Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/andreaswasita/copilot-agents-dojonpx agentmods add skills/andreaswasita/copilot-agents-dojo/using-mcpWrote 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/skills/andreaswasita/copilot-agents-dojo/using-mcp)<a href="https://agentmods.dev/skills/andreaswasita/copilot-agents-dojo/using-mcp"><img src="https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-dojo/using-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/skills/andreaswasita/copilot-agents-dojo/using-mcp"><img src="https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-dojo/using-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00017 | $0.01405 |
| Opus 5 | $0.00009 | $0.00702 |
| Sonnet 5 | $0.00003 | $0.00281 |
| Haiku 4.5 | $0.00002 | $0.00140 |
Grade A, and why
using-mcp scanned grade A with 1 finding 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 9d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
Generic → node mcp/scripts/mcp-subprocess.js list <server-binary> How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using MCP Skill
Discovers, configures, and verifies Model Context Protocol servers from Copilot, Claude Code, Cursor, and other MCP-compliant clients. Treats mcp/registry.yaml as the source of truth and least-privilege scopes as non-negotiable. Does NOT itself author servers (see building-mcp-servers) or bypass the broker (see calling-mcp-tools-via-subprocess).
When to Use
- User mentions MCP, MCP server, "add a tool", "connect to ".
- Agent needs data from an external system (GitHub, Postgres, Azure, Graph, browser, FS).
- "Why can't Copilot see X?" — check the MCP wiring before anything else.
- Authoring or modifying
.vscode/mcp.json,.mcp.json,.cursor/mcp.json.
Prerequisites
- A Copilot client that supports MCP (Copilot CLI, VS Code agent mode, Claude Code, Cursor).
mcp/registry.yamlaccessible in the dojo (this skill is parasitic on the registry).npx/nodeavailable for stdio servers, or hosted endpoint for Streamable HTTP.- Auth context already set up (
az login,gh auth, OAuth flow, etc.) — never paste raw secrets into configs. - The
view,edit, andpowershellCopilot tools.
How to Run
1. Open `mcp/registry.yaml`. Find the server.
2. Pick the transport (stdio for local, Streamable HTTP for hosted).
3. Drop the config snippet from `mcp/configs/` into the client's config file.
4. Set scopes to least privilege.
5. Verify the server is green in the client; call one tool end-to-end.
Quick Reference
| Transport | When | Auth model |
|---|---|---|
| stdio | Local dev, single user | Inherits CLI session env (az, gh) |
| Streamable HTTP | Hosted, teams, sandboxed | OAuth 2.1 + PKCE |
| SSE (legacy) | Only if server still requires it | Migrate to Streamable HTTP |
| Client | Config file |
|---|---|
| VS Code / GHCP agent mode | .vscode/mcp.json (workspace) or user-level via MCP: Open User Configuration |
| Copilot CLI | ~/.copilot/mcp.json or per-project .copilot/mcp.json |
| Claude Code | .mcp.json (repo) or ~/.claude.json (user) |
| Cursor | .cursor/mcp.json or ~/.cursor/mcp.json |
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.
- 9d ago First seen · 134 lines · 17 tokens per session scan A 4067ea12a909
using-mcp is a skill published in the GitHub repository andreaswasita/copilot-agents-dojo (52 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 1,405 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
harness
Use when governing a workspace's control plane, code or not — the 01-TOOLS/ tooling layer, the 02-DOCS/ chaos→knowledge wiki, the root Knowledge map. Audits it, migrates legacy XX- folders, scaffolds provider tooling, sweeps the inbox, writes root CLAUDE.md/AGENTS.md. NOT the bootstrap front door (that is init, which…
decision-ledger
A session record for tracking unresolved decisions and drafting them into `.governance/claims/` when they are settled. It preserves both the decision and the reason behind it.
governance-bootstrap
A guided checklist for creating a project's governance system from scratch when no governance exists.
session-grounding
A session-start procedure for checking the current facts, scope, and work track in a governed project before taking action.
truth-first
A set of rules for writing technical conclusions and performing irreversible or state-changing operations. It requires evidence tied to file and line locations and restricts unsupported claims.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…