How to Use the Leiga MCP in LlamaIndex

Q: How do I install the Leiga MCP Server tool for LlamaIndex?

Run pip install llama-index-tools-mcp to get the necessary package. Initialize the BasicMCPClient with the Vinkius URL, convert it to a tool spec, and pass it to your agent.

Q: Can I use LlamaIndex to search my Leiga tasks semantically?

Yes, you can index the output of listtasks into a vector store. This lets you search for similar tickets or find duplicate bug reports using natural language queries.

Q: Does LlamaIndex support real-time updates from Leiga?

Yes, by calling gettaskdetails or listprojects during the query loop, LlamaIndex pulls the latest live data directly from your project boards before generating a response.

Q: Can I limit LlamaIndex to read-only Leiga tools?

Yes, you can use the allowedtools filter when setting up the tool spec. This lets you expose listtasks while blocking modifying tools like createtask.

Index your Leiga project data into LlamaIndex using this MCP Server to query backlogs, team capacity, and workflows using natural language.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Leiga MCP to LlamaIndex

Create your Vinkius account to connect Leiga 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 Leiga with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantic Search Over Leiga Backlogs

The Leiga MCP Server allows LlamaIndex to fetch project data and index it directly into vector stores. Your agent can run `list_tasks` to pull active tickets, convert that data into document nodes, and index them so you can run semantic queries across your entire backlog. Instead of clicking through filters, you ask your agent which team members are working on high-priority bugs. The agent queries the index, matches the semantic intent, and uses `get_task_details` to verify the current status.

Grounded RAG with LlamaIndex and Leiga

This Leiga MCP Server integration ensures your project management queries are grounded in real-time data instead of model hallucinations. LlamaIndex queries the server using `get_project_details` and `list_workflows` to build a context window filled with actual project metadata. When you ask for a status report, the agent doesn't guess. It reads the live output of your active workflows, ensuring your summaries match the ground truth on your project boards.

Indexing Team Capacity and Workflows

Feed team structures and automated workflows into your LlamaIndex knowledge base using Leiga tools. The agent calls `list_organizational_teams` and `list_team_members` to build a vector-searchable index of your organizational structure. You can then query who is responsible for specific types of tasks or which team handles particular automated workflows. The index updates dynamically, keeping your resource planning aligned with reality.

Setup guide

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

Run `pip install llama-index-tools-mcp` to get the necessary package. Initialize the `BasicMCPClient` with the Vinkius URL, convert it to a tool spec, and pass it to your agent.

Yes, you can index the output of `list_tasks` into a vector store. This lets you search for similar tickets or find duplicate bug reports using natural language queries.

Yes, by calling `get_task_details` or `list_projects` during the query loop, LlamaIndex pulls the latest live data directly from your project boards before generating a response.

Yes, you can use the `allowed_tools` filter when setting up the tool spec. This lets you expose `list_tasks` while blocking modifying tools like `create_task`.

Vinkius manages the connection using ephemeral, zero-trust environments. Your team lists, task descriptions, and project workflows are transmitted securely and never cached or exposed to external networks.

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