habitica-mcp
Habitica MCP server built with Effect v4, currently exposing a hello-world tool, resource, and prompt over stdio for early development and testing.
README
habitica-mcp
Habitica Model Context Protocol server built with Effect v4 beta.
The server exposes typed Habitica read/write tools over stdio. Tool handlers
depend on an Effect HabiticaGateway port; the live adapter uses Effect HTTP
and schema-decodes Habitica API responses at the boundary.
Requirements
- Node.js
>=22.12.0 - pnpm
>=10
This repo uses pnpm rather than bun because the server runs on Node stdio, the lockfile is already deterministic, and the Effect MCP docs target Node runtime primitives.
Install
pnpm add -g habitica-mcp@alpha
For local development:
pnpm install
Required variables:
HABITICA_USER_IDHABITICA_API_TOKENHABITICA_CLIENT_IDHABITICA_API_BASE_URLdefaults tohttps://habitica.com/api/v3
For a local checkout, copy the example env file and fill in your Habitica credentials:
cp .env.example .env
Commands
pnpm dev # run the stdio MCP server from TypeScript
pnpm build # emit dist
pnpm check # full deterministic gate used by Lefthook
pnpm test # run unit tests
pnpm test:coverage # run unit tests with 100% coverage threshold
pnpm e2e # run strict effect-bdd Gherkin tests
pnpm mutation # run Stryker with 100% mutation threshold
pnpm e2e is a deterministic fake-gateway suite. It exercises the full MCP tool
handler surface without live Habitica credentials or network calls.
Deterministic Gate
pnpm check runs build, typecheck, suppression policy, deterministic scope
policy, custom oxlint RuleTester coverage, oxlint, format check, 100% unit
coverage, strict effect-bdd Gherkin e2e, 100% Stryker mutation coverage for
the deterministic core, and knip.
Lefthook runs pnpm check on pre-commit:
pnpm prepare
GitHub Actions runs the same pnpm check gate on pushes to main and pull
requests.
Tool Surface
HelloWorldTool returns a deterministic greeting and does not require Habitica
credentials. Use it as the first MCP smoke test.
Core tools cover profile, stats, tasks, tags, checklists, and notifications. Expanded tools cover rewards, inventory, shop items, pets, mounts, and skills.
Mutating tools use explicit verb names such as CreateTaskTool,
UpdateTaskTool, DeleteTaskTool, ScoreTaskTool, ReadNotificationTool,
BuyRewardTool, and CastSkillTool. They request approval and return typed
structured results.
Architecture Guardrails
- MCP stdout is protocol-owned; logs go to stderr.
- Tools import
HabiticaGateway, notHabiticaHttpAdapteror raw route strings. - Habitica credentials and auth headers must never be logged.
- Every
Tool.makecall declares a success schema. - Deterministic modules must be listed in coverage and mutation scope.
MCP Config
Use the local TypeScript entrypoint while developing:
{
"mcpServers": {
"habitica": {
"command": "pnpm",
"args": ["--dir", "/absolute/path/to/habitica-mcp", "dev"]
}
}
}
After pnpm build, use the package binary:
{
"mcpServers": {
"habitica": {
"command": "node",
"args": ["/absolute/path/to/habitica-mcp/dist/main.js"]
}
}
}
After installing from npm, use the binary:
{
"mcpServers": {
"habitica": {
"command": "habitica-mcp"
}
}
}
Publishing
This package is intentionally pre-1.0. Publish early builds with the manual
Publish GitHub Actions workflow. It uses the repository NPM_TOKEN secret,
runs pnpm check, and publishes with npm provenance on the alpha dist-tag.
Equivalent local command:
pnpm check
npm publish --tag alpha --provenance
prepack builds dist/; publishConfig marks the package public and enables npm provenance.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.