daggerheart-ai
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
daggerheart-ai
MCP server for semantic search over the Daggerheart SRD (~790 markdown files + 212 bestiary creatures), exposed to Claude Code during DnD session prep.
Tools
search_srd — semantic search across all rules, abilities, classes, equipment, and lore.
get_entry — fetch a named entry by category + name (exact or partial match).
query_monsters — filter adversaries + creatures by tier, role, thematic
family, difficulty range, attack range, keyword, and source. Bestiary environments are excluded by default (include_environmentsto add them).list_entries — list every entry in a category.
Related MCP server: ragi
How it works
Content is indexed once into a local SQLite database (srd.db) with
bge-small-en-v1.5 embeddings (384-dim) stored in sqlite-vec. Searches
use sqlite-vec KNN with a brute-force cosine fallback.
Embeddings are computed fully on-device via
fastembed (ONNX Runtime) — no
API key, no proxy, no network. The model (~30MB) downloads once to
.fastembed_cache/ on first use, then everything runs offline.
Setup
Prerequisites: Node 18+. No accounts, keys, or proxies.
npm install # uses .npmrc: Netflix registry + legacy-peer-depsSRD content
The srd/ folder is git-ignored. Populate it from your vault copy, then index:
rsync -a --exclude='.git' --exclude='.build' --exclude='.github' \
'/path/to/daggerheart-srd/' srd/
npm run index # one-time; clears + rebuilds the index (first run downloads the model)
npm run buildRe-run npm run index after any SRD change.
Register with Claude Code
Add to the relevant project/vault .mcp.json:
"daggerheart": {
"type": "stdio",
"command": "node",
"args": ["/Users/chrisdhanaraj/projects/daggerheart-ai/dist/index.js"]
}Restart Claude Code, then /mcp should show daggerheart connected with 4 tools.
Scripts
Script | Purpose |
| Embed the SRD into |
| Compile |
| Run the server from source via tsx |
| Run the built server ( |
Notes
Never write to stdout in the server — it is the JSON-RPC channel. Logs go to stderr.
Embeddings are on-device (
fastembed/ bge-small-en-v1.5, 384-dim). The query side usesqueryEmbed(BGE instruction prefix); indexing usesembed.sqlite-vec
vec0primary keys must be bound asBigIntin better-sqlite3.Rebuild (
npm run build) after any change undersrc/.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Official remote MCP server for Archivist AI TTRPG campaign memory: characters, sessions, and more.
An MCP server for search and retrieval over a local LanceDB database
MCP server for querying Forkast documentation
Related MCP Servers
- AlicenseAqualityBmaintenanceD\&D 5e SRD MCP server - monster search, spell lookup, encounter building, and character tools powered by ground-truth SRD data2097 npm8MIT
- AlicenseAqualityDmaintenanceLocal-first RAG indexing and semantic search MCP server. Enables document retrieval and context-aware queries using local embedding models.36 npmMIT

SagaSmith D&D MCPofficial
AlicenseNot gradedqualityFmaintenanceA local MCP server for Dungeons & Dragons campaign management, combining core runtime with skill and module-generation packs. It enables campaign creation, module generation and import, rule and skill searching via tools, resources, and prompts.Apache 2.0- FlicenseNot gradedqualityBmaintenanceSelf-hosted MCP server for D&D 5e rules reference, answering rule questions, providing character summaries, and assisting with character creation, based on imported sources with proper attribution.-