Midplane
Safe-by-default SQL guardrails for AI agents: AST-checked queries, per-table policy, audit log.
Power your agent
Add this server
The publisher's own command. Not a PlugMCP endpoint.
Local command
npx -y [email protected]
Credentials from the publisher
- DATABASE_URL — Postgres connection string the agent's queries run against. Give it a least-privilege role: Midplane constrains what SQL is allowed, it does not widen or narrow what the role itself can reach.
- MIDPLANE_POLICY_FILE — Path to a policy YAML granting per-table read/read_write access, tenant scoping, and column masking. Omit for the safe default: reads allowed, writes and DDL denied. Generate one with `npx midplane init`.
- DB_PATH — Where the local SQLite audit log is written. Defaults to ~/.midplane/audit.db; read it back with `midplane audit denies`.
- MIDPLANE_TELEMETRY — Set to 0 to disable anonymous usage telemetry (DO_NOT_TRACK=1 also works). Never includes SQL, table or column names, or identifiers.
Provider
Claude Code
DATABASE_URL=<secret> MIDPLANE_POLICY_FILE=<value> DB_PATH=<value> MIDPLANE_TELEMETRY=<value> claude mcp add ai.midplane-midplane -- npx -y [email protected]
Run in a terminal.
Claude Desktop
{
"mcpServers": {
"ai.midplane-midplane": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"DATABASE_URL": "<secret>",
"MIDPLANE_POLICY_FILE": "<value>",
"DB_PATH": "<value>",
"MIDPLANE_TELEMETRY": "<value>"
}
}
}
}claude_desktop_config.json
Remote URL or a command on your machine? How the two installs differ
Run on PlugMCP
Host a copy with our keys and logs.
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
LaunchRelated MCP
View more- Firecrawl🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
- NNotionToken-auth Notion MCP: pages, databases, blocks, comments, files. Runs headless in CI and agents.
- Context7Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
Related skills
View all- reaReverse engineer anything with agents, from app behavior down to native binaries.
- rea-changelog-updatePrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.
- rea-tool-designDesign or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.
Safe-by-default SQL guardrails for AI agents: AST-checked queries, per-table policy, audit log.
README is not crawled yet. Open the repository
- How do I install Midplane?
- Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.
- Does Midplane need an API key?
- The publisher lists these environment variables: DATABASE_URL, MIDPLANE_POLICY_FILE, DB_PATH, MIDPLANE_TELEMETRY, PORT.
- What transport does Midplane use?
- Midplane runs locally over stdio.
- When was Midplane last checked?
- Last checked 2026-10-16. Safe-by-default SQL guardrails for AI agents: AST-checked queries, per-table policy, audit log.
No tool list yet. Remote servers get one after the first health check.