Mantora

★ 5

from josephwibowo

Mantora is a local-first MCP observer: a lightweight UI + proxy for inspecting LLM data access (sessions, tool calls, results) with protective defaults.

🔥🔥🔥✓ VerifiedFreeQuick setup

#automation #slack #database #git

⌁ labsco summary — our analysis, not the vendor's

What it is — Mantora is a local-first MCP observer: a lightweight UI plus proxy that sits between your agent and its database, logging LLM data access with protective defaults.

What you get —

Session logs — capture the exact SQL and tool calls an agent makes for verification and reproduction
Protective mode — basic guardrails that block or warn on destructive SQL patterns by default
Shareable Markdown reports — one-click "Copy for GitHub" produces a collapsible <details> block with SQL, timing, and safety checks for PRs or Slack
A Control Room UI (localhost:3030) to create, activate, and switch DB targets without restarting the agent

Requirements — env is empty. Install with pipx install "mantora[duckdb,postgres]"; targets like DuckDB/Postgres are configured in the UI or a mantora.toml.

Cost snapshot — Open source under MIT; free. Local-first, no paid service.

Setup effort — pipx install mantora, add the mantora mcp proxy to your client, then mantora up for the dashboard.

Our take — A useful accountability layer for DB-touching agents, but it's focused on SQL targets (DuckDB/Postgres), and the author calls the guardrails "basic" — it's a review/log tool, not a full policy engine.

Source: the project README — summarized 2026-07-08.

⌁ readme from github — mirrored (latest on GitHub ↗)

Mantora 🛡️

The open-source run log for MCP agents. Get a shareable report to verify and reproduce what the agent did — plus a protective mode for common dangerous SQL.

Mantora UI screenshot

Mantora focuses on making agent behavior reviewable and repeatable. It records the key evidence from each session and turns it into a Markdown report. Protective mode adds basic guardrails (block/warn rules) so you don’t learn about a bad query the hard way.

What you get

🔍 Session Logs

Capture the exact SQL and tool calls an agent makes for easy verification.

Session Logs

🛡️ Protective Mode

Basic guardrails that block or warn on destructive SQL patterns by default.

Protective Mode

🧾 Shareable Reports

One-click to generate a Markdown summary for Pull Requests or Slack.

Shareable Reports

Daily Workflow

📋 Copy a PR Report

Don't paste messy screenshots. In the Session Summary, click "Copy for GitHub".

Result: A collapsible <details> block containing the SQL, execution time, and safety checks. Perfect for Pull Requests.

🛑 Review Blocked Mutations

If an agent tries to DROP TABLE users, Mantora intercepts it.

The Agent sees: "Error: Action blocked by safety policy."
You see: A red entry in the Mantora UI with the exact SQL that was blocked.

📤 Export Evidence

Need to archive a session?

Export JSON: Get the raw trace data.
Download Markdown: Get a readable log of the entire conversation.

Safety Defaults

Mantora is designed to be read-only safe out of the box.

Action	Default Policy
`SELECT`	✅ Allowed
`INSERT`, `UPDATE`	⚠️ Requires Approval (Configurable)
`DELETE` (with WHERE)	⚠️ Requires Approval
`DROP`, `TRUNCATE`	🛑 Blocked
`DELETE` (no WHERE)	🛑 Blocked

Want to change this? See Configuration.

Supported Data Stores

DuckDB (Local files, MotherDuck)
Postgres (Direct connection, Supabase, Neon)
BigQuery, Snowflake, Databricks (Coming Soon)

All data is stored locally. See Privacy for details.

Documentation

Configuration Guide - Flags, ports, and policy overrides.
Architecture - How the proxy internals work.
Contributing - Build setup and testing.

Copy & paste — that's it

{
  "mcpServers": {
    "mantora": {
      "command": "mantora",
      "args": ["mcp"]
    }
  }
}

Quick Start

1. Install

pipx install "mantora[duckdb,postgres]"

2. Connect Your Agent

Configure your MCP client (e.g., claude_desktop_config.json or Cursor Settings) to run the Mantora proxy. No target configuration is needed here!

{
  "mcpServers": {
    "mantora": {
      "command": "mantora",
      "args": ["mcp"]
    }
  }
}

3. Run the Control Room (UI)

Start the dashboard to manage your connections and view logs in real-time:

mantora up

4. Configure Targets

Open the Control Room (http://localhost:3030) and use the target switcher in the top navigation bar to:

Create new targets for your databases (DuckDB, Postgres, etc.).
Activate the target you want your agent to use.
Switch targets instantly without restarting your agent.

Note: For advanced configuration (safety policy, storage paths), you can use a mantora.toml file. See Configuration for details.

How it works

sequenceDiagram
    participant Agent as Claude/Cursor
    participant Mantora as Mantora 🛡️
    participant DB as Postgres/DuckDB

    Agent->>Mantora: "SELECT * FROM users"
    Note over Mantora: 1. Check Safety Policy
    Mantora->>DB: Execute Query
    DB-->>Mantora: Return Rows
    Note over Mantora: 2. Log Report (Async)
    Mantora-->>Agent: Relay Result