clearml-mcp: Instructions file for Claude Code

CLAUDE.md

clearml-mcp CLAUDE.md is an instructions file for Claude Code from prassanna-ravishankar/clearml-mcp. It costs 780 tokens per session, scanned A, original, MIT.

Instructions for an MCP server that lets AI agents inspect ClearML, a platform for tracking machine-learning experiments, models, projects, and outputs.

In plain words
What is it for?
Listing projects, tasks, and models; comparing training results; reading parameters and metrics; and retrieving experiment or model artifacts.
Why use it?
It provides a defined way to find experiments and models and retrieve their settings, metrics, files, and lineage.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is prassanna-ravishankar/clearml-mcp's own configuration. It tells Claude Code how to work on clearml-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything clearml-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to prassanna-ravishankar/clearml-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/prassanna-ravishankar/clearml-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/prassanna-ravishankar/clearml-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for clearml-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/prassanna-ravishankar/clearml-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/prassanna-ravishankar/clearml-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/prassanna-ravishankar/clearml-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/prassanna-ravishankar/clearml-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for clearml-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/prassanna-ravishankar/clearml-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/prassanna-ravishankar/clearml-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 780 This file is loaded in full into every session.
When invoked 780 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00780 $0.00780
Opus 5 $0.00390 $0.00390
Sonnet 5 $0.00156 $0.00156
Haiku 4.5 $0.00078 $0.00078

Measured 11d ago against content hash a4fee84c97a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

clearml-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ClearML MCP Server

This project implements a Model Context Protocol (MCP) server for ClearML, enabling AI agents to interact with ClearML experiments, models, and projects.

Project Overview

The ClearML MCP server provides comprehensive tools for AI agents to:

  • Discover and analyze ML experiments
  • Compare model performance across tasks
  • Retrieve training metrics and artifacts
  • Search and filter projects and tasks
  • Get comprehensive model context and lineage

Available Tools

Task Operations

  • get_task_info(task_id) - Get ClearML task details, parameters, and status
  • list_tasks(project_name, status, tags) - List ClearML tasks with filters
  • get_task_parameters(task_id) - Get task hyperparameters and configuration
  • get_task_metrics(task_id) - Get task training metrics and scalars
  • get_task_artifacts(task_id) - Get task artifacts and outputs

Model Operations

  • get_model_info(task_id) - Get model metadata and configuration
  • list_models(project_name) - List available models with filtering
  • get_model_artifacts(task_id) - Get model files and download URLs

Project Operations

  • list_projects() - List available ClearML projects
  • get_project_stats(project_name) - Get project statistics and task counts

Analysis Tools

  • compare_tasks(task_ids, metrics) - Compare multiple tasks by metrics
  • search_tasks(query, project_name) - Search tasks by name, tags, or description

Technical Details

Dependencies

  • fastmcp>=0.1.0
  • clearml>=1.16.0
  • pydantic>=2.0.0

Architecture

  • Built with FastMCP framework
  • Uses stdio transport for Claude Desktop integration
  • Leverages existing ~/clearml.conf for authentication
  • Implements JSON-RPC 2.0 protocol

Entry Point

  • Main executable: clearml-mcp (via uvx)
  • Main module: src/clearml_mcp/clearml_mcp.py

Usage

Prerequisites

Users must have a configured ~/clearml.conf file with:

[api]
api_server = https://your-clearml-server.com
access_key = your-access-key
secret_key = your-secret-key

Read the full file on GitHub · 126 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 126 lines · 780 tokens per session scan A a4fee84c97a6

Subscribe to this mod's changes

clearml-mcp CLAUDE.md is an instructions file published in the GitHub repository prassanna-ravishankar/clearml-mcp (16 stars, last pushed 2mo ago), licensed MIT. It adds 780 tokens to every session, about $0.0039 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens