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/jtche/houdini-mcp/architecturegit clone --depth 1 https://github.com/JTCHE/houdini-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/jtche/houdini-mcp/architecture)<a href="https://agentmods.dev/agents/jtche/houdini-mcp/architecture"><img src="https://agentmods.dev/badge/agents/jtche/houdini-mcp/architecture.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 | $0.00281 |
| Opus 5 | $0.00000 | $0.00140 |
| Sonnet 5 | $0.00000 | $0.00056 |
| Haiku 4.5 | $0.00000 | $0.00028 |
Grade A, and why
architecture 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 4d ago.
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.
What it actually says
Architecture
Three layers. Each runs in a different process.
- Bridge —
houdini_mcp_server.py. Speaks MCP over stdio to the client. Speaks JSON over a TCP socket to the plugin. Holds the tool definitions. - Plugin —
src/houdinimcp/. Runs inside Houdini.server.pyaccepts the socket and dispatches tohandlers/. Only this layer importshou. - Offline —
houdini_docs.pyandscripts/. No Houdini needed.houdini_docs.pyreads the documentation from HoudiniMD over HTTP.scripts/onboarding/installs,scripts/runtime/starts a session,scripts/ingest/parses.hipfiles.
A tool that needs hou gets a wrapper in the bridge and a function in a handler
module. A tool that does not need hou stays in the bridge alone.
Boundaries
- The plugin must not know about MCP. The bridge must not import
hou. - Each handler module owns one Houdini context (nodes, geometry, LOPs, COPs...). A new context gets a new module, not a longer existing one.
- Handlers take plain JSON and return plain JSON. Keep Houdini types inside.
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.
- 4d ago First seen · 23 lines · 0 tokens per session scan A 495f287c4505
architecture is an agent published in the GitHub repository JTCHE/houdini-mcp (3 stars, last pushed 28d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 281 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.