renpy-mcp-creator (Renoyz/renpy-mcp-creator) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 71 tools. No publisher has claimed this listing.

C
Caution
74/100

renpy-mcp-creator

Provides 70+ MCP tools for creating and managing Ren'Py projects, enabling natural language requirements to be converted into editable projects with build, preview, and asset generation capabilities.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

Renoyz

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 3 credentials: ANTHROPIC_API_KEY, OPENAI_API_KEY, SESSION_SECRET
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes69 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

create_project

Create a new Ren'Py project directory using the requested template.

story_flow_graph

Analyze the story flow and return a graph of labels and their connections.

find_dead_ends

Find labels that are dead ends (unreachable or have no exit).

track_variables

Track all game variables — where they are defined, set, and read.

count_dialogue

Count dialogue blocks, words, and characters per route/label.

character_map

Map all characters: definitions, dialogue counts, and scene appearances.

validate_script

Lightweight script validation — faster than full lint.

playtest_report

Run all available test cases and generate a test report.

generate_scene

Generate a RenPy scene script template.

list_screens

List all screen definitions in the project.

music_timeline

Map music and sound effects across the story timeline.

search_script

Search across all game scripts for text patterns.

consistency_check

Check for consistency issues in dialogue and narration.

accessibility_check

Check the project for accessibility issues.

generate_background

Generate a background image asset using Gemini.

generate_character

Generate a character sprite using Gemini.

list_assets

List all image, audio, and video assets in the project.

find_unused_assets

Find asset files that are not referenced in any .rpy script.

list_audio

List all audio files with their usage in scripts.

image_size_check

Check image dimensions against project resolution.

install_bridge

Install the MCP bridge script into the current project.

uninstall_bridge

Remove the MCP bridge script and IPC files from the project.

live_ping

Ping the running game to check if the bridge is active.

live_get_state

Get the current game state from a running game.

live_screenshot

Take a screenshot of the currently running game.

live_eval

Evaluate a Python expression in the running game context.

live_notify

Show a notification message in the running game.

live_jump

Warp to a specific label in the running game.

live_set_variable

Set a game variable in the running game.

style_inspector

Inspect RenPy styles in the running game.

save_inspector

Inspect save files in the running game.

screen_hierarchy

Inspect the widget hierarchy of a currently shown screen.

build_project

Run the build pipeline for a project.

start_web_preview

Serve the generated web build from a local HTTP server.

stop_web_preview

Stop the local preview server.

screenshot_scene

Take a screenshot by warping to a specific script location.

list_warp_targets

List available warp targets (labels and scene locations) in the project.

scene_preview_gallery

Generate a gallery of screenshots from multiple scenes.

list_projects

Return metadata for available projects in the workspace.

list_project_files

List all files in a project's game directory.

read_project_file

Read the contents of a file in a project's game directory.

edit_project_file

Edit or create a file in a project's game directory.

generate_script

Write a Ren'Py script file to the project.

attach_background_to_start

Insert a scene statement for the given background image under label start in script.rpy.

set_project

Set the active RenPy project path.

get_project_info

Get information about the current RenPy project structure.

lint_project

Run RenPy lint to check the project for errors and warnings.

compile_project

Compile RenPy scripts (.rpy -> .rpyc).

dump_project_metadata

Dump project metadata (characters, labels, screens, etc.) to JSON.

package_info

Show build/packaging configuration from the project.

rename_character

Rename a character variable across all script files.

rename_label

Rename a label and update all jump/call references.

extract_route

Extract a complete story route into a separate file.

insert_dialogue

Insert dialogue or script lines at a specific position.

run_test

Run RenPy automated tests.

create_test

Create a RenPy test case file.

list_tests

List all test cases defined in the project.

list_translations

List all available translation languages and their completion status.

find_untranslated

Find untranslated strings for a specific language.

translation_diff

Find translation entries where the original text may have changed.

generate_translations

Generate translation files for a new language using RenPy CLI.

extract_translation_strings

Extract translatable strings to JSON for external translation tools.

merge_translation_strings

Merge translated strings from JSON back into RenPy translation files.

auto_translate

Prepare untranslated strings for AI-assisted translation.

open_story_map

Open the visual story map in a browser.

open_dashboard

Open the real-time development dashboard in a browser.

open_script_editor

Open the visual script editor in a browser.

open_heatmap

Open the playtest heatmap in a browser.

open_asset_manager

Open the asset manager in a browser.

// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configRENPY_SDK_PATHRen'Py SDK 8.x(vn-creator start 会在缺失时自动下载;也可自行安装并通过 指定)
🔐 secretANTHROPIC_API_KEY
configRENPY_MCP_CAPTURE
configRENPY_MCP_GALLERY
configRENPY_MCP_GALLERY_IDX
configRENPY_MCP_MOCK_IMAGE_GEN
configSystemRoot
configRENPY_MCP_MOCK_BUILD
configRENPY_MCP_MOCK_LLM
configRENPY_MCP_MOCK_LLM_MALFORMED_JSON
configANTHROPIC_BASE_URL
configANTHROPIC_MODEL
🔐 secretOPENAI_API_KEY
configOPENAI_BASE_URL
configOPENAI_MODEL
🔐 secretSESSION_SECRET
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

71/71 tools missing one or more hints — create_project (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); story_flow_graph (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); find_dead_ends (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +68 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Destructive tools are labelled

3 tools perform destructive updates without destructiveHint — uninstall_bridge deletes at line 78 (f.unlink()); screenshot_scene deletes at line 193 (shutil.rmtree(screenshot_dir, ignore_errors=True)); scene_preview_gallery deletes at line 320 (shutil.rmtree(gallery_dir, ignore_errors=True))

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Tool test coverage

29/71 tools referenced in tests (41%)

Write tests that reference each tool by name so every tool has at least one test.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/renoyz/renpy-mcp-creator?variant=verified)](https://m8ven.ai/mcp/renoyz/renpy-mcp-creator)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 6f720cf2f2a06ad5706862d65253a8c83a51b9d2
code hash: 713775f50be501ae7ddb8e2c40bb3b6ab586b599bcb775b2ad051ed1d7899639
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client