Skip to content
Agentmart
Submit a tool

PlainQuery | MCP DB Agent

Query PostgreSQL databases in plain English — LLM-generated, safety-validated SQL.

Connector by Jarvis-27 · GitHub account verified by the MCP Registry

IndexedMITRemote (HTTP)
Write a review

Install

Works with Claude Code, VS Code, Cursor, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install connector/jarvis-27-mcp-db-agent

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Remote endpoint

  • https://plainquery.in/mcp/ Remote (HTTP)

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Query PostgreSQL databases in plain English — LLM-generated, safety-validated SQL.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
5 read · 0 write · 0 deleteRead-only
Secrets
1 (API keys, tokens or passwords)
Install scripts
Nothing to install (hosted)
Runs as
Hosted (remote endpoint)

Tools by what they do 5

Read from the source code; the running server may list different tools.

Read 5 · Look things up without changing anything.

  • ask_database
  • describe_schema
  • get_sample_data
  • list_tables
  • query_history

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • X-API-Key

Network hosts it talks to 1

  • plainquery.in · found in remote endpoint, install command

Tools (5)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • ask_databaseAsk database

    Ask a natural-language question about the database. The agent translates your question into SQL, validates it for safety (no writes allowed), executes it, and returns structured JSON results. If the generated SQL fails, it automatically retries with LLM-assisted self-correction up to three times before reporting failure. Returns a JSON object with: - ``query``: the SQL that was executed - ``row_count``: total number of rows returned - ``columns``: list of column names - ``data``: list of row dicts (capped at 100) - ``attempts``: number of generation/correction cycles used - ``cached``: prese…

  • describe_schemaDescribe database schema

    Describe the columns, primary keys, foreign keys, and sample values for a table. Returns a formatted string with full column metadata — type, nullability, whether it is a primary key — plus a few sampled values per column so you can see what the data actually looks like before writing a query. Call list_tables first if you are unsure which tables exist. Args: table_name: Name of the table to describe.

  • get_sample_dataGet sample data

    Get sample rows from a table to understand the data format and values. Returns a JSON array of row objects. The limit is clamped to [1, 20]; use ask_database for larger result sets. Call list_tables first if you are unsure which tables exist. Args: table_name: Name of the table to sample. limit: Number of rows to return (1–20). Defaults to 5.

  • list_tablesList database tables

    List all tables in the database with their row counts. Returns a JSON array where each element has ``table_name`` (str) and ``row_count`` (int). Call this first to discover what data is available before running a query or describing a specific table.

  • query_historyView query history

    See recent questions asked to the database, the SQL generated, and whether they succeeded. Returns a JSON array of the last N queries (default 10), newest first. Each entry has: - ``question``: the original natural-language question - ``sql``: the SQL that was executed - ``success``: whether the query succeeded - ``row_count``: number of rows returned (0 on failure) - ``attempts``: number of generation/correction cycles used - ``duration_ms``: total pipeline wall-clock time in milliseconds - ``error``: error message if the query failed, otherwise ``null`` - ``timestamp``: UTC timestamp of the…

Signals

Stars
0
Forks
0
Open issues
1
Last commit
Jul 12, 2026 (3 months ago)
Last release
May 16, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.Jarvis-27/mcp-db-agent
Version
1.0.1
Auth
API key
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Cite this page

PlainQuery | MCP DB Agent. Agent Mart. https://agentmart.dev/connectors/jarvis-27-mcp-db-agent (last updated 2026-10-24)