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 DiegoLopez0208/RpgMakerMVUltimate-MCP --skill rpgmaker-mv-mcpgit clone --depth 1 https://github.com/DiegoLopez0208/RpgMakerMVUltimate-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/diegolopez0208/rpgmakermvultimate-mcp/rpgmaker-mv-mcp)<a href="https://agentmods.dev/skills/diegolopez0208/rpgmakermvultimate-mcp/rpgmaker-mv-mcp"><img src="https://agentmods.dev/badge/skills/diegolopez0208/rpgmakermvultimate-mcp/rpgmaker-mv-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/diegolopez0208/rpgmakermvultimate-mcp/rpgmaker-mv-mcp"><img src="https://agentmods.dev/badge/skills/diegolopez0208/rpgmakermvultimate-mcp/rpgmaker-mv-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 | $0.00139 | $0.01781 |
| Opus 5.5 | $0.00056 | $0.00712 |
| Sonnet 5.5 | $0.00028 | $0.00356 |
| Haiku 4.5 | $0.00014 | $0.00178 |
Grade A, and why
rpgmaker-mv-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 15d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Driving the RPG Maker MV MCP correctly
This MCP edits a real RPG Maker MV project on disk (data/*.json, validated against the actual engine). It is powerful but the engine is unforgiving: a wrong tile ID, a sprite that doesn't exist, or a missing field crashes the game. Follow this workflow and you produce coherent, playable content; ignore it and you produce "random tiles everywhere" and Loading-Error crashes.
The one rule that prevents 90% of bad output
Do NOT hand-paint tiles or place objects one tile at a time, and never invent IDs. Build maps with generate_map and add content with the manage_map_event presets. generate_map is knowledge-driven: for most themes it clones a real hand-authored reference map from the 106 bundled templates (real multi-tile houses, walls, furniture) instead of painting tiles procedurally, so the output looks like a real RPG Maker map and only uses IDs that exist. When you do need an ID (tile, sprite, troop, skill, item), get it from get_project_context — never guess.
Standard workflow
get_project_context(detailfull) — ALWAYS first. Returns every database id+name, switch/variable names, starting position, and the sprite filenames available perimg/folder. This is your source of truth; read it before creating anything.- Build the world with
generate_map(defaultmode:"procedural", which is knowledge-driven):- Pick a
theme(town, village, forest, dungeon, cave, world, interior, castle, beach, desert, snow, …) and omittilesetId— it auto-selects the right tileset. For themes with a bundled reference map (town, village, dungeon, interior, castle, world, …) it clones a real hand-authored map from the knowledge base, adapted to your tilesets; for themes without one (beach, swamp, desert) it generates procedurally. Combat themes auto-wire random encounters from existing troops. - Want a specific reference map? List them with
get_project_context detail:"templates", thengenerate_map mode:"template" templateId:<id>(or passtemplateIdin procedural mode to force that one). Force pure procedural generation withuseTemplate:false. Sameseed+ params → the same map. town/villageauto-create enterable house interiors with two-way warps (returned ininteriorMapIds); opt out withenterableHouses:false.- To connect maps, use
edit_map action:"connect"(bidirectional) ormanage_map_event preset:"door"/"teleport".
- Pick a
- Populate with
manage_map_eventpresets (each builds a complete, working event):npc{dialogues[], characterName?, characterIndex?}— characterName must be a real sprite fromget_project_context(e.g.People1); omit for invisible.chest{items:[{type:item|weapon|armor,id,amount}]}— IDs must exist (check first).shop{goods:[[type,id,priceType,price]]},inn{cost},boss{troopId},teleport/door{destMapId,destX,destY},puzzle_switch.
- Database via
create_database_entry/update_database_entry/query_database(entity = actors/classes/skills/items/weapons/armors/enemies/states/troops/common_events). Presets exist for skills (damage_skill,healing_skill, …),boss_enemy,encounter_troop. - System:
manage_systemfor title, switch/variable names, andset_starting_position(validate the map exists first).
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.
- 15d ago Changed 62237c3ec236
- 1mo ago First seen · 67 lines · 139 tokens per session scan A d76e731e5a0b
rpgmaker-mv-mcp is a skill published in the GitHub repository DiegoLopez0208/RpgMakerMVUltimate-MCP (28 stars, last pushed 15d ago), licensed MIT. It adds 139 tokens to every session and 1,781 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
gate-check
Validate readiness to advance between development phases. Produces a PASS/CONCERNS/FAIL verdict with specific blockers and required artifacts. Use when user says 'are we ready to move to X', 'can we advance to production', 'check if we can start the next phase', 'pass the gate'.
smoke-check
Run the critical path smoke test gate before QA hand-off. Executes the automated test suite, verifies core functionality, and produces a PASS/FAIL report. Run after a sprint's stories are implemented and before manual QA begins. A failed smoke check means the build is not ready for QA.
art-generate
Generates placeholder .aseprite files from asset specs using the Aseprite MCP. Reads asset specs and art bible, creates sprites with correct dimensions/palette/layers, exports PNGs. Run after /asset-spec has produced specs and /art-bible exists.
help
Analyzes what is done and the users query and offers advice on what to do next. Use if user says what should I do next or what do I do now or I'm stuck or I don't know what to do.
qa-plan
Generate a QA test plan for a sprint or feature. Reads GDDs and story files, classifies stories by test type (Logic/Integration/Visual/UI), and produces a structured test plan covering automated tests required, manual test cases, smoke test scope, and playtest sign-off requirements. Run before sprint begins or when…
asset-audit
Audits game assets for compliance with naming conventions, file size budgets, format standards, and pipeline requirements. Identifies orphaned assets, missing references, and standard violations.