pulse8-ai-cortex-knowledge-vault
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| API_KEY | No | Static API key for x-api-key header (used when AUTH_METHOD=apikey) | |
| QMD_URL | No | External QMD URL for cortex-only mode | |
| VAULT_DIR | No | Path to your vault directory | ./example_vault |
| INGEST_DIR | No | Path to bulk-ingest source directory (mounted as /ingest in Docker) | ./ingest |
| AUTH_METHOD | No | Authentication method: none, apikey, or oidc | none |
| LLM_API_KEY | No | OpenRouter (or compatible) API key (for cross-referencing only) | |
| LLM_BACKEND | No | LLM backend: openai-compatible, bedrock (AWS credential chain), or none (zero LLM calls) | openai-compatible |
| LLM_BASE_URL | No | LLM API base URL | https://openrouter.ai/api/v1 |
| OIDC_BASE_URL | No | Public base URL of the Cortex server (used for OAuth callbacks) | http://localhost:8420 |
| COMPILER_MODEL | No | Model for cross-reference detection | anthropic/claude-sonnet-4 |
| OIDC_CLIENT_ID | No | Microsoft Entra ID app (client) ID | |
| OIDC_TENANT_ID | No | Microsoft Entra ID tenant ID (used when AUTH_METHOD=oidc) | |
| QMD_SEARCH_MODE | No | Default search mode: hybrid, semantic, or keyword | hybrid |
| TEAMS_WEBHOOK_URL | No | Incoming webhook / Power Automate URL | |
| OIDC_CLIENT_SECRET | No | Microsoft Entra ID client secret | |
| TEAMS_APP_BASE_URL | No | Optional public Cortex base URL for a View in Cortex link | |
| QMD_EMBED_TIMEOUT_MS | No | Embed timeout in ms | 600000 |
| QMD_CACHE_TTL_SECONDS | No | TTL for the search-result cache | 30 |
| CORTEX_RESOURCE_MAX_ITEMS | No | LRU cap before oldest entry is dropped | 1000 |
| QMD_SEARCH_TIMEOUT_SECONDS | No | Per-request search timeout | 120 |
| CORTEX_RESOURCE_TTL_SECONDS | No | Max age before a stored resource is evicted | 3600 |
| QMD_REFRESH_INTERVAL_SECONDS | No | Periodic re-index interval (seconds; 0 to disable) | 900 |
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
ActivitySlowing
ResponsivenessNo issues