Fang
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fang_check_diffA | Diff-scoped mutation testing. Mutates only added Python lines versus a git revision (default HEAD), runs the test suite, and returns the mutants the tests failed to detect. Use this to verify that new tests actually bite. |
| fang_mutation_scoreA | Return only the mutation score and counts for a diff or the whole project. Cheaper than fang_check_diff when you just need the number. |
| fang_list_survivorsC | Run the analysis and return surviving mutants only, with file, line, operator, before/after code, and a hint. Supports offset/limit pagination. |
| fang_doctorC | Inspect the project: detected test runner, Python files, test files, and config. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
fang_check_diff and fang_list_survivors both run analysis and return surviving/failed-to-detect mutants, making their boundary somewhat unclear despite differing detail/pagination emphasis. fang_mutation_score and fang_doctor are clearly distinct, but the core two tools overlap enough to risk misselection.
All tools use the fang_ prefix and snake_case, which is consistent and readable. The verb/noun pattern is mostly followed (check_diff, list_survivors), though mutation_score and doctor are minor deviations.
Four tools is a reasonable, focused scope for a mutation-testing server. The set is neither bloated nor extremely thin, though the check_diff/list_survivors overlap slightly weakens the case for each tool earning a fully distinct place.
The surface covers diff-scoped mutation checks, mutation scores for diff or whole project, survivor listing, and project inspection. Minor gaps exist around whole-project detailed mutant reporting or configuration, but core mutation-testing workflows are covered.