Public leaderboard

Public assessment

vicseeai/vicsee-mcp-server (@vicsee/mcp-server)

vicsee-mcp-server · v0.4.0 · scanned

What changed in the harness

Selection accuracy 100→100, token cost up 2%, unconfirmed writes 0%→0%.

Category breakdown

Where the score comes from.

Earned points across the four signals Gradable measures. Safety and Legibility are scored out of 30; Economics and Discoverability are scored out of 20.

01Safety

0.0 / 30

0.0 out of 30
02Legibility

29.0 / 30

29.0 out of 30
03Economics

19.7 / 20

19.7 out of 20
04Discoverability

12.6 / 20

12.6 out of 20

Highest-impact fix

Estimated gain +30 points

Add explicit identity and permission preflight tools

Expose machine-readable principal/tenant confirmation and a non-mutating permission check so agents can verify both before destructive actions.

Description evidence

Defects and rewrites.

2 defects found across the exposed tool descriptions. Suggested rewrites make purpose, inputs, boundaries, and returns easier for an agent to understand.

Tool Defect types Suggested rewrite
vicsee_list_models
no_return_description
List available VicSee models with their capabilities and credit costs, optionally filtered by the `type` parameter (image, video, or music). Returns the list of matching models; use a returned model's `id` as the `model` argument to vicsee_generate and consult its options to see valid parameters.
vicsee_get_credits
no_return_description
Get the current VicSee credit balance for the configured API key. Returns the remaining credit balance so you can check quota before running generations.

Selection evidence

Confusable tool pairs.

2 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.

Tool A Tool B Confidence Why they collide
vicsee_upscale_image vicsee_upscale_video medium A user asking to "upscale this" a file or URL without stating whether it is an image or video maps to both tools; they have identical async task-id behavior and nearly identical schemas (image_url vs video_url), so an agent could pick the wrong one from the media type.
vicsee_generate vicsee_upscale_image medium A request like "improve/enhance this image" is genuinely ambiguous: vicsee_generate supports image-to-image via image_urls and local file paths, while vicsee_upscale_image enhances via resolution upscaling, so an agent could select the wrong tool based on intent phrasing.

Compare the field

One score is useful.
The evidence makes it actionable.

Back to the leaderboard