Borrowing it
Nothing to install: this file belongs to tsilva/mcp-wandb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tsilva/mcp-wandb/main/AGENTS.mdgit clone --depth 1 https://github.com/tsilva/mcp-wandbWrote 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.
[](https://agentmods.dev/instructions/tsilva/mcp-wandb/agents-md)<a href="https://agentmods.dev/instructions/tsilva/mcp-wandb/agents-md"><img src="https://agentmods.dev/badge/instructions/tsilva/mcp-wandb/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00398 | $0.00398 |
| Opus 5 | $0.00199 | $0.00199 |
| Sonnet 5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
mcp-wandb AGENTS.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 6d 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.
What it actually says
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
A Model Context Protocol (MCP) server that exposes Weights & Biases (W&B) functionality as tools. Built with FastMCP, it provides tools for querying W&B projects, runs, metrics, and generating metric plots.
Development Commands
# Install dependencies (requires Python 3.13+)
uv sync
# Run the MCP server (stdio transport)
python server.py
# Run tests (requires W&B API key and test environment variables)
WANDB_API_KEY=<key> TEST_WANDB_ENTITY=<entity> TEST_WANDB_PROJECT=<project> TEST_WANDB_RUN_ID=<run_id> TEST_WANDB_METRICS=<metric1,metric2> pytest tests/
Architecture
Single-file server (server.py): All MCP tools are defined in one file using the @mcp.tool() decorator from FastMCP.
MCP Tools exposed:
get_wandb_projects- List projects for an entitylist_wandb_runs- List runs in a projectlist_project_metrics- Get unique metric names across all runsplot_run_metric- Generate PNG plot of metrics (returns base64-encoded image via FastMCPImage)get_run_details- Get comprehensive run info (overview, config, summary, system metrics)
Environment: Requires WANDB_API_KEY environment variable (loaded via python-dotenv from .env file).
Testing Notes
Tests in tests/test_tools.py stub out FastMCP and dotenv to test tool functions directly against the real W&B API. Tests are skipped if required environment variables are not set.
Key Maintenance
README.md must be kept up to date with any significant project 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.
- 6d ago First seen · 42 lines · 398 tokens per session scan A b6a2192febb2
mcp-wandb AGENTS.md is an instructions file published in the GitHub repository tsilva/mcp-wandb (1 stars, last pushed 9d ago), licensed MIT. It adds 398 tokens to every session, about $0.0020 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 2026-08-31.
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.
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.
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).
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).
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.
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.