intently
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GROQ_API_KEY | No | LLM vendor key (any subset of vendors can be used) | |
| GEMINI_API_KEY | No | LLM vendor key (any subset of vendors can be used) | |
| OPENAI_API_KEY | No | LLM vendor key (any subset of vendors can be used) | |
| INTENTLY_CHAINS | No | JSON file overriding the model fallback chains (query, rerank, bulk) | |
| OPENAI_BASE_URL | No | Custom base URL for OpenAI-compatible endpoints | |
| DEEPSEEK_API_KEY | No | LLM vendor key (any subset of vendors can be used) | |
| INTENTLY_PROFILE | No | corpus profile JSON | ai-tools |
| INTENTLY_VENDORS | No | Restrict vendors, e.g. 'groq,gemini' | |
| MOONSHOT_API_KEY | No | LLM vendor key (any subset of vendors can be used) | |
| ANTHROPIC_API_KEY | No | LLM vendor key (any subset of vendors can be used) | |
| INTENTLY_DATA_DIR | No | corpus, cards, index, caches, model | ./intently-data |
| INTENTLY_PUBLIC_URL | No | The public URL for agents to use, shown in UI, llms.txt and tool output | |
| INTENTLY_EMBED_MODEL | No | Any sentence-transformers model that publishes onnx/model.onnx (rebuild after changing) | MongoDB/mdbr-leaf-ir |
| INTENTLY_PROXY_SECRET | No | Accept only requests from a reverse proxy that sends X-Intently-Proxy-Secret, and trust its X-Forwarded-For | off |
| INTENTLY_PUBLIC_API_URL | No | The public API URL for agents to use, shown in UI, llms.txt and tool output | |
| INTENTLY_PUBLIC_MCP_URL | No | The public MCP URL for agents to use, shown in UI, llms.txt and tool output | |
| INTENTLY_SMART_DAILY_LIMIT | No | LLM-backed requests per process per day before offline mode | off |
| INTENTLY_RATE_LIMIT_PER_DAY | No | Per-client limits on search, find-tools, answer and MCP tool calls | off |
| INTENTLY_RATE_LIMIT_PER_MIN | No | Per-client limits on search, find-tools, answer and MCP tool calls | off |
| INTENTLY_FIND_TOOLS_DEADLINE | No | Seconds find_tools waits for reranking | 9 |
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