Supertag Cli

Created By
jcfischer5 months ago
Complete MCP server for Tana PKM with 16 tools. Full-text and semantic vector search, unified query language with field filtering, graph traversal, meeting transcript search, aggregation/analytics, and node creation. Runs 100% locally - no cloud, no tracking. Works with Claude Desktop, ChatGPT, Cursor, VS Code Copilot, Claude Code, and Windsurf.
Overview

what is Supertag Cli?

Supertag Cli is a complete MCP server for Tana PKM that provides 18 tools for full-text and semantic vector search, unified query language, graph traversal, meeting transcript search, aggregation/analytics, and node creation, all running locally without cloud dependency or tracking.

how to use Supertag Cli?

To use Supertag Cli, set up the server by configuring the command with your TANA_WORKSPACE and run the standalone binary. You can then access various tools for searching, exploring, and mutating your data.

key features of Supertag Cli?

  • Full-text search across your workspace
  • Semantic vector search for content by meaning
  • SQL-like query capabilities with field filtering
  • Graph traversal to find connected nodes
  • Meeting transcript search and management
  • Local operation with no cloud or tracking

use cases of Supertag Cli?

  1. Conducting in-depth research with full-text and semantic searches.
  2. Managing and analyzing meeting transcripts for insights.
  3. Creating and organizing nodes with specific supertags for better data management.

FAQ from Supertag Cli?

  • Is Supertag Cli cloud-based?

No, Supertag Cli runs 100% locally with no cloud dependency.

  • What tools are included in Supertag Cli?

It includes tools for searching, exploring, and mutating data, such as full-text search, semantic search, and transcript management.

  • Do I need Node.js to run Supertag Cli?

No, Supertag Cli is a standalone binary and does not require Node.js.

Server Config

{
  "mcpServers": {
    "tana": {
      "command": "/path/to/supertag-mcp",
      "env": {
        "TANA_WORKSPACE": "main"
      }
    }
  }
}
Project Info
Created At
5 months ago
Updated At
4 months ago
Author Name
jcfischer
Star
-
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

20 hours ago
Gpt Scrambler

2 days ago