npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@mikado-ai/cli

v0.3.2

Published

Mikado AI CLI and MCP server — submit transcripts, extract insights, integrate with AI agents

Readme

@mikado-ai/cli

Command-line interface and MCP server for Mikado AI — submit conversation transcripts, extract structured insights, and integrate with AI agents.

Install

npx @mikado-ai/cli

Or install globally:

npm install -g @mikado-ai/cli

Quick Start

# 1. Authenticate (get your API key from Mikado AI → Settings → API Keys)
mikado auth

# 2. See available campaigns
mikado campaigns

# 3. Submit a transcript
mikado submit transcript.txt --campaign 928721aa

Authentication

Interactive

mikado auth

You'll be prompted for your API key and server URL.

Non-Interactive

mikado auth --key mkd_your_api_key --url https://mikadoai.app

Environment Variable

export MIKADO_API_KEY=mkd_your_api_key
export MIKADO_URL=https://mikadoai.app

Environment variables take precedence over the config file.

Config File

Credentials are stored in ~/.mikado/config.json. The file is created with restricted permissions (owner-only read/write).

Commands

mikado submit <file>

Submit a conversation transcript for processing. By default, waits for results.

# Submit and wait for results (default)
mikado submit transcript.txt --campaign 928721aa

# Submit without waiting
mikado submit transcript.txt --campaign 928721aa --no-wait

# Read from stdin
cat transcript.txt | mikado submit -

# JSON output for scripting
mikado submit transcript.txt --campaign 928721aa --json

# Custom timeout (default: 300s)
mikado submit transcript.txt --timeout 60

Options:

| Flag | Description | |------|-------------| | -c, --campaign <id> | Campaign UUID, UUID prefix, or name | | --no-wait | Return immediately with job ID | | --timeout <seconds> | Max wait time (default: 300) | | --json | Output JSON to stdout |

mikado campaigns

List available campaigns in your organization.

mikado campaigns
  ID        Name              Status    Templates Conversations
  928721aa  Sales Calls       ACTIVE    2         142
  3f8a2b1c  Support Tickets   ACTIVE    1         89

mikado status <job-id>

Check the processing status of a submitted transcript.

mikado status 3f8a2b1c-...
  Job:      3f8a2b1c-...
  Status:   ✓ SUCCESS
  Duration: 11.2s
  Insights: 1 generated
  Sentiment: positive (0.82)

mikado result <conversation-id>

Retrieve full results for a processed conversation.

mikado result 550e8400-...

mikado auth

Set up or update authentication credentials.

mikado auth
mikado auth --key mkd_... --url https://api.mikado.ai

JSON Output

All commands support --json for machine-readable output. Errors go to stderr, data goes to stdout.

# Pipe to jq
mikado submit transcript.txt --campaign 928721aa --json | jq '.insights[0]'

# Batch processing
for f in transcripts/*.txt; do
  mikado submit "$f" --campaign 928721aa --json >> results.jsonl
done

Exit Codes

| Code | Meaning | |------|---------| | 0 | Success | | 1 | General error (auth failure, network error) | | 2 | Invalid arguments | | 3 | Processing failed (pipeline error) | | 4 | Timeout (polling exceeded --timeout) |

MCP Server

Use Mikado AI as a tool in AI agents via the Model Context Protocol.

Configuration

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "mikado": {
      "command": "npx",
      "args": ["-y", "-p", "@mikado-ai/cli", "mikado", "mcp"],
      "env": {
        "MIKADO_API_KEY": "mkd_your_api_key",
        "MIKADO_URL": "https://mikadoai.app"
      }
    }
  }
}

Claude Code:

claude mcp add mikado -- npx -y -p @mikado-ai/cli mikado mcp

Available Tools

| Tool | Description | |------|-------------| | mikado_submit_and_wait | Submit a transcript and wait for full results. Primary tool for AI agents. | | mikado_submit | Submit a transcript, return immediately with job ID. | | mikado_status | Check processing status of a job. | | mikado_result | Get results for a completed conversation. | | mikado_campaigns | List available campaigns. |

Example Agent Workflow

1. Call mikado_campaigns to see available campaigns
2. Call mikado_submit_and_wait with transcript + campaign
3. Use the returned insights (scores, labels, extracted data) in your response

Local Development

cd cli
npm install
npm run build      # Build to dist/
npm run dev        # Watch mode

# Test locally
node dist/index.js --help
node dist/index.js auth --key mkd_... --url http://localhost:8100

Requirements

  • Node.js 18 or later
  • A Mikado AI account with an API key

License

MIT