outdated training data.

Ground candidate searches in real-time CRM data

Traditional search filters in recruitment CRMs are too rigid. With this MCP Server, your LlamaIndex agent can run `list_candidates` to ingest profiles and convert them into searchable vector embeddings. This lets you run semantic searches like finding developers who transitioned into product management across your talent pool. The agent uses `get_candidate` to fetch full profiles on demand, ensuring your vector store stays updated. It eliminates the gap between your static database and your AI's understanding of your talent pipeline.

Analyze placement trends using LlamaIndex RAG

Spotting patterns in your historical hiring data is tough when it's locked in a database. Use LlamaIndex to query your placement history by letting the agent ingest records from `list_placements` and `list_companies`. You can ask complex questions about which clients hire the fastest or which sectors are growing. LlamaIndex indexes these tool outputs so you don't have to write complex SQL queries. Your agent parses the raw data, identifies trends, and presents structured insights directly in your terminal.

Setup guide

Set up Firefish 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 Firefish 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 Firefish tools.",
)
response = await agent.run("List recent Firefish 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 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 LlamaIndex

Install the MCP tool package via `pip install llama-index-tools-mcp`. Initialize `BasicMCPClient` with your Vinkius URL, wrap it in `McpToolSpec`, and convert it using `to_tool_list_async()`.

Yes, you can use `list_candidates` to pull records, index them into a vector database, and perform semantic queries. This lets you find candidates based on skills and experience rather than exact keyword matches.

The `FunctionAgent` evaluates user queries against the tool descriptions. If a user asks about active roles, the agent automatically triggers `list_jobs` to fetch the necessary data.

Yes, if your agent needs to add a new profile, it can invoke `create_candidate` with the structured arguments generated during the conversation.

Your recruitment database remains isolated behind Vinkius's zero-trust gateway. LlamaIndex only indexes the specific JSON payloads returned by tools like `get_candidate` or `list_contacts`, ensuring your master CRM credentials are never exposed to the LLM.

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