Public assessment

MobileReality/mdma (@mobile-reality/mdma-mcp)

mobile-reality-mdma-mcp · v0.2.4 · scanned Aug 3, 2026

What changed in the harness

Selection accuracy 98%, destructive-action safety rate 100% (baseline only -- no rewrite pass applied).

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

30.0 / 30

30.0 out of 30

02Legibility

28.2 / 30

28.2 out of 30

03Economics

19.9 / 20

19.9 out of 20

04Discoverability

14.1 / 20

14.1 out of 20

Highest-impact fix

Estimated gain +6 points

Make target tools discoverable on the first call

Clarify tool names, decision boundaries, and required argument schemas so an agent can choose and construct the target call without exploratory steps.

Description evidence

Defects and rewrites.

0 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
No description defects were flagged in this assessment.

Selection evidence

Confusable tool pairs.

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

Tool A	Tool B	Confidence	Why they collide
`get-spec`	`get-doc`	high	Spec and doc are near-synonyms in natural language; a task like 'get the MDMA specification documentation' or 'show me the spec' fits both tools since both return spec/documentation-style content.
`get-prompt`	`get-doc`	medium	Both 'get' something; a task like 'fetch the prompt documentation' or 'show me the prompt doc' could select get-prompt (which returns prompt templates) instead of get-doc (which fetches markdown docs about prompts).
`get-prompt`	`list-prompt-variants`	medium	A task like 'what prompts are available?' or 'show me the author prompt' could land on either: list-prompt-variants returns the catalog, get-prompt returns an actual prompt and requires a name, so 'list the prompts' is genuinely ambiguous.
`list-docs`	`get-doc`	medium	A task like 'get the documentation' or 'show me the docs' is ambiguous between listing the doc catalog (list-docs) and fetching a doc's contents (get-doc), especially when the user doesn't name a specific file.
`get-spec`	`get-prompt`	low	A task like 'get the spec of the mdma-author prompt' could be read as needing the full specification (get-spec) or the named prompt definition (get-prompt); plausible but weak since spec and prompt are distinct objects.

Compare the field

One score is useful.
The evidence makes it actionable.

Back to the leaderboard