io.github.ashishsinha1602/schemagate MCP Server
io.github.ashishsinha1602/schemagate
What this kind of tool is for
- Query, inspect, or seed a database without writing a one-off script.
- Let your agent look up schema details before it writes migration code.
- Move a small dataset between tools without leaving the terminal.
How to compare servers like this
- Engine match:
- Confirm it speaks your exact database and version, not just the family.
- Access scope:
- Read-only connections are the safe default — start there before granting writes.
- Safety rails:
- Check whether destructive statements need an explicit confirmation before they run.
- Maintenance signal:
- Database drivers change; a recently updated tool is less likely to break mid-query.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the io.github.ashishsinha1602/schemagate MCP server?
Identity-scoped schema selection for text-to-SQL. Returns only the tables the caller may read.
How to install io.github.ashishsinha1602/schemagate
Copy-paste configuration for popular MCP clients.
SCHEMAGATE_DATABASE_URLrequiredsecretSQLAlchemy URL of the database to reflect, or 'demo' for the bundled schema
SCHEMAGATE_CATALOG_CONFIGOptional path to a JSON file with roles, hints and shadow-name overrides
{
"mcpServers": {
"schemagate": {
"command": "python",
"args": [
"schemagate",
"-m",
"schemagate.mcp_server"
],
"env": {
"SCHEMAGATE_DATABASE_URL": "<YOUR_SCHEMAGATE_DATABASE_URL>",
"SCHEMAGATE_CATALOG_CONFIG": "<YOUR_SCHEMAGATE_CATALOG_CONFIG>"
}
}
}
}Related MCP servers

io.github.ashwinvis/scb-opendata-mcp
Statistics Sweden’s open data made available as an MCP server, using Python and FastMCP

Yandex Metrica MCP
MCP server for Yandex Metrica API: list counters, goals and pull web-analytics statistics.

CogniRepo
Persistent memory and context for AI agents—FAISS, AST, call graphs, and 35 MCP tools for 50–80% token reduction.

Lexicon
Fixes the names and jargon speech-to-text gets wrong before your agent acts on a dictated prompt.
