pg-mcp-bridge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PG_MCP_TOKEN | Yes | Same bearer token as in server config.php | |
| PG_MCP_TUNNEL_URL | Yes | Full URL to pg_mcp_tunnel.php |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_schemasA | List non-system PostgreSQL schemas available through the remote tunnel |
| list_tablesA | List tables and views in a schema |
| describe_tableA | Describe columns, types, nullability, defaults, and primary key for a table |
| queryA | Run a single SQL statement. Allowed statements depend on server access_mode: readonly (SELECT/EXPLAIN/SHOW), readwrite (+ INSERT/UPDATE/DELETE), full (+ CREATE/ALTER/DROP and other DDL). Use ping to see the current access_mode. Only one statement per call. |
| pingA | Check tunnel and PostgreSQL connectivity; returns version, database, user, and access_mode (readonly|readwrite|full) |
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 5 tools
Each tool has a clear, unique purpose: listing schemas, listing tables, describing columns, running SQL queries, and checking connectivity. There is no overlap or ambiguity.
All tool names use a consistent snake_case verb_noun pattern, such as list_schemas, list_tables, describe_table, query, and ping. The naming is predictable and uniform.
With 5 tools, the server covers all essential operations for a PostgreSQL bridge: schema exploration, table metadata, column details, arbitrary SQL execution, and connectivity checks. The count is well-scoped without unnecessary extras.
The tool surface is complete for its domain, providing full CRUD-like capabilities through the general query tool, plus necessary introspection tools. There are no obvious gaps; it supports both read and write operations as per access mode.