ScholarScout
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | No | Free Gemini API key from Google AI Studio. Required when using the Gemini provider. | |
| OPENALEX_API_KEY | No | Free OpenAlex API key with its own daily budget. Optional; without it, ScholarScout shares a small per-IP budget and continues with arXiv alone. | |
| ANTHROPIC_API_KEY | No | Claude API key. Required when using the Claude provider. | |
| SCHOLARSCOUT_MODEL | No | Model name, e.g. `gemini-3.8-flash` or `claude-opus-5-5`. `gemini-3.5-flash-lite` is faster. Defaults to the provider's default model. | |
| SCHOLARSCOUT_EFFORT | No | Thinking effort: `low`, `medium` or `high` (Claude also `xhigh`, `max`). | medium |
| SCHOLARSCOUT_PROVIDER | No | LLM provider to use: `gemini` (free tier) or `claude` (paid). | gemini |
| SCHOLARSCOUT_MAX_PAPERS | No | Number of papers kept after ranking. | 15 |
| SCHOLARSCOUT_MAX_REVISIONS | No | Number of critic and reviser rounds. | 1 |
| SCHOLARSCOUT_EMBEDDING_MODEL | No | Local FastEmbed embedding model. | snowflake/snowflake-arctic-embed-xs |
| SCHOLARSCOUT_QDRANT_LOCATION | No | Qdrant location: `:memory:`, a folder, or a Qdrant server URL. | :memory: |
| SCHOLARSCOUT_FULL_TEXT_PAPERS | No | Number of arXiv PDFs read in full. | 4 |
| SCHOLARSCOUT_REFUSAL_FALLBACK | No | Claude only: retry a declined request on a fallback model. | true |
| SCHOLARSCOUT_CHUNKS_PER_QUESTION | No | Number of passages each researcher receives. | 8 |
| SCHOLARSCOUT_GEMINI_MAX_PARALLEL | No | Number of simultaneous Gemini requests; free-tier limits are per minute. | 2 |
| SCHOLARSCOUT_GEMINI_FALLBACK_MODELS | No | Comma-separated models used when the main model is rate-limited or overloaded (each model has its own free quota). | gemini-3.6-flash,gemini-3.5-flash-lite |
| SCHOLARSCOUT_MAX_FOLLOW_UP_SEARCHES | No | Extra searches a researcher may run. | 1 |
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