How to Use the Lancerkit MCP in LlamaIndex

Q: How do I load Lancerkit tools into a LlamaIndex MCP agent?

Install llama-index-tools-mcp. Set up your BasicMCPClient and wrap it in McpToolSpec. Await totoollistasync() and pass the array to your agent.

Q: Can LlamaIndex search my Lancerkit client metadata?

Yes. You run listclients to grab the workspace list, then getclient for specific details. LlamaIndex embeds those results for natural language querying later.

Q: Does the Lancerkit MCP integration require persistent storage?

No. You can fetch getstatus and listprojects on the fly. If you want semantic search, you index the outputs into a vector store of your choice.

Q: How do I restrict which tools LlamaIndex can call?

Use the allowedtools filter in your tool spec. You can grant access to listservices while blocking getinvoice entirely.

Index your freelance business data into LlamaIndex using Lancerkit.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lancerkit MCP to LlamaIndex

Create your Vinkius account to connect Lancerkit 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 Lancerkit with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vectorize Your Time Logs

Lancerkit feeds `get_time_logs` and `list_tasks` straight into your LlamaIndex vector stores. Your RAG application ingests these hours spent and creates a searchable knowledge base of your own work history. You stop guessing how long a feature took. You ask your agent about past performance. It queries the indexed data, pulls the exact recorded hours, and gives you an answer grounded in reality. No hallucinated estimates. Just raw metrics from your actual working sessions.

Semantic Invoice Search via MCP Server

Finding an old bill means running `list_invoices` and indexing the global pipeline statistics. LlamaIndex turns that raw JSON array into semantic nodes. You just type a natural language query and the engine handles the rest. Once it finds the match, the agent runs `get_invoice` to pull the specific payments and billings for that ID. You get the exact line items returned in plain text. It saves me at least three hours a week in administrative digging.

Grounded Project Context

Pulling project details uses `get_project` to fetch the single project ID details. LlamaIndex takes this output and embeds it alongside your local documentation. Your AI client now understands your codebase and your billing constraints simultaneously. Setup is dead simple. You install `llama-index-tools-mcp`, configure `BasicMCPClient`, and pass the tools to your `FunctionAgent`. You can even filter access using `allowed_tools` if you only want it reading `list_services` and nothing else.

Setup guide

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

Install `llama-index-tools-mcp`. Set up your `BasicMCPClient` and wrap it in `McpToolSpec`. Await `to_tool_list_async()` and pass the array to your agent.

Yes. You run `list_clients` to grab the workspace list, then `get_client` for specific details. LlamaIndex embeds those results for natural language querying later.

No. You can fetch `get_status` and `list_projects` on the fly. If you want semantic search, you index the outputs into a vector store of your choice.

Use the `allowed_tools` filter in your tool spec. You can grant access to `list_services` while blocking `get_invoice` entirely.

This MCP Server processes your billable service items and payment records. Vinkius enforces a zero-trust architecture where auth tokens are handled externally. The connection is entirely stateless, meaning your API keys never sit in a vulnerable database.

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