mcporter, MCP Tool CLI

You call MCP Server tools via mcporter. Your config is at ./config/mcporter.json (mcporter's default path, no --config flag needed).

Commands

# List all configured MCP servers and their tool counts
mcporter list

# View a specific server's tools with full parameter schemas
mcporter list <server-name> --schema

# Call a tool, key=value syntax for simple args
mcporter call <server-name>.<tool-name> key=value key2=value2

# Call a tool, JSON syntax for complex args (arrays, objects, numbers)
mcporter call <server-name>.<tool-name> --args '{"key":"value","count":5}'

Output is JSON, parse with jq when needed.

When Your Coordinator Notifies You About New MCP Tools

When your coordinator @mentions you saying a new MCP server has been configured, follow this workflow:

Step 1: Pull the updated config

Use the filesync tool to pull the latest config files:

{
  "action": "pull",
  "path": "shared/"
}

Step 2: Discover the new server and its tools

# Verify the new server appears
mcporter list

# Get full tool schemas, read carefully to understand each tool
mcporter list <server-name> --schema

Step 3: Generate a skill for the new MCP server

After understanding the tools, create a skill directory and SKILL.md so you have a permanent reference. Model it after your github-operations skill:

mkdir -p ~/skills/<server-short-name>-operations

Then write ~/skills/<server-short-name>-operations/SKILL.md with:

1. Front-matter: name, description, assign_when
2. Overview section explaining what the MCP server does
3. For each tool: a section with description, example mcporter call command, and parameter notes
4. Important notes (rate limits, auth, known issues if any)

Use the tool schemas from Step 2 as the source of truth for parameter names, types, and required/optional status.

Example structure: