godot-mcp: Skill for Claude Code

.agents/skills/mcp-server/SKILL.md

mcp-server is a skill for Claude Code, Codex from Vollkorn-Games/godot-mcp. It costs 184 tokens per session (2,264 once invoked), scanned A, original, MIT.

A development guide for building and maintaining an MCP server, a service that gives coding agents access to defined tools and data.

In plain words
What is it for?
Use it to choose between local and remote connections, define tools, extend a server safely, and protect it from malicious instructions.
Why use it?
It covers the decisions and ongoing work needed after the initial setup, including transports, compatibility, security, and changes over time.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for cline. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); built for cline.

This is Vollkorn-Games/godot-mcp's own configuration. It tells Claude Code and Codex how to work on godot-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 godot-mcp configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is npx @modelcontextprotocol/inspector node build/index.js.

Reuse

Borrowing it

Nothing to install: this file belongs to Vollkorn-Games/godot-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/Vollkorn-Games/godot-mcp/main/.agents/skills/mcp-server/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Vollkorn-Games/godot-mcp

Made for: Claude Code, Codex.

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 mcp-server

README.md
[![agentmods](https://agentmods.dev/badge/skills/vollkorn-games/godot-mcp/mcp-server/github.svg)](https://agentmods.dev/skills/vollkorn-games/godot-mcp/mcp-server)
Your own site
<a href="https://agentmods.dev/skills/vollkorn-games/godot-mcp/mcp-server"><img src="https://agentmods.dev/badge/skills/vollkorn-games/godot-mcp/mcp-server/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 mcp-server

Your own site · 80×15
<a href="https://agentmods.dev/skills/vollkorn-games/godot-mcp/mcp-server"><img src="https://agentmods.dev/badge/skills/vollkorn-games/godot-mcp/mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 184 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,264 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00184 $0.02264
Opus 5 $0.00092 $0.01132
Sonnet 5 $0.00037 $0.00453
Haiku 4.5 $0.00018 $0.00226

Measured 11d ago against content hash 2f79819de0ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mcp-server 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.

.agents/skills/mcp-server/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build and maintain an MCP server

Scaffolding an MCP server is the easy 10%. The heavy lifting is everything after init: writing tool definitions the agent reads correctly, extending the surface without breaking agents that already depend on it, defending against tool poisoning and prompt injection, and operating the thing once it is remote. This skill covers the whole lifecycle. The deep reference for each phase is the vendored OKF bundle in references/; SKILL.md is the procedure.

Target the current protocol

MCP uses date-string protocol revisions. As of 2026-06-21 the current stable revision is 2025-11-25 (it superseded 2025-06-18); a stateless-core revision 2026-07-28 is the imminent next release. Build against 2025-11-25 and let the SDK negotiate older clients. The production SDK is @modelcontextprotocol/sdk (v1.x, TypeScript). The split @modelcontextprotocol/server + /client packages are the unreleased V2 line, not current. Full protocol surface, lifecycle, and result shapes in protocol.md.

Step 1: Pick the transport

Use Transport Why
Local, client spawns the server as a subprocess, one user stdio No auth, no sessions, no scaling. Default for local tools. Log to stderr only.
Remote, hosted, multiple clients Streamable HTTP Single endpoint (POST + optional SSE upgrade), Mcp-Session-Id, OAuth, you own scaling and ops.

Prefer stdio until you genuinely need remote multi-client access. The old HTTP+SSE transport is deprecated (replaced by Streamable HTTP in 2025-03-26). Transport mechanics, the stdio-vs-HTTP operational cliff, and sessions are in protocol.md and maintenance.md.

Step 2: The five layers

Every server, regardless of target, has the same skeleton:

  1. Server & transport (src/index.ts) — entry point, lifecycle, cleanup, chosen transport.
  2. Tool definitions (src/tool-definitions.ts) — the contract the agent reads to decide what to call. The single most important file.
  3. Router & handlers (src/tool-router.ts, src/handlers/*.ts) — dispatch, validation, response shaping.
  4. The bridge (src/executor.ts, scripts/*) — how you actually talk to the target. 80% of the work.
  5. Security & validation (src/utils.ts) — input validation, execFile over exec, path checks, tool filtering.

Read the full file on GitHub · 105 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 105 lines · 184 tokens per session scan A 2f79819de0ef

Subscribe to this mod's changes

mcp-server is a skill published in the GitHub repository Vollkorn-Games/godot-mcp (3 stars, last pushed 1mo ago), licensed MIT. It adds 184 tokens to every session and 2,264 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

agui-dotnet-protobuf

Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…

ag-ui-protocol/ag-ui · 162 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

fastapi-router-py

Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.

microsoft/skills · 46 tokens

aws-sdk-java-v2-core

Provides AWS SDK for Java 2.x client configuration, credential resolution, HTTP client tuning, timeout, retry, and testing patterns. Use when creating or hardening AWS service clients, wiring Spring Boot beans, debugging auth or region issues, or choosing sync vs async SDK usage.

giuseppe-trisciuoglio/developer-kit · 62 tokens

migrate-segw-to-rap

Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…

arc-mcp/arc-1 · 106 tokens