PostgreSQL MCP by InsightfulPipe
Server Details
Hosted PostgreSQL MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- Insightful-Pipe/postgresql-mcp-server
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
The read/write split between query_data and execute_action is clear, and prompts_menu serves a distinct prompt-catalog purpose. query_contexts is more of a workflow helper than a peer tool, but the two 'Step 3 FINAL' tools could briefly confuse an agent until the read-only vs write distinction is read.
Three of four tools follow a verb_noun pattern (execute_action, query_contexts, query_data). prompts_menu is noun_noun and slightly breaks the pattern, but the overall set remains predictable and readable.
Four tools is well-scoped for a PostgreSQL gateway: one read path, one write path, one context planner, and one prompt catalog. The surface is lean rather than bloated, though the heavy reliance on meta-tools means only two tools perform core SQL operations.
The tool set covers the essential lifecycle: context discovery, read queries, write/DDL execution, and prompt access. Minor gaps exist around explicit schema browsing, transaction control, and connection management, but these are largely workable through SQL or the context workflow.
Available Tools
4 toolsexecute_actionpostgresql Data Execute ActionADestructiveInspect
Execute postgresql action (Step 3 (FINAL) of workflow).
REQUIRED: Complete these steps first using query_contexts:
request='accounts' - Get workspace_id, brand_id, connection_slug AND available_actions
request='actions_details' with actions=['xxxxxx', 'xxxxxx', 'xxxxxx'] - Get detailed body structure for specific action(s) using actions from available_actions
IMPORTANT: Always call step 2 to see the exact body structure before executing.
execute_action runs write SQL (INSERT/UPDATE/DELETE/DDL). Writes succeed only if your workspace role allows writes and the connected database role has the needed privileges.
Inputs: body (required). Returns: object
query_contextspostgresql Setup HelperARead-onlyInspect
Helper for planning InsightfulPipe postgresql requests.
Step 1: request='accounts' – Retrieve workspace_id, brand_id, connection_slug, other source metadata, AND available_actions (all read-only actions you can call).
Step 2: request='actions_details' with actions=['xxxxxx', 'xxxxxx', 'xxxxxx'] – REQUIRED before querying. Replace with actions from available_actions to get the exact request body, required identifiers, fields, and notes for each action.
Optional: request='available_actions' – Standalone call to list all available actions (already included in accounts response).
Optional: request='brands' with brand_id + workspace_id to pull brand guidelines.
Inputs: request (required), actions, brand_id, platform, +1 more. Returns: object
query_datapostgresql DataARead-onlyInspect
Query postgresql data (Step 3 (FINAL) of workflow).
REQUIRED: Complete these steps first using query_contexts:
request='accounts' - Get workspace_id, brand_id, connection_slug AND available_actions
request='actions_details' with actions=['xxxxxx', 'xxxxxx', 'xxxxxx'] - Get detailed body structure for specific action(s) using actions from available_actions
IMPORTANT: Always call step 2 to see the exact body structure before querying.
query_data accepts read-only SQL only: a single SELECT (or EXPLAIN) statement. Write statements (INSERT/UPDATE/DELETE/DDL) are rejected here - send them through execute_action.
Inputs: body (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Hosted SQL Server MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Hosted MySQL MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Hosted BigQuery MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Hosted Airtable MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA production-ready MCP server for PostgreSQL — built for Claude Desktop, Claude Code, and any MCP-compatible AI agent.Apache 2.0
- AlicenseNot gradedqualityDmaintenanceA general-purpose PostgreSQL MCP server with full read-write SQL access, atomic multi-statement transactions, and schema inspection. Works with any PostgreSQL instance — local, Supabase, AWS RDS, or self-hosted — and connects to Claude, Cursor, Windsurf, or any MCP-compatible AI client.123 npm3ISC
- FlicenseNot gradedqualityDmaintenanceA secure PostgreSQL MCP server allowing AI models to read, write, update, and delete database records with parameterized queries, transactional dry-runs, disposable testing, and automated backups.-
- AlicenseNot gradedqualityDmaintenanceAn extensible MCP server for database operations that supports PostgreSQL for managing schemas, tables, data, and user permissions. It features automatic migration recording for DDL changes and integrates with various AI-powered editors like Cursor, Zed, and Claude Code.26 npm2MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.