Universal Database MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ANVAYA_JWT_SECRET | No | Secret key for JWT tokens. If not set, authentication is disabled. | |
| ANVAYA_MCP_TRANSPORT | No | Transport mode (e.g., 'http' for Streamable HTTP, 'stdio' for stdio). Defaults to stdio if not set. | |
| ANVAYA_DEFAULT_DB_URI | No | Default database URI used when no specific db_uri is provided. | sqlite:///test.db |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_database_schemaA | Discover tables, columns, primary keys, and foreign-key relationships, filtered to only what your role is allowed to see. |
| execute_safe_queryA | Validate and run a read-only SELECT statement. Applies RBAC, tenant row-level filtering, and sensitive-data masking before returning results. |
| explain_sql_queryA | Return the database's execution plan for a read-only SELECT statement, so query performance can be checked before running it. |
| export_results_formatB | Run a read-only query (through the same security checks as execute_safe_query) and return it reshaped for a specific use. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
get_database_schema and explain_sql_query are clearly distinct from each other. However, export_results_format and execute_safe_query both run read-only queries, and the difference (reshaping/output format vs. raw results) is only clear from the description, creating mild overlap.
All names use snake_case with a verb-first pattern (export_, get_, execute_, explain_), which is predictable and readable. export_results_format is slightly awkward (verb_noun_noun) but still follows the convention.
Four tools is lean but well-scoped for a read-only, safety-focused query server; each tool covers a distinct capability (schema, query, plan, export). It sits just above the thin end of the range but earns its place.
The read-only lifecycle is well covered: discover schema, inspect plans, run queries, and export results. Gaps are minor, such as no way to list available databases/connections, but the stated read-only purpose is served without dead ends.