Skip to main content
Glama

SQL Server MCP by InsightfulPipe

Server Details

Hosted SQL Server MCP server for Claude, ChatGPT and Cursor, with each action switched per account.

Ownership verified
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/mssql-mcp-server
GitHub Stars
0
ChatGPT
–
Claude
–

TDQS

A3.9/5.0

Scored across 4 tools

Disambiguation4/5

execute_action and query_data are clearly split into write SQL versus read-only SQL, while query_contexts and prompts_menu serve distinct auxiliary purposes. The only mild confusion is the shared Step 3 workflow text repeated in both execute_action and query_data, which could cause brief hesitation.

Naming Consistency4/5

Three tools follow a readable verb_noun pattern in snake_case: execute_action, query_data, and query_contexts. prompts_menu deviates as a noun_noun name, but the overall convention is mostly consistent.

Tool Count4/5

Four tools is a tightly scoped set: one read path, one write path, one context/action-discovery helper, and one prompt catalog. It is slightly thin for a SQL Server MCP, but each tool has a recognizable role.

Completeness4/5

The surface covers reading data, executing writes/DDL, and discovering context/action details, with prompts as an auxiliary catalog. Minor gaps such as no dedicated schema-introspection or transaction-management tool are likely workable through SELECT/EXPLAIN and execute_action.

Available Tools

4 tools
execute_actionmssql Data Execute ActionA
Destructive
Inspect

Execute mssql action (Step 3 (FINAL) of workflow).

REQUIRED: Complete these steps first using query_contexts:

  1. request='accounts' - Get workspace_id, brand_id, connection_slug AND available_actions

  2. 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

prompts_menumssql PromptsA
Read-only
Inspect

Access mssql prompt catalog with 4 operations:

  1. List Public Prompts: • request='menu' - No additional params needed • Returns: All public/system prompts available for mssql

  2. List Custom Prompts: • request='menu', prompt_type='custom', workspace_id= • Returns: All custom prompts for the specified workspace

  3. Get Public Prompt Details: • request='prompt_details', prompt_id= • Returns: Full text/details of a public prompt

  4. Get Custom Prompt Details: • request='prompt_details', prompt_id=, is_custom=True, workspace_id= • Returns: Full text/details of a custom prompt

Inputs: request (required), is_custom, prompt_id, prompt_type, +1 more. Returns: object

query_contextsmssql Setup HelperA
Read-only
Inspect

Helper for planning InsightfulPipe mssql 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_datamssql DataA
Read-only
Inspect

Query mssql data (Step 3 (FINAL) of workflow).

REQUIRED: Complete these steps first using query_contexts:

  1. request='accounts' - Get workspace_id, brand_id, connection_slug AND available_actions

  2. 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

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      A database-agnostic MCP server that enables natural language queries to your database through Claude or Copilot, automatically writing and executing SQL.
      8
      5 npm
      MIT
    • F
      license
      Not graded
      quality
      C
      maintenance
      MCP server that exposes SQL Server databases to Claude, allowing natural language queries with tools to list tables, describe schemas, and run read-only SELECT statements.
      -
    • A
      license
      A
      quality
      D
      maintenance
      MCP server providing read-only access to SQL Server databases for AI assistants, enabling schema exploration, query execution, and foreign key inference with token-efficient TOON responses.
      9
      1
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A comprehensive MCP server for SQL Server database operations, enabling CRUD operations, schema exploration, and stored procedure execution through natural language.
      3 npm
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.