How to Use the Harness MCP in LlamaIndex

Q: How do I set up the Harness MCP Server with LlamaIndex?

Install the llama-index-tools-mcp package. Create a BasicMCPClient pointing to your Vinkius endpoint, wrap it in an McpToolSpec, and pass that to your FunctionAgent.

Q: Can LlamaIndex search through Harness audit logs?

It pulls the raw events via the getauditlogs tool and embeds them. You then run semantic queries across your platform's entire operational history.

Q: Does LlamaIndex support triggering Harness deployments?

The agent calls executepipeline if you include it in the allowed tools filter. You restrict it to read-only operations by omitting execution tools during setup.

Index your Harness configurations via MCP Server into LlamaIndex to build a searchable CI/CD 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 Harness MCP to LlamaIndex

Create your Vinkius account to connect Harness 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 Harness with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index pipeline configurations

LlamaIndex pulls the raw YAML from `get_pipeline` and the microservice definitions from `list_services`. It chunks this infrastructure data into your vector store. Instead of digging through a web UI, you query your index. The system retrieves the exact configuration blocks that define your current staging environment.

Query historical CI/CD data with LlamaIndex

Your application fetches historical deployment data using `list_executions` and `get_audit_logs`. This turns your entire deployment history into a semantic search target. When someone asks why a build broke last Tuesday, the agent searches the index. It finds the specific failed step and the associated commit without hallucinating details.

Map infrastructure via the MCP Server

The MCP Server reads your Git, Docker, and Kubernetes integrations using `list_connectors`. LlamaIndex combines this with `list_environments` to build a complete dependency graph. You get accurate answers about where things live. If a developer needs to know which cluster hosts a specific service, the RAG agent pulls the exact mapping from the live API.

Setup guide

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

Install the `llama-index-tools-mcp` package. Create a `BasicMCPClient` pointing to your Vinkius endpoint, wrap it in an `McpToolSpec`, and pass that to your `FunctionAgent`.

It pulls the raw events via the `get_audit_logs` tool and embeds them. You then run semantic queries across your platform's entire operational history.

The agent calls `execute_pipeline` if you include it in the allowed tools filter. You restrict it to read-only operations by omitting execution tools during setup.

Scope the API token you provide to specific environments. The `list_projects` tool only returns what that token is authorized to view.

Zero-trust architecture ensures Vinkius retains nothing. When your agent fetches `list_connectors` data, the transmission is encrypted and the sandbox is destroyed right after the request finishes.

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