How to Use the Comet ML MCP in LlamaIndex

Q: How do I load Comet ML tools into my LlamaIndex pipeline?

Install llama-index-tools-mcp and initialize the client. Wrap it in McpToolSpec to convert tools like listexperiments into LlamaIndex-compatible tools for your agent.

Q: Can LlamaIndex search through historical Comet ML run data?

Yes. By indexing the output of getexperiment into a vector index, your agent can perform semantic search over past training runs to find specific configurations.

Q: Can I filter which Comet ML tools are visible to LlamaIndex?

Yes. You can use the allowedtools filter in the LlamaIndex client to expose only specific tools, such as restricting access to listprojects while hiding raw experiment payloads.

Index Comet ML training runs into LlamaIndex for semantic search using this managed MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Comet ML MCP to LlamaIndex

Create your Vinkius account to connect Comet ML 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 Comet ML with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Comet ML project structures into LlamaIndex

This tool lets your agent call `list_projects` to map out your entire Comet setup and index the structure into your vector store. Your agent calls `list_workspaces` to locate active environments and converts the layout into searchable nodes. This lets you query your workspace layout using natural language instead of digging through the UI. Your agent can find which project contains specific experiments by searching the indexed metadata.

Ground RAG applications in real training metrics

By calling `get_experiment_metrics`, your LlamaIndex pipeline pulls real-time numeric bounds and injects them straight into your query engine context. Stop relying on static reports to analyze your models. This MCP Server integration ensures your agent answers questions based on actual, live training data. Your RAG system can compare current run metrics against historical baselines without hallucinating the numbers.

Retrieve exact experiment parameters for semantic search

This tool lets your agent call `list_experiments` to search through your training history and find matching configurations. The agent then calls `get_experiment_params` to inspect the exact API taxonomy of those runs. LlamaIndex converts these MCP tools outputs into document nodes, making your experiment parameters searchable. You can ask your agent which hyperparameters produced the best results, and it will pull the exact records to prove it.

Setup guide

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

Install `llama-index-tools-mcp` and initialize the client. Wrap it in `McpToolSpec` to convert tools like `list_experiments` into LlamaIndex-compatible tools for your agent.

Yes. By indexing the output of `get_experiment` into a vector index, your agent can perform semantic search over past training runs to find specific configurations.

LlamaIndex grounds its responses directly in the live data fetched by `get_experiment_metrics`. The agent reads the exact numeric bounds from the tool call rather than guessing.

Yes. You can use the `allowed_tools` filter in the LlamaIndex client to expose only specific tools, such as restricting access to `list_projects` while hiding raw experiment payloads.

The MCP Server runs in an isolated sandbox on Vinkius, which handles your credentials securely. Your raw experiment parameters and metric values are processed ephemerally and never stored.

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