Public assessment

doggybee/mcp-server-leetcode (@mcpfun/mcp-server-leetcode)

mcpfun-mcp-server-leetcode · v1.0.0 · scanned Aug 3, 2026

What changed in the harness

Selection accuracy 100→100, token cost up 12%, unconfirmed writes 100%→100%.

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

26.9 / 30

26.9 out of 30

03Economics

20.0 / 20

20.0 out of 20

04Discoverability

14.5 / 20

14.5 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.

7 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
`get-daily-challenge`	no_return_description	Retrieves the current LeetCode daily challenge problem, including its title, difficulty, and related problem details.
`get-problem`	no_return_description	Returns the LeetCode problem identified by the provided titleSlug, including its statement, difficulty, tags, and solution-related content.
`search-problems`	no_return_description	Searches LeetCode problems filtered by the optional tags and difficulty, returning a list of up to 'limit' problems after skipping the first 'skip' results.
`get-user-profile`	no_return_description	Returns the LeetCode profile for the given username, including ranking, problem-solving statistics, and account details.
`get-user-submissions`	no_return_description	Returns the most recent submissions for the given LeetCode username, up to the specified limit, with details for each submission.
`get-contest-details`	no_return_description	Returns details for the LeetCode contest identified by the provided contestSlug, such as its schedule, problems, and standings information.
`get-user-contest-ranking`	no_return_description	Returns the contest ranking and rating information for the given LeetCode username, including contest history and performance.

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-user-profile`	`get-user-submissions`	medium	Both take only a username and share 'get user'; with empty descriptions, a task like 'show me this user's recent activity' or 'pull the user's stats' could select either tool.
`get-contest-details`	`get-user-contest-ranking`	medium	Both revolve around 'contest'; a task like 'get the contest details/results for this user' could mis-map to get-contest-details, which expects a contestSlug, when the user meant their ranking.
`get-user-profile`	`get-user-contest-ranking`	medium	Both are user-scoped with identical input (username); a task like 'show this user's contest rating or profile' is ambiguous because a profile plausibly contains rankings and ratings.
`get-problem`	`search-problems`	medium	Both relate to 'problems'; 'find me a problem on arrays/dynamic-programming' could send the agent to get-problem (which needs a slug) instead of search-problems with tags, since names don't distinguish fetch-by-slug from filtered search.
`get-daily-challenge`	`get-problem`	medium	The daily challenge is itself a problem; 'get today's problem' or 'show me the challenge problem' could resolve to the generic get-problem instead of get-daily-challenge when the dedicated tool's existence isn't obvious from names alone.

Compare the field

One score is useful.
The evidence makes it actionable.

Back to the leaderboard