api-shakedown
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_API_KEY | No | Bring your own key for OpenAI. | |
| SHAKEDOWN_MODEL | No | Model to use, per provider. Defaults: `qwen3:8b` (Ollama), `gpt-5-mini` (OpenAI), `claude-sonnet-5-5` (Anthropic). | |
| ANTHROPIC_API_KEY | No | Bring your own key for Anthropic. | |
| SHAKEDOWN_TIMEOUT | No | Seconds per request. Defaults: 600 (Ollama) / 120. | |
| SHAKEDOWN_BASE_URL | No | Endpoint override, e.g. an OpenAI-compatible server. | |
| SHAKEDOWN_PROVIDER | No | LLM provider to use. One of `ollama`, `openai`, or `anthropic`. | ollama |
| SHAKEDOWN_REASONING | No | Ollama: turn a reasoning model's thinking on/off. Default: model default. | |
| SHAKEDOWN_OLLAMA_URL | No | Where Ollama runs. | http://localhost:11434 |
| SHAKEDOWN_AGENT_MODELS | No | Per-agent models, e.g. `{"reviewer": "anthropic:claude-sonnet-5-5"}`. | |
| SHAKEDOWN_CONTEXT_WINDOW | No | Ollama context size. | 16384 |
| SHAKEDOWN_AGENT_REASONING | No | Per-agent thinking, e.g. `{"reviewer": true}`. Default: thinking off for generators. |
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
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| doctorA | Check that the configured LLM provider is reachable and the model is available. |
| inspect_specA | Load and validate an OpenAPI spec (file path or http(s) URL) and list its operations. |
| generate_harnessA | Generate a ready-to-run chaos test harness for an OpenAPI spec into out_dir. offline=true skips the LLM (deterministic, seconds); otherwise this takes minutes on a local model, and review=false roughly halves that. Refuses a non-empty out_dir unless force=true (which overwrites only the harness's own files). |
| list_chaos_scenariosB | List the chaos scenarios of a generated harness. |
| activate_chaosA | Turn one chaos scenario on in the harness's running WireMock (others go off). |
| deactivate_chaosB | Turn all chaos scenarios off: the stubs behave normally again. |
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 6 tools
Each tool targets a clearly distinct step: provider health check (doctor), spec loading/validation (inspect_spec), harness generation (generate_harness), and scenario listing/toggling (list/activate/deactivate_chaos). There is no meaningful overlap between any pair.
Five of six tools follow a clean snake_case verb_noun pattern (inspect_spec, generate_harness, list_chaos_scenarios, activate_chaos, deactivate_chaos). The lone outlier 'doctor' is a bare noun, a minor but visible deviation from the otherwise consistent convention.
Six tools is well-scoped for a focused chaos-testing pipeline, with each tool mapping to a necessary step from provider check to scenario toggling. Nothing feels padded or missing at the count level.
The surface covers the core lifecycle: verify provider, inspect spec, generate harness, and toggle scenarios. Minor gaps exist around harness execution/teardown (no explicit start/stop/reset of WireMock, and deactivate is all-or-nothing), but these are workable around.