Repo Test Architect
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_repositoryA | Start here for an unfamiliar repository or a general test-architecture review. Detect and audit all project roots once, then return the complete deterministic summary, blockers, findings, ranking, plan, execution hints, verification commands, and stats. Prefer this over audit_repo unless one project root and adapter were explicitly selected. |
| list_adaptersA | List registered language adapters available to audit repositories. |
| list_project_detection_rulesA | List deterministic project marker rules and ignored directories used during project detection. |
| detect_projectsB | Detect project roots and matching adapters inside a repository. |
| audit_projectsA | Return raw per-project audit artifacts for all detected supported roots and report unsupported roots. Use when a downstream specialist tool needs project-audits/v1; for a complete first-pass review, prefer analyze_repository. |
| summarize_project_auditsA | Summarize an existing project-audits/v1 artifact. Use only when a compact coverage view is needed separately; analyze_repository already includes this result. |
| rank_project_candidatesA | Rank candidates from an existing project-audits/v1 artifact while preserving project identity. analyze_repository already includes this result. |
| generate_project_test_planA | Generate a project-aware plan from an existing project-audits/v1 artifact. analyze_repository already includes this result. |
| collect_project_findingsA | Collect concise top findings from an existing project-audits/v1 artifact. analyze_repository already includes this result. |
| analyze_project_test_placementA | Analyze project-aware test placement from a project-audits artifact. |
| collect_project_statsB | Collect local deterministic project audit stats for coverage, counts, risk and signal distributions, framework distribution, and adapter usage. |
| audit_repoA | Audit one explicitly selected project root and return audit/v1. Use only when the caller selected a single adapter or project boundary; adapterId defaults to javascript. For an unfamiliar or complete repository review, use analyze_repository. |
| get_audit_graphA | Validate and return an existing audit/v1 artifact unchanged; this does not scan a repository. Use audit_repo or analyze_repository for repository discovery. |
| generate_test_planB | Generate a deterministic test plan from an audit graph. |
| get_plan_execution_hintsA | Derive provider-neutral execution, context, parallel-safety, and repository-reasoning hints from a plan without invoking models or subagents. |
| explain_targetB | Explain one audit target by stable target id. |
| rank_test_candidatesA | Rank testable audit targets by risk reduction and maintenance cost. |
| analyze_test_placementB | Analyze existing test placement from an audit graph and return advisory placement findings. |
| generate_selected_testA | Return a structured deferred result. This tool does not generate or write test code while native generation remains disabled. |
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 19 tools
Most tools have clearly distinct purposes, and descriptions explicitly guide when to use which (e.g., analyze_repository vs audit_repo vs audit_projects). Some overlap exists among tools that operate on the same project-audits/v1 artifact, but their scopes and usage notes are clearly differentiated.
Tool names generally follow a verb_noun pattern with underscores (e.g., list_adapters, detect_projects, generate_test_plan). Minor deviations include using 'repo' instead of 'repository' (audit_repo vs analyze_repository) and inconsistency between 'project_test_plan' and 'test_plan', but the overall pattern is predictable.
The server has 19 tools, which falls in the borderline heavy range. While each tool has a specific role, many are specialized subsets of the umbrella analyze_repository tool, making the count feel slightly inflated for the core purpose.
The tool set covers the major steps of repository analysis: detection, audit, summarization, ranking, planning, placement analysis, and execution hints. However, generate_selected_test is a deferred stub that does not actually generate test code, and there is no tool to modify detection rules or adapters, leaving some gaps in the full lifecycle.