Houdini MCP Server
houdini-mcp-server
PyPI
v0.6.0
Published by jtche — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Connect AI Agents to SideFX Houdini, with full documentation and screenshot support.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 10
high Dynamic evaluation of a non-literal value (src/houdinimcp/handlers/code.py)MTC-SRC-010
In the server's implementation (`src/houdinimcp/handlers/code.py:212`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: Globals() val = eval(expression, result) else: val = hou.hscriptExpression(expression) return {"
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/houdinimcp/handlers/code.py
high Dynamic code execution in server code (src/houdinimcp/handlers/code.py)MTC-SRC-001
In the server's implementation (`src/houdinimcp/handlers/code.py:151`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: r_capture): exec(compile(code, name, "exec"), namespace) except watchdog.Stopped: stopped = watc
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/houdinimcp/handlers/code.py
high Dynamic code execution in server code (src/houdinimcp/handlers/parameters.py)MTC-SRC-001
In the server's implementation (`src/houdinimcp/handlers/parameters.py:244`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ves the index back from eval(), never the token that was written, so the raw value decides for a token. """
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/houdinimcp/handlers/parameters.py
high Shell/command execution in server code (src/bridge/connection.py)MTC-SRC-002
In the server's implementation (`src/bridge/connection.py:370`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ssions()} _hython = subprocess.Popen([hython, HEADLESS_SCRIPT], env=houdini_env(), st
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/bridge/connection.py
high Shell/command execution in server code (src/bridge/onboarding/harnesses.py)MTC-SRC-002
In the server's implementation (`src/bridge/onboarding/harnesses.py:94`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: p add --scope user" subprocess.run(["claude", "mcp", "remove", "--scope", "user", SERVER_NAME], c
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/bridge/onboarding/harnesses.py
high Shell/command execution in server code (src/bridge/onboarding/install.py)MTC-SRC-002
In the server's implementation (`src/bridge/onboarding/install.py:126`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: eturn True result = subprocess.run(["uv", "sync"], cwd=REPO_DIR, stdout=tui.stream) if result.returncode != 0:
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/bridge/onboarding/install.py
high Shell/command execution in server code (src/bridge/tools/render.py)MTC-SRC-002
In the server's implementation (`src/bridge/tools/render.py:64`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: s", "aux"] result = subprocess.run(command, capture_output=True, text=True, timeout=30) processes = [] for
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/bridge/tools/render.py
high Shell/command execution in server code (src/houdinimcp/handlers/code.py)MTC-SRC-002
In the server's implementation (`src/houdinimcp/handlers/code.py:151`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: r_capture): exec(compile(code, name, "exec"), namespace) except watchdog.Stopped: stopped = watc
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/houdinimcp/handlers/code.py
high Shell/command execution in server code (src/houdinimcp/handlers/offscreen.py)MTC-SRC-002
In the server's implementation (`src/houdinimcp/handlers/offscreen.py:169`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: "hython") result = subprocess.run([hython, os.path.join(os.path.dirname(__file__), "gl_child.py"),
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/houdinimcp/handlers/offscreen.py
high Shell/command execution in server code (src/houdinimcp/handlers/sheets.py)MTC-SRC-002
In the server's implementation (`src/houdinimcp/handlers/sheets.py:113`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: , ".mp4")) result = subprocess.run( [_encoder(), "-y", "-loglevel", "error", "-framerate", str(fps),
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/houdinimcp/handlers/sheets.py
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 3
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.6.0 latest |
A 93/100 | 10 | 1.14.0 | 2026-09-28 |
v0.5.0 |
A 93/100 | 10 | 1.14.0 | 2026-09-25 |
v0.4.2 |
A 93/100 | 7 | 1.14.0 | 2026-09-20 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan houdini-mcp-server --online --registry pypiMore in Developer Tools
Hotel booking MCP server — 300K+ properties, real confirmation numbers, loyalty programs. Builders monetize every booking via Stripe Connect. The first MCP server that completes real hotel reservations inside AI conversations.
Generates production-ready UI components from natural language, inspired by v0.
Model Context Protocol server that serves the A11y Context accessibility-pattern corpus (WCAG 2.2 AA patterns, Foundations rules) to AI coding agents.
Manage AdGuard Home through AI assistants
Read-only Azure DevOps for MCP clients using only your existing browser session — no PAT, no Azure CLI. Browse work items, pull requests, comments, attachments and Artifacts feeds across every project, repo and feed you can access.
MCP server for Adobe Experience Manager Assets integration development