Model Mondays is a weekly Microsoft livestream and Discord-based learning series about choosing and using generative AI models. Developers and other AI practitioners use its roundups, spotlight sessions, demonstrations, and office hours to understand model fundamentals, compare options, and plan solutions. The catalogue contains an instruction related to the series.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/microsoft/model-mondaysWrote 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/commands/microsoft/model-mondays/0-setup-mcp)<a href="https://agentmods.dev/commands/microsoft/model-mondays/0-setup-mcp"><img src="https://agentmods.dev/badge/commands/microsoft/model-mondays/0-setup-mcp/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.
<a href="https://agentmods.dev/commands/microsoft/model-mondays/0-setup-mcp"><img src="https://agentmods.dev/badge/commands/microsoft/model-mondays/0-setup-mcp.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00752 |
| Opus 5.5 | $0.00000 | $0.00301 |
| Sonnet 5.5 | $0.00000 | $0.00150 |
| Haiku 4.5 | $0.00000 | $0.00075 |
Grade A, and why
0-setup-mcp 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 21d 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Server Setup Meta Prompt
You are an expert assistant helping to set up Model Context Protocol (MCP) servers in Visual Studio Code. Your task is to help create and configure a .vscode/mcp.json file with the appropriate MCP servers for enhanced GitHub Copilot functionality.
Getting Started
I need to set up MCP servers in my VS Code workspace. Please help me create a .vscode/mcp.json configuration file that includes:
Required MCP Servers:
- Microsoft Docs MCP Server (for documentation search and grounding)
- GitHub MCP Server (for repository and GitHub API access)
Optional MCP Servers (ask if I want to include):
- Hugging Face MCP Server (for model and dataset information)
- Other relevant MCP servers based on my project needs
Configuration Requirements
Security Considerations
- Never hardcode sensitive tokens directly in the configuration
- Use environment variables or input prompts for authentication tokens
- Explain how to set up GitHub Codespaces secrets for token management
- Ensure the
.vscode/mcp.jsonfile is added to.gitignore
Required Tokens/Authentication
Help me understand what tokens I need to create:
- GitHub Personal Access Token (PAT): Fine-grained token for GitHub MCP server
- Hugging Face Token: Read-only token for HF MCP server (if included)
- Other tokens: Based on additional servers selected
Configuration Format
The MCP configuration should include:
- inputs: For secure token handling via prompts
- servers: Configuration for each MCP server including:
- Connection details (URL or Docker command)
- Authentication setup
- Environment variable handling
Expected Deliverables
-
Complete
.vscode/mcp.jsonfile with:- Microsoft Docs MCP server configuration
- GitHub MCP server with secure token handling
- Any additional servers I request
-
Setup Instructions including:
- How to create required tokens
- How to set up GitHub Codespaces secrets
- How to ensure
.vscode/mcp.jsonis in.gitignore - How to test the MCP server connections
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.
- 21d ago First seen · 97 lines · 0 tokens per session scan A 775c3bc43d1c
0-setup-mcp is a command published in the GitHub repository microsoft/model-mondays (301 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 752 tokens. 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 2026-09-25.
Other commands, from other repositories
vibe-workflow
The vibe-coding workflow turns an app idea into a working MVP in 5 stages. Your job: figure out where the user is and route them to the right stage.
vibe-agents
Step 4 of the vibe-coding workflow: generate AGENTS.md + tool configs so the AI builder stays on track.
vibe-build
Step 5 of the vibe-coding workflow: build the MVP one verified feature at a time.
vibe-prd
Step 2 of the vibe-coding workflow: define WHAT to build, WHO it's for, and WHY it matters.
vibe-research
Step 1 of the vibe-coding workflow: validate the app idea with deep research before anything gets built.
vibe-techdesign
Step 3 of the vibe-coding workflow: plan HOW to build it — stack, architecture, costs, deployment.