Skip to main content
Glama
homello

Homello MCP

Official
by homello
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Homello MCP

Minimal Model Context Protocol (MCP) stdio server for the Homello platform.

  • Package: @homello/mcp

  • Binary: mcp

  • License: AGPL-3.0-only

  • Runtime: Node.js ≥ 20

What it does

Exposes a single MCP tool over stdio:

  • homello.get_info – returns Homello product/docs metadata plus effective runtime config (API base, market, timeout, debug). Response is emitted as both text and structuredContent.

Quick start

# Run once (no install)
npx -y @homello/mcp

# Or add to a project
npm i -D @homello/mcp
npx mcp

The default command is start. It connects over stdio and waits for an MCP client.

With Goose (auto-install an extension)

Writes/updates ~/.config/goose/config.yaml (override with GOOSE_DIR or GOOSE_CONFIG_PATH).

# Install/update the extension entry
npx -y @homello/mcp install \
  --enabled=true \
  --timeout=300 \
  --available-tools homello.get_info \
  --env HOMELLO_API_BASE=https://api.homello.ai \
  --env-key HOMELLO_API_KEY

# Remove the extension entry
npx -y @homello/mcp uninstall

Common options:

  • --id (default: homello) – extension id

  • --name (default: Homello MCP)

  • --description (default: Homello platform integration)

  • --cmd (default: npx) and repeated --arg (default: -y @homello/mcp@latest)

  • --enabled (default: false)

  • --timeout seconds (default: 300)

  • --bundled true|false|null (default: null)

  • repeated --available-tools (e.g. homello.get_info)

  • repeated --env KEY=VALUE (persist literal values)

  • repeated --env-key KEY (reference variables to be supplied by the host)

Configuration

Config is resolved from process env, then Goose extension envs, with these keys:

  • HOMELLO_API_BASE (default: https://api.homello.ai)

  • HOMELLO_API_KEY (default: empty)

  • HOMELLO_DEFAULT_MARKET (default: US)

  • HOMELLO_TIMEOUT_SECS (default: 30)

  • HOMELLO_DEBUG (1|true enables debug; default: 0)

Local dev toggle:

  • HOMELLO_MCP_LOCAL_DEV=1
    Uses a dev extension id (homellomcp) and local Node/entrypoint paths from DEFAULTS.localCmd/localArgs.

CLI

# Start the stdio server (same as no subcommand)
mcp start

# Create/update Goose extension entry
mcp install [options]

# Remove Goose extension entry
mcp uninstall [--id homello]

Tool contract

homello.get_info returns:

{
  "platform": "Homello",
  "api_base": "https://api.homello.ai",
  "market": "US",
  "timeout_secs": 300,
  "debug": false,
  "docs": { "...": "..." }
}

docs is sourced from a packaged JSON bundle.

Development

# Dev (tsx)
npm run dev

# Build
npm run build

# Watch typescript
npm run watch

# Release patch version
npm run release

Node/stdio details

  • Transport: @modelcontextprotocol/sdk stdio (McpServer + StdioServerTransport)

  • Server identity: name: homello-mcp, version: 0.2.0, description: MCP server connecting to the Homello platform

  • Graceful shutdown on SIGINT/SIGTERM.

Repository

https://github.com/homello/mcp

Available Tools

1 tool
homello.get_infoHomello Platform InfoB

Returns Homello platform information and docs

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure but only states what is returned, not how. It omits critical details like response format, potential errors, rate limits, or authentication requirements, which are essential for safe and effective tool invocation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise—a single, clear sentence with no wasted words. It is front-loaded with the core action and resource, making it easy to parse and understand immediately.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of annotations and output schema, the description is incomplete. It fails to explain what 'platform information and docs' entails, such as data structure, examples, or usage scenarios, leaving significant gaps for the agent to infer behavior and results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters, and the input schema has 100% description coverage (though empty), so no parameter documentation is needed. The description appropriately does not discuss parameters, earning a baseline score of 4 for this context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('Returns') and resource ('Homello platform information and docs'), making it immediately understandable. However, with no sibling tools to differentiate from, it cannot achieve a perfect score of 5 for sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool, such as for retrieving system status, documentation links, or version details. It lacks any context about prerequisites, alternatives, or specific use cases, leaving the agent without operational direction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool update
    • First observedhomello.get_info
Deploy Server
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

TDQS

B3.2/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap between tools. The single tool has a clear and distinct purpose: retrieving platform information and documentation.

Naming Consistency5/5

The naming follows a consistent pattern of server_name.verb_noun (homello.get_info). With only one tool, there is no inconsistency to evaluate, and the naming is clear and predictable.

Tool Count2/5

A single tool is too few for most practical server purposes, as it severely limits functionality and scope. This feels thin and inadequate for a platform that likely requires more operations beyond just retrieving basic info.

Completeness1/5

The tool surface is severely incomplete for a platform server. It only provides get_info, with no CRUD operations, data manipulation, or other essential functions expected from a platform, leading to significant gaps and dead ends for agents.

Resources

Related MCP Connectors