Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/homeassistant-ai/ha-mcp/developmentgit clone --depth 1 https://github.com/homeassistant-ai/ha-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/homeassistant-ai/ha-mcp/development)<a href="https://agentmods.dev/agents/homeassistant-ai/ha-mcp/development"><img src="https://agentmods.dev/badge/agents/homeassistant-ai/ha-mcp/development.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.02039 |
| Opus 5 | $0.00000 | $0.01019 |
| Sonnet 5 | $0.00000 | $0.00408 |
| Haiku 4.5 | $0.00000 | $0.00204 |
Grade A, and why
development scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development reference
Read this document when setting up the repository, running the server, choosing
verification commands, researching Home Assistant APIs, or orienting yourself
in the architecture. Behavioral rules about when testing is required remain in
AGENTS.md; test implementation details live in
tests/AGENTS.md.
External documentation
| Resource | Use |
|---|---|
| Home Assistant REST API | Entity states, services, and configuration. |
| Home Assistant WebSocket API | Events, subscriptions, and in-process commands. |
| Home Assistant Core | Undocumented or version-specific behavior. |
| Home Assistant app development | App packaging and configuration. |
| FastMCP | MCP server framework. |
| Model Context Protocol | Protocol semantics. |
Prefer current primary sources. When local behavior depends on an undocumented Home Assistant detail, verify it against the exact upstream source or a focused runtime test rather than relying on memory.
Setup and server commands
uv sync --group dev
cp .env.example .env
uv run ha-mcp
uv run ha-mcp-web
ha-mcp uses stdio and needs interactive stdin. ha-mcp-web runs HTTP mode
and serves the settings UI at http://localhost:8086/mcp/settings. Settings UI
details are in
src/ha_mcp/settings_ui/AGENTS.md.
Test commands
E2E tests live in tests/src/e2e/ (not tests/e2e/), use testcontainers,
and require a running Docker daemon. Launch them from tests/ so pytest
loads the correct conftest.py. Unit tests in tests/src/unit/ do not use
Docker.
# Full E2E suite. Use only before claiming the full suite passes.
(cd tests && uv run pytest src/e2e/ -n2 --dist loadscope -v --tb=short)
# One relevant E2E file.
(cd tests && uv run pytest src/e2e/workflows/automation/test_lifecycle.py -v)
# Unit suite, parallel as in CI.
(cd tests && uv run pytest src/unit/ -n auto --tb=short)
# Interactive isolated Home Assistant environment.
uv run hamcp-test-env
uv run hamcp-test-env --no-interactive
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 207 lines · 0 tokens per session scan A 8c70686e907b
development is an agent published in the GitHub repository homeassistant-ai/ha-mcp (4,594 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,039 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-02.
Other agents, from other repositories
raise-pull-request
Use this agent when creating a pull request for the Home Assistant core repository after completing implementation work. This agent automates the PR creation process including running tests, formatting checks, and proper checkbox handling.
blocky-bump-review
The concrete definition of what CLAUDE.md calls the manual review a Blocky bump requires. Renovate opens these as a one-line change to BLOCKYVERSION in blocky/Dockerfile (Tempio bumps are the same shape via TEMPIOVERSION). Most bumps merge as that bare one-liner — this runbook is how you earn that conclusion instead…
ha-esphome-config-reviewer
Produces one bundled, read-only device-level review of an ESPHome device configuration: config-pattern conformance, credential and API/OTA hardening, schema currency against the official ESPHome docs, Home-Assistant-driven binding correctness, display rendering discipline, display design conformance (palette roles…
ha-esphome-fleet-reviewer
Produces one bundled, read-only repository-level review of an ESPHome fleet: directory layout, package architecture and concern cuts, the substitution and defaults interface each package exposes, deviation handling through !extend / !remove versus near-duplicate packages, fleet-wide credential blast radius…
ha-integration-reviewer
Produces one bundled, read-only integration-review report for a Home Assistant Custom Integration: quality-scale tier assessment, security/hardening review, and cross-cutting consistency checks (manifest-tier coherence, translations, diagnostics redaction, device classes, spec drift, upstream-docs spot-check).…
gemini-robotics
Gemini Robotics (anchored by Gemini Robotics 3 and its embodied reasoning variant, Gemini Robotics ER 3) is Google DeepMind's flagship model family designed for physical hardware orchestration, humanoid whole-body control, and multi-robot fleet coordination. It operates as a Vision-Language-Action (VLA) foundation…