TextToSQL MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | No | Model name for the LLM (default: gpt-oss:120b) | gpt-oss:120b |
| SKILL_DIR | No | Where skills live | skills/ |
| FIXTURE_DIR | No | Where fixtures live | tests/ |
| LLM_API_KEY | No | API key for the LLM endpoint (default: ignored for local) | |
| SCHEMA_NAME | Yes | Schema to introspect/query (required; SQLite: main) | |
| DATABASE_URL | Yes | Async SQLAlchemy DSN (required) | |
| LLM_BASE_URL | No | Base URL for the LLM endpoint (default: http://localhost:11434/v1) | http://localhost:11434/v1 |
| INTROSPECTION | No | true during Phases 1–2, false in production | false |
| MCP_HTTP_PORT | No | HTTP port (default 8765) | 8765 |
| DEV_DB_VERSION | No | Bump to invalidate the harness result cache | 0 |
| LANGFUSE_ENABLED | No | Enable Langfuse tracing (default: false) | false |
| SAMPLE_ROW_LIMIT | No | Sample rows per table in drafts | 100 |
| EXPLAIN_HARD_COST | No | Cost guard threshold to reject (PostgreSQL only) | 10000 |
| EXPLAIN_WARN_COST | No | Cost guard threshold to warn (PostgreSQL only) | 1000 |
| LANGFUSE_BASE_URL | No | Langfuse base URL | |
| LLM_PROBE_TIMEOUT | No | Timeout in seconds for probing the primary LLM endpoint (default: 2) | 2 |
| LLM_FALLBACK_MODEL | No | Fallback model (default: openrouter/auto) | openrouter/auto |
| LANGFUSE_PUBLIC_KEY | No | Langfuse public key | |
| LANGFUSE_SECRET_KEY | No | Langfuse secret key | |
| LLM_FALLBACK_API_KEY | No | Fallback API key (required for fallback to work) | |
| ALLOWED_QUERY_SCHEMAS | No | Extra schemas SELECTs may reference (empty = SCHEMA_NAME only) | |
| LLM_FALLBACK_BASE_URL | No | Fallback LLM base URL (default: https://openrouter.ai/api/v1) | https://openrouter.ai/api/v1 |
| INTROSPECTION_TABLE_PREFIXES | No | CSV of table-name prefixes to limit scope (empty = all) |
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
ActivityStale
ResponsivenessNo issues