pg-mcp
by awaketai
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_MODEL | No | Model to use for SQL generation | gpt-4o |
| OPENAI_API_KEY | Yes | OpenAI API key | |
| OPENAI_BASE_URL | No | Custom endpoint (Azure, proxy, etc.) | |
| PG_MCP_MAX_ROWS | No | Max rows returned (1-1000) | 100 |
| PG_MCP_DATABASES | Yes | Comma-separated PostgreSQL connection strings | |
| PG_MCP_LOG_LEVEL | No | Log level: DEBUG, INFO, WARNING, or ERROR | INFO |
| PG_MCP_DEFAULT_DB | No | Default database for queries (defaults to first DSN in PG_MCP_DATABASES) | |
| PG_MCP_QUERY_TIMEOUT | No | Query timeout in seconds | 30 |
| PG_MCP_SCHEMA_CACHE_PATH | No | Path for persistent schema cache |
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 | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/awaketai/postgres-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server