nextQ MCP server
Officialby forecastera
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NEXTQ_TENANTS | No | Registry JSON secret holding every tenant's database and the rules that map users to tenants. | |
| NEXTQ_AUTH_MODE | No | Authentication mode. `static` / `none` for local development only. | workos |
| NEXTQ_LOG_LEVEL | No | Log level. | INFO |
| NEXTQ_DEV_TOKENS | No | Static dev tokens for testing tenant routing with NEXTQ_AUTH_MODE=static. | |
| NEXTQ_ENVIRONMENT | No | Environment. `production` requires `workos` auth. | production |
| NEXTQ_CATALOG_PATH | No | Alternative catalog path. | nextq_mcp/data/catalog.yaml |
| NEXTQ_SCORING_PATH | No | Alternative scoring path. | nextq_mcp/data/scoring.yaml |
| NEXTQ_TENANTS_FILE | No | Path to the tenant registry JSON file (alternative to NEXTQ_TENANTS). | |
| NEXTQ_PUBLIC_BASE_URL | Yes | Public base URL of the server, e.g. https://<server-name>.fastmcp.app | |
| NEXTQ_DB_POOL_MAX_SIZE | No | Maximum per-tenant database pool size (per instance). | 8 |
| NEXTQ_DB_POOL_MIN_SIZE | No | Minimum per-tenant database pool size (per instance). | 1 |
| NEXTQ_QUERY_TIMEOUT_MS | No | Statement timeout in milliseconds. | 15000 |
| NEXTQ_RATE_LIMIT_BURST | No | Per-user rate limit burst. | 20 |
| NEXTQ_MAX_RESPONSE_BYTES | No | Tool responses are truncated above this size. | 200000 |
| NEXTQ_SEARCH_TTL_SECONDS | No | Search index refresh TTL in seconds. | 1800 |
| NEXTQ_CONTEXT_TTL_SECONDS | No | Per-account cache TTL in seconds. | 300 |
| NEXTQ_RATE_LIMIT_PER_SECOND | No | Per-user rate limit per second, counts every MCP request. | 5 |
| NEXTQ_WORKOS_AUTHKIT_DOMAIN | Yes | WorkOS AuthKit domain, e.g. https://your-app.authkit.app | |
| NEXTQ_SEARCH_WARM_ON_STARTUP | No | Build every tenant's index at startup (2 at a time). | true |
| NEXTQ_DB_STATEMENT_CACHE_SIZE | No | Set 0 behind PgBouncer in transaction mode. | 100 |
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 | |