How to Use the LinearB MCP in LlamaIndex

Q: How do I load LinearB metrics into a LlamaIndex vector store?

You use the llama-index-tools-mcp package to initialize the client and convert the tools into a standard tool list. Your agent can then run querysoftwaremetrics and write the returned JSON documents directly into your index.

Q: Can LlamaIndex query historical LinearB incidents to answer natural language questions?

Yes, by passing listsoftwareincidents as an allowed tool to your function agent. The agent fetches the incident list, indexes the raw text, and uses semantic search to find which teams had the highest MTTR last quarter.

Index your team's DORA metrics and deployment logs into a searchable LlamaIndex knowledge base.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LinearB MCP to LlamaIndex

Create your Vinkius account to connect LinearB 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 LinearB with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground your LlamaIndex RAG apps in real engineering data

Stop letting your agent guess how your engineering teams are performing. This MCP Server lets your LlamaIndex application query actual delivery metrics using `query_software_metrics` and index those results straight into a vector store for semantic search. When you ask your agent about delivery bottlenecks, it does not hallucinate answers based on stale documentation. It queries your active team structures from `list_engineering_teams` and matches them against real-world metrics to give you a grounded, accurate assessment of your delivery pipelines.

Semantic search over historical deployments and incidents

Finding patterns in old outages is painful when the data is locked in separate systems. You can use this integration to pull historical records via `list_software_deployments` and `list_software_incidents`, transforming raw API payloads into searchable document nodes. Your agent searches this indexed history to find recurring failure modes. By comparing past incident timestamps with specific deployment refs, the system uncovers hidden correlations that help your team prevent future downtime.

Keep your engineering knowledge base fresh

Static documentation about repository ownership is useless because teams change constantly. Your RAG pipelines can run scheduled queries using `list_connected_repos` via our MCP Server to update your local vector index automatically. Whenever a new project starts or a repo is archived, the index reflects the change. This keeps your agent's context window loaded with accurate, up-to-date repository mapping without requiring manual wiki updates.

Setup guide

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

You use the `llama-index-tools-mcp` package to initialize the client and convert the tools into a standard tool list. Your agent can then run `query_software_metrics` and write the returned JSON documents directly into your index.

Yes, by passing `list_software_incidents` as an allowed tool to your function agent. The agent fetches the incident list, indexes the raw text, and uses semantic search to find which teams had the highest MTTR last quarter.

Yes, your agent can write data as well as read it. You can configure the agent to execute `record_new_deployment` whenever it detects a successful pipeline build index update.

The server handles connection pooling, but you should configure your agent loops with backoff logic. This prevents hitting API rate thresholds when running heavy queries across dozens of engineering teams.

All communications are encrypted in transit, and Vinkius runs the integration inside a zero-trust, ephemeral sandbox. Your team structures and deployment logs are pulled directly from the API to your local LlamaIndex instance, ensuring no persistent storage of your engineering metadata occurs on our platform.

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