Echoes MCP Server
OfficialClick on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Echoes MCP Serversearch the bloom arc for Alice's first meeting"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Echoes MCP Server
Model Context Protocol server for AI integration with Echoes storytelling platform.
Features
Narrative Knowledge Graph: Automatically extracts characters, locations, events, and their relationships using Gemini AI
Semantic Search: Find relevant chapters using natural language queries
Entity Search: Search for characters, locations, and events
Relation Search: Explore relationships between entities
Arc Isolation: Each arc is a separate narrative universe - no cross-arc contamination
Statistics: Aggregate word counts, POV distribution, and more
Dynamic Prompts: Reusable prompt templates with placeholder substitution
Installation
npm install -g @echoes-io/mcp-serverOr run directly with npx:
npx @echoes-io/mcp-server --helpRequirements
Node.js 20+
Gemini API key (for entity extraction)
Usage
CLI
# Count words in a markdown file
echoes words-count ./content/arc1/ep01/ch001.md
# Index timeline content
echoes index ./content
# Index only a specific arc
echoes index ./content --arc bloom
# Get statistics
echoes stats
echoes stats --arc arc1 --pov Alice
# Search (filters by arc to avoid cross-arc contamination)
echoes search "primo incontro" --arc bloom
echoes search "Alice" --type entities --arc bloom
# Check narrative consistency
echoes check-consistency bloom
echoes check-consistency bloom --rules kink-firsts,outfit-claimsMCP Server
Configure in your MCP client (e.g., Claude Desktop, Kiro):
{
"mcpServers": {
"echoes": {
"command": "npx",
"args": ["@echoes-io/mcp-server"],
"cwd": "/path/to/timeline",
"env": {
"GEMINI_API_KEY": "your_api_key"
}
}
}
}Environment Variables
Variable | Required | Default | Description |
| Yes | - | API key for Gemini entity extraction |
| No |
| Gemini model for extraction |
| No |
| HuggingFace embedding model |
| No |
| Quantization level: |
| No | - | HuggingFace token for gated models |
Available Tools
Tool | Description |
| Count words and statistics in a markdown file |
| Index timeline content into LanceDB |
| Search chapters, entities, or relations |
| Get aggregate statistics |
| Analyze arc for narrative inconsistencies |
| Quick overview of all arcs: status, chapters, words, POVs |
| Export knowledge graph in various formats |
| Query character/arc history (kinks, outfits, locations, relations) |
| Generate review file for pending entity/relation extractions |
| Show review statistics for an arc |
| Apply corrections from review file to database |
Available Prompts
Prompt | Arguments | Description |
| arc, episode?, lastChapters? | Load complete context for resuming work on an arc |
| arc, chapter | Create a new chapter |
| arc, chapter | Revise an existing chapter |
| arc, chapter, target | Expand chapter to target word count |
| name | Create a new character sheet |
| arc, episode | Create a new episode outline |
| name | Create a new story arc |
| arc | Review and fix an entire arc |
Architecture
Content Hierarchy
Timeline (content directory)
└── Arc (story universe)
└── Episode (story event)
└── Chapter (individual .md file)Arc Isolation
Each arc is treated as a separate narrative universe:
Entities are scoped to arcs:
bloom:CHARACTER:Alice≠work:CHARACTER:AliceRelations are internal to arcs
Searches can be filtered by arc to avoid cross-arc contamination
Data Flow
┌─────────────────────────────────────────────────────────────┐
│ INDEXING PHASE │
├─────────────────────────────────────────────────────────────┤
│ 1. Scan content/*.md (filesystem scanner) │
│ 2. Parse frontmatter + content (gray-matter) │
│ 3. For each chapter: │
│ a. Extract entities/relations with Gemini API │
│ b. Generate embeddings (Transformers.js ONNX) │
│ c. Calculate word count and statistics │
│ 4. Save everything to LanceDB │
└─────────────────────────────────────────────────────────────┘Development
# Install dependencies
npm install
# Run tests
npm test
# Run tests with coverage
npm run test:coverage
# Lint
npm run lint
# Type check
npm run typecheck
# Build
npm run buildTech Stack
Purpose | Tool |
Runtime | Node.js 20+ |
Language | TypeScript |
Vector DB | LanceDB |
Embeddings | @huggingface/transformers (ONNX) |
Entity Extraction | Gemini AI |
MCP SDK | @modelcontextprotocol/sdk |
Testing | Vitest |
Linting | Biome |
Performance Notes
Embedding Quantization
The default embedding model (Xenova/e5-small-v2) supports different quantization levels via ECHOES_EMBEDDING_DTYPE:
Level | Speed | Quality | Memory | Recommendation |
| Baseline | Best (100%) | High | Production with ample resources |
| 2-3x faster | Excellent (99.6%) | 50% less | Recommended - optimal balance |
| 3-4x faster | Good (99.1%) | 75% less | Resource-constrained environments |
Note: Some models like onnx-community/embeddinggemma-300m-ONNX don't support fp16. Always check model documentation.
Recommended setting:
export ECHOES_EMBEDDING_DTYPE=q8License
MIT
Part of the Echoes project - a multi-POV digital storytelling platform.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/echoes-io/mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server