How do I install the Dial MCP Server skill?

Run npx skillmds@latest add tomevault-io/dial-mcp-server in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Dial MCP Server safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Dial MCP Server?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Dial MCP Server free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Dial MCP Server?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Dial MCP Server by tomevault-io — Agent Skill

Name: Dial MCP Server
Author: tomevault-io

File contents

MCP Server Mode

Expose DIAL as tools via the Model Context Protocol (MCP).

Start the Server

npx dialai --mcp

Configure Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "dialai": {
      "command": "npx",
      "args": ["dialai", "--mcp"]
    }
  }
}

Config File Location

Platform	Path
macOS	`~/Library/Application Support/Claude/claude_desktop_config.json`
Windows	`%APPDATA%\Claude\claude_desktop_config.json`
Linux	`~/.config/Claude/claude_desktop_config.json`

Available Tools

Once connected, Claude has access to these tools:

Tool	Description
`create_session`	Start a new decision process from a machine definition
`get_session`	Get current state and history of a session
`get_sessions`	List all sessions
`register_proposer`	Register a proposer specialist for a machine
`register_arbiter`	Register an arbiter specialist for a machine
`submit_proposal`	Submit a transition proposal
`evaluate_consensus`	Check if consensus has been reached (read-only)
`submit_arbitration`	Evaluate consensus and optionally execute the winning transition
`execute_transition`	Apply a transition directly
`run_session`	Run a machine to completion
`get_collapse_metrics`	Get progressive collapse metrics
`get_decision_log`	Get decision log records

Example Conversation

User: Create a code review session for my PR.

Claude (using tools):

1. create_session({ machine: { machineName: "code-review", ... } })
2. register_proposer({ specialistId: "ai-reviewer", machineName: "code-review", strategyFnName: "firstAvailable" })
3. register_arbiter({ specialistId: "arbiter", machineName: "code-review", strategyFnName: "alignmentMargin" })
4. submit_proposal({ sessionId: "...", specialistId: "ai-reviewer" })
5. submit_arbitration({ sessionId: "..." })

Tool Schemas

create_session

{
  "machine": {
    "machineName": "code-review",
    "initialState": "pending",
    "goalState": "approved",
    "states": { ... }
  }
}

submit_proposal

{
  "sessionId": "session-uuid",
  "specialistId": "proposer-id",
  "transitionName": "approve",
  "reasoning": "Why this transition"
}

Server Options

# Stdio transport (default for MCP)
npx dialai --mcp

Debugging

Check server logs:

npx dialai --mcp --verbose

Test with MCP Inspector:

npx @modelcontextprotocol/inspector npx dialai --mcp

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

---name: dial-mcp-serverdescription: Run DIAL as an MCP server for AI assistants. Use when integrating with Claude Desktop or other MCP clients. Use when this capability is needed.---# MCP Server ModeExpose DIAL as tools via the Model Context Protocol (MCP).## Start the Server```bashnpx dialai --mcp```## Configure Claude DesktopAdd to `claude_desktop_config.json`:```json{ "mcpServers": { "dialai": { "command": "npx", "args": ["dialai", "--mcp"] } }}```### Config File Location| Platform | Path ||----------|------|| macOS | `~/Library/Application Support/Claude/claude_desktop_config.json` || Windows | `%APPDATA%\Claude\claude_desktop_config.json` || Linux | `~/.config/Claude/claude_desktop_config.json` |## Available ToolsOnce connected, Claude has access to these tools:| Tool | Description ||------|-------------|| `create_session` | Start a new decision process from a machine definition || `get_session` | Get current state and history of a session || `get_sessions` | List all sessions || `register_proposer` | Register a proposer specialist for a machine || `register_arbiter` | Register an arbiter specialist for a machine || `submit_proposal` | Submit a transition proposal || `evaluate_consensus` | Check if consensus has been reached (read-only) || `submit_arbitration` | Evaluate consensus and optionally execute the winning transition || `execute_transition` | Apply a transition directly || `run_session` | Run a machine to completion || `get_collapse_metrics` | Get progressive collapse metrics || `get_decision_log` | Get decision log records |## Example Conversation**User**: Create a code review session for my PR.**Claude** (using tools):```1. create_session({ machine: { machineName: "code-review", ... } })2. register_proposer({ specialistId: "ai-reviewer", machineName: "code-review", strategyFnName: "firstAvailable" })3. register_arbiter({ specialistId: "arbiter", machineName: "code-review", strategyFnName: "alignmentMargin" })4. submit_proposal({ sessionId: "...", specialistId: "ai-reviewer" })5. submit_arbitration({ sessionId: "..." })```## Tool Schemas### create_session```json{ "machine": { "machineName": "code-review", "initialState": "pending", "goalState": "approved", "states": { ... } }}```### submit_proposal```json{ "sessionId": "session-uuid", "specialistId": "proposer-id", "transitionName": "approve", "reasoning": "Why this transition"}```## Server Options```bash# Stdio transport (default for MCP)npx dialai --mcp```## DebuggingCheck server logs:```bashnpx dialai --mcp --verbose```Test with MCP Inspector:```bashnpx @modelcontextprotocol/inspector npx dialai --mcp```---> Converted and distributed by [TomeVault](https://tomevault.io/claim/eloquentanalytics) — claim your Tome and manage your conversions.

Frequently asked questions

Dial MCP Server