How to Use the Incident.io MCP in LlamaIndex

Q: How do I load Incident.io data into a LlamaIndex vector store?

Use llama-index-tools-mcp to initialize the client and fetch tools like listincidents. Pass the tool outputs to your index writer to store them as document nodes. This makes your live incident data searchable via standard query engines.

Q: Can LlamaIndex search through Incident.io custom fields?

Yes, the agent calls listcustomfields to understand your workspace metadata before running a search. It then filters your indexed documents using these fields. This ensures your RAG pipeline respects your specific categorization.

Q: How does LlamaIndex avoid hallucinations when querying Incident.io?

By grounding the LLM in real-time data retrieved from getincident. The agent fetches the exact incident payload before generating a response. This prevents the model from inventing non-existent outages or incorrect severities.

Q: Can I filter which tools this MCP Server exposes to LlamaIndex?

Yes, you can pass an allowedtools list when initializing the McpToolSpec. If you only want your agent to view rosters, restrict its access to listschedules and listusers. This prevents the agent from making unnecessary API calls.

Index Incident.io on-call schedules and active outages directly into your LlamaIndex vector store for semantic search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Incident.io MCP to LlamaIndex

Create your Vinkius account to connect Incident.io 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 Incident.io with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index active outages into LlamaIndex

This Incident.io MCP Server lets you turn live operational data into a searchable knowledge base. Your LlamaIndex agent queries `list_incidents` and `get_incident` to retrieve current outage statuses, then indexes those payloads directly into your vector database. Instead of scrolling through old Slack channels, you query your index to find past resolutions. The agent searches through indexed incident details to find historical precedents for the exact error you are seeing right now.

Query Incident.io rosters with LlamaIndex RAG

This Incident.io MCP Server exposes your organization's human structure so your LlamaIndex pipeline can query it semantically. By indexing the outputs of `list_schedules` and `list_users`, the agent matches active personnel to specific technical domains. You ask who is on call for a specific database issue, and the agent resolves the query by checking the indexed schedule. It combines this with data from `list_teams` to pinpoint the exact group responsible for the affected service.

Map custom metadata using LlamaIndex and MCP Server

This MCP Server provides direct access to your workspace configuration through `list_custom_fields` and `list_catalog_types`. LlamaIndex uses these endpoints to build a structured schema of your operational metadata. The agent injects this schema into its retrieval context, ensuring search results align with your internal terminology. You query past incidents classified under specific custom fields without worrying about keyword mismatches.

Setup guide

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

Use `llama-index-tools-mcp` to initialize the client and fetch tools like `list_incidents`. Pass the tool outputs to your index writer to store them as document nodes. This makes your live incident data searchable via standard query engines.

Yes, the agent calls `list_custom_fields` to understand your workspace metadata before running a search. It then filters your indexed documents using these fields. This ensures your RAG pipeline respects your specific categorization.

By grounding the LLM in real-time data retrieved from `get_incident`. The agent fetches the exact incident payload before generating a response. This prevents the model from inventing non-existent outages or incorrect severities.

Yes, you can pass an `allowed_tools` list when initializing the `McpToolSpec`. If you only want your agent to view rosters, restrict its access to `list_schedules` and `list_users`. This prevents the agent from making unnecessary API calls.

Your user rosters and schedule data are processed entirely in memory within a zero-trust environment. The Vinkius sandbox executes `list_users` over an encrypted connection and never caches the results on disk. Your API token remains isolated and is 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