Skip to main content
Glama
Sign In
Echoes MCP Server

Echoes MCP Server

Official
by echoes-io
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Echoes MCP Server

CI npm Node License: MIT

Model Context Protocol server for AI integration with the Echoes storytelling platform — Mage image generation and content tools.

Features

  • Mage Image Generation: Queue, monitor, and save AI-generated images via AppSync

  • Word Count: Count words and text statistics in markdown chapter files

  • MCP Resources: Expose Mage status, queue, results, and characters as MCP resources

  • CLI: Full command-line interface for all operations

  • Thin Client: No heavy dependencies — just GraphQL calls to AppSync

Related MCP server: idea-basin-mcp

Installation

npm install -g @echoes-io/mcp-server

Or run directly with npx:

npx @echoes-io/mcp-server --help

Requirements

  • Node.js 22+

  • AppSync API URL and API Key (for Mage tools)

Configuration

Create a .env file in your timeline repo root:

PUBLISHER_API_URL=https://xxx.appsync-api.eu-west-1.amazonaws.com/graphql
PUBLISHER_API_KEY=da2-xxxxxxxxxxxxxxxxxxxx

The timeline is auto-detected from the cwd path (e.g., /path/to/timeline-eros/ → eros).

MCP Client Configuration

{
  "mcpServers": {
    "publisher": {
      "command": "npx",
      "args": ["@echoes-io/mcp-server"]
    }
  }
}

Available Tools

Tool

Description

words-count

Count words and statistics in a markdown file

mage_queue_add

Queue a single image/video generation

mage_queue_add_bulk

Queue multiple generations (one prompt per line)

mage_queue_list

List queued and processing jobs

mage_queue_pause

Pause the queue

mage_queue_resume

Resume the queue

mage_queue_cancel

Cancel a queued job

mage_results_list

List generated results

mage_results_save

Save a result to local filesystem

mage_results_save_all

Save all unsaved results for specified arcs

mage_status

Get overall system status

mage_characters_list

List configured characters with placeholders

Available Resources

URI

Description

publisher://mage/status

Mage system status

publisher://mage/queue

Current queue

publisher://mage/results

Recent results

publisher://mage/characters

Configured characters

CLI Usage

# Word count
echoes words-count ./content/arc/ep01/ch001.md
echoes words-count -d ./content/arc/ep01/ch001.md  # detailed

# Start MCP server
echoes serve

# Mage commands
echoes mage status
echoes mage characters
echoes mage queue list
echoes mage queue add "[01] Full body of [ALE] at café" -t scene -a ale -e 1
echoes mage queue add-bulk "<prompts>" -t scene -a ale -e 1
echoes mage queue pause
echoes mage queue resume
echoes mage queue cancel <job-id>
echoes mage results list
echoes mage results list --unsaved
echoes mage results save <job-id>
echoes mage results save-all --arcs ale cri

Architecture

Agent (Kiro/Claude) → MCP Server (stdio) → AppSync (GraphQL, API Key) → Lambda/DynamoDB
                           ↑
                    .env in timeline repo root

The MCP server is a thin GraphQL client — it doesn't execute any generation logic. It calls the same AppSync mutations/queries used by the Publisher web portal.

Development

# Install dependencies
npm install

# Run tests
npm test

# Run tests with coverage
npm run test:coverage

# Lint
npm run lint

# Type check
npx tsc --noEmit

# Build
npm run build

Tech Stack

Purpose

Tool

Runtime

Node.js 22+

Language

TypeScript

MCP SDK

@modelcontextprotocol/sdk

CLI

Commander

Testing

Vitest

Linting

Biome

License

MIT

Part of the Echoes project — a multi-POV digital storytelling platform.

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityNo data
ResponsivenessSyncing

Resources

Related MCP Connectors

Related MCP Servers

  • Alethea World History Engine

    Watashicuvu
    A
    license
    Not graded
    quality
    D
    maintenance
    A narrative graph engine that enables LLMs to generate, track, and mutate complex fictional worlds while maintaining consistency between factions, characters, and locations. It acts as a specialized RAG framework for storytelling, allowing models to manage thousands of entities without exceeding context limits.
    MIT

  • storyai

    jedikim
    A
    license
    B
    quality
    B
    maintenance
    Enables writers and AI agents to preserve continuity in long-form fiction by maintaining a narrative knowledge graph and exposing MCP tools for querying outlines, entities, references, and consistency diagnostics.
    14
    MIT