Chaos-MCP
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 | {} |
| prompts | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| audit_code_resilienceA | Runs on-demand, sandbox-isolated mutation testing against a single source file to identify gaps in unit test coverage. Chaos-MCP generates mutants (logical faults like changing |
| triage_test_coverageA | Batch triage: audit a set of files and/or directories and return a weakest-first ranked leaderboard of mutation scores, so you can see where the test suite is most fragile in one call. Directories are recursively expanded to supported source files (.ts/.js/.py/.rs/.php), skipping test files. Files are audited in parallel (see fileConcurrency, default min(4, cpus-1)), under a shared wall-clock budget (see totalTimeoutMs). Drill into a weak file with audit_code_resilience for per-mutant survivor detail: each row's |
| estimate_auditA | Cheap pre-flight estimate of how big/long auditing a file will be, WITHOUT running the full mutation test cycle. Returns an approximate mutant count (for Rust, an exact count of the mutants cargo-mutants --list GENERATES — the audit scores fewer, excluding unviable ones as |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| harden_file | Walk through hardening one file: audit → write tests for survivors → verify by runId → repeat. |
| triage_changes | Triage a PR's changed files weakest-first, then harden the weakest. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Supported languages | Languages, their mutation engine, line-scope support, and estimate fidelity. |
| Config schema | chaos-mcp.config.json keys with types and meaning. |
| Capabilities overview | The three tools, their arguments, and the triage→audit→verify workflow. |
TDQS
Scored across 3 tools
Each tool occupies a distinct stage of the workflow: estimate_audit is pre-flight sizing, audit_code_resilience is a deep single-file mutation audit, and triage_test_coverage is a batch leaderboard. There is no meaningful overlap in purpose, and the descriptions make the differences explicit.
All three tool names follow a consistent verb_noun snake_case pattern: estimate_audit, audit_code_resilience, triage_test_coverage. The verbs clearly indicate the operation and the objects describe the domain artifact being acted on.
Three tools is minimal but well-scoped for a focused mutation-testing server: estimate, single-file audit, and batch triage. Each tool earns its place and there is no filler or redundant utility.
The tool set covers the full workflow: triage to find weak files, estimate to decide whether to audit, and audit to get detailed per-mutant survivor information. No obvious gaps exist for the stated purpose of mutation-testing coverage analysis.