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/wvfp/gear-mcp-servernpx agentmods add skills/wvfp/gear-mcp-server/agent-skillWrote 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/wvfp/gear-mcp-server/agent-skill)<a href="https://agentmods.dev/skills/wvfp/gear-mcp-server/agent-skill"><img src="https://agentmods.dev/badge/skills/wvfp/gear-mcp-server/agent-skill/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/wvfp/gear-mcp-server/agent-skill"><img src="https://agentmods.dev/badge/skills/wvfp/gear-mcp-server/agent-skill.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 | $0.00086 | $0.02828 |
| Opus 5.5 | $0.00034 | $0.01131 |
| Sonnet 5.5 | $0.00017 | $0.00566 |
| Haiku 4.5 | $0.00009 | $0.00283 |
Grade A, and why
gear-mcp-godot 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 1mo 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gear-mcp-godot
End-to-end guide for working with the Godot project under
g:\Godot\godot-mcp\gear-mcp-server\project\. The MCP server runs
inside the Godot editor process (a GDExtension). A 50-line Node.js
proxy at proxy/index.js bridges stdio ↔ TCP 127.0.0.1:8510. End
users of the npm package just run the editor; AI agents in this IDE
talk to the editor directly.
Project layout
gear-mcp-server/
├── src/ ← C++ GDExtension source
│ ├── server/ ← TCP server (port 8510)
│ ├── godot_api/ ← Wrappers for EditorInterface / ProjectSettings
│ └── tools/
│ ├── editor/ ← run_scene_with_timeout, screenshot, restart_editor
│ ├── scene/ ← create_scene, add_node, attach_script, ...
│ ├── script/ ← write_file (gd), parse helpers
│ ├── project/ ← ProjectSettings getters/setters
│ ├── resource/ ← load_resource, save_resource
│ └── config/ ← set_project_setting, get_project_setting
├── project/ ← The Godot project being controlled
│ ├── project.godot
│ ├── scenes/ ← .tscn files
│ ├── scripts/ ← .gd files
│ └── addons/gear_mcp/ ← The plugin (panel UI, helper scripts)
└── proxy/
├── index.js ← npm package entry (50 lines, the stdio↔TCP proxy)
├── package.json
├── README.md
└── dev/
└── send.js ← One-shot test request sender (NOT in npm)
How to talk to the editor
The Godot editor (when started on the project directory) listens on
127.0.0.1:8510. The MCP server is a GDExtension, so it's loaded at
editor startup. You must restart the editor whenever the DLL is
rebuilt — cmake --build does not hot-reload GDExtensions.
A request looks like:
{"jsonrpc":"2.0","method":"tools/call","params":{"name":"<tool>","arguments":{...}},"id":1}
For dev/testing, save it to a file and send it with proxy/dev/send.js:
What ships with it
1 file 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.
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.
- 1mo ago First seen · 257 lines · 86 tokens per session scan A 18babb9d8f5e
gear-mcp-godot is a skill published in the GitHub repository wvfp/gear-mcp-server (3 stars, last pushed 4mo ago), licensed MIT. It adds 86 tokens to every session and 2,828 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
playtest-report
Structured playtest report template, or turn existing playtest notes into structured feedback.
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
motion
Reconstruct a skeleton from calibrated mesh projections and sequential VLM joint annotations, then fit joints and skin weights. Generate motion from joint-position trajectories, rhythm and contact constraints through IK; refine bone orientation against the action, then export, retarget and validate on the target mesh.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.
unity-manual-component
Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.