ask-expert
by NatsUIJM
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ASK_EXPERT_MODEL | Yes | Model ID supported by the endpoint. Required, no default; injected by the caller. | |
| ASK_EXPERT_API_KEY | Yes | API key for the OpenAI-compatible endpoint. Required, no default; injected by the caller via the MCP server environment variable settings. | |
| ASK_EXPERT_TIMEOUT | No | Per-request timeout in seconds; must cover the worst-case single consultation duration. | 600 |
| ASK_EXPERT_BASE_URL | Yes | OpenAI-compatible endpoint base URL (e.g. https://your-endpoint.example/v1). Required, no default; injected by the caller. | |
| ASK_EXPERT_TEMPERATURE | No | Sampling temperature. Default value without empirical basis. | 0.3 |
| ASK_EXPERT_EVIDENCE_ROOTS | No | Colon-separated absolute paths allowed for server-side read-only automatic evidence gathering. Empty disables the feature. | |
| ASK_EXPERT_STREAM_RETRIES | No | Number of backoff retries for retryable errors (timeouts, connection errors, 502/503/504/429). | 2 |
| ASK_EXPERT_CACHE_TTL_HOURS | No | Default cache TTL in hours for other question types. | 72 |
| ASK_EXPERT_MIN_CALL_INTERVAL | No | Minimum interval between consecutive outbound calls, in seconds. | 5.0 |
| ASK_EXPERT_PROGRESS_INTERVAL | No | Minimum interval between progress notifications, in seconds. | 2.0 |
| ASK_EXPERT_MAX_ARTIFACT_CHARS | No | Maximum length of a single audit artifact in characters; exceeding it causes rejection. | 80000 |
| ASK_EXPERT_MAX_EVIDENCE_BYTES | No | Maximum size in bytes/chars for reading a single evidence file. | 20000 |
| ASK_EXPERT_MAX_EVIDENCE_FILES | No | Maximum number of evidence requests handled per automatic evidence round. | 8 |
| ASK_EXPERT_AUTO_EVIDENCE_ROUNDS | No | Maximum number of automatic evidence follow-up rounds; 0 disables the feature. | 0 |
| ASK_EXPERT_CACHE_TTL_CODE_HOURS | No | Cache TTL in hours for code_debug questions. | 24 |
| ASK_EXPERT_CACHE_TTL_MATH_HOURS | No | Cache TTL in hours for math_reasoning questions. | 168 |
| ASK_EXPERT_CACHE_TTL_AUDIT_HOURS | No | Cache TTL in hours for audit results. | 24 |
| ASK_EXPERT_CACHE_TTL_OTHER_HOURS | No | Cache TTL in hours for other question types. | 72 |
| ASK_EXPERT_CACHE_TTL_RESEARCH_HOURS | No | Cache TTL in hours for open_research questions. | 72 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues