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.
npx skills add andreaswasita/copilot-agents-dojo --skill building-mcp-serversgit clone --depth 1 https://github.com/andreaswasita/copilot-agents-dojoWrote 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/building-mcp-servers)<a href="https://agentmods.dev/skills/andreaswasita/copilot-agents-dojo/building-mcp-servers"><img src="https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-dojo/building-mcp-servers/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/building-mcp-servers"><img src="https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-dojo/building-mcp-servers.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 | $0.01568 |
| Opus 5 | $0.00009 | $0.00784 |
| Sonnet 5 | $0.00003 | $0.00314 |
| Haiku 4.5 | $0.00002 | $0.00157 |
Grade A, and why
building-mcp-servers 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.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building MCP Servers Skill
Authors a Model Context Protocol server in TypeScript or Python using the official SDKs (@modelcontextprotocol/sdk, mcp), with deliberate tool/resource/prompt design, both stdio and Streamable HTTP transports, OAuth 2.1 auth, and a test fixture. Does NOT roll its own JSON-RPC framing and does NOT ship without registry + config snippet.
When to Use
- A required system is not in
mcp/registry.yaml. - An existing MCP server is too broad; you need a domain-specific facade.
- User says "build", "write", "author", "create" + "MCP server".
- Wrapping internal APIs so an agent can call them without bespoke skills.
Prerequisites
- Node 20+ (TypeScript) or Python 3.11+.
- The official SDK installed (
@modelcontextprotocol/sdkormcp). - An auth strategy decided upfront (CLI inheritance for local, OAuth 2.1 + PKCE for hosted).
mcp/registry.yamlandmcp/configs/writable.@modelcontextprotocol/inspectorfor handshake debugging.
How to Run
1. Pick primitives: tools / resources / prompts. Default to tools.
2. Design tool names (verb_object) and JSON Schema inputs.
3. Scaffold the server with the official SDK + stdio transport.
4. Add Streamable HTTP transport if the server is hosted.
5. Implement auth — CLI inheritance (local) or OAuth 2.1 + PKCE (hosted).
6. Add tests: in-memory transport unit tests + a real stdio smoke test.
7. Register in `mcp/registry.yaml` and add a `mcp/configs/` snippet.
Quick Reference
| Primitive | Use for | Mental model |
|---|---|---|
| tools | Side-effectful or arg'd queries | RPC the agent decides to invoke |
| resources | Read-only documents addressable by URI | Things the agent or user attaches |
| prompts | Pre-baked agent instructions | Slash commands the user invokes |
| Concern | Rule |
|---|---|
| Tool naming | verb_object snake_case (get_my_deals) |
| Input schema | JSON Schema, required fields marked, description on every property |
| Output | Text content first; structured JSON in a second content block |
| Logging | stderr only — stdout is reserved for JSON-RPC framing |
| Auth | CLI inheritance (local) or OAuth 2.1 + PKCE (hosted), never tokens in tool args |
| Pagination | Every list tool has limit (default ≤50) and cursor |
| Idempotency | Mutations accept a client-provided idempotency key |
| Versioning | Bump serverInfo.version on schema 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.
- 11d ago First seen · 149 lines · 17 tokens per session scan A 442e557c964e
building-mcp-servers is a skill published in the GitHub repository andreaswasita/copilot-agents-dojo (53 stars, last pushed 4d ago), licensed MIT. It adds 17 tokens to every session and 1,568 once invoked, about $0.0001 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.
Other skills, from other repositories
fastapi
Use when building, reviewing, testing, securing or shipping a FastAPI / async Python service — routers, Pydantic v2 schemas, dependency injection, async SQLAlchemy 2.0, OAuth2/JWT, ASGITransport tests, production wiring. NOT language-level Python or packaging (that is python), NOT engine-level SQL (that is…
csharp-dotnet
Use when writing, reviewing, testing, or shipping C# / .NET code — ASP.NET Core APIs (minimal APIs vs controllers), EF Core data access, async correctness, solution layout in .cs/.csproj/.sln. NOT a Java/Spring backend (that is spring-boot), NOT a Node/TypeScript backend (that is nestjs), NOT framework-neutral REST…
firebase
Use when building on Firebase — Firestore data modeling, Security Rules, Auth and custom claims, Cloud Functions, Storage, modular Web/Admin SDK imports — including symptoms like a database open to the internet, a query rejected by rules, or a doc stuck at 1 write/sec. NOT managed-Postgres BaaS with SQL and RLS (that…
gamedev-multiplayer
Use when adding multiplayer or netcode to a game — client-server vs P2P, server authority and anti-cheat, state replication vs RPCs, prediction and reconciliation, lag compensation, plus Godot 4 / Unity NGO / Unreal wiring. NOT single-player gameplay (that is godot, unity, unreal), NOT matchmaking or server hosting…
gcp-essentials
Use when running a small product on core Google Cloud via the gcloud CLI: a project, Cloud Run deploys, a locked-down Cloud Storage bucket, managed Cloud SQL, and least-privilege IAM wiring them together. NOT AWS (that is aws-essentials), NOT the CI pipeline that ships the image (that is deployment), NOT Postgres…
go
Use when writing, reviewing, testing, or shipping Go code and HTTP services: idioms, %w error wrapping, goroutine/context/errgroup concurrency, net/http 1.22 routing, log/slog, project layout, table-driven tests, Go hardening. NOT language-agnostic threat modeling (that is secure-coding), NOT Dockerfile/CI shipping…