M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

DimensionFXHoudini MCP ServerThe most comprehensive MCP server for SideFX HoudiniMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS65 / 100 · C79 / 100 · B
Reliability11 / 2012 / 20
Security and permissions11 / 2018 / 20
Maintenance15 / 2016 / 20
Documentation15 / 2018 / 20
Setup experience13 / 2015 / 20
Best for
  • VFX artists and TDs who want to accelerate Houdini workflows with AI assistants
  • Users needing procedural modeling and simulation setup
  • Users familiar with Houdini but wanting to automate repetitive tasks
  • Engineering teams scaling AI coding agents while controlling spend
  • Platform teams that need auditable, rollback-aware agent execution records
  • Organizations using multiple agents (Claude, Codex, Gemini) under one governed flow
Not for
  • Users without Houdini 20.5+
  • Scenarios requiring real-time interactive operation with low latency
  • Environments with strict security policies that cannot accept arbitrary Python execution
  • Developers who just want a simple code-completion helper without run governance
  • Teams unwilling to accept local JSONL run records with HMAC signing
  • Environments without a supported adapter (Claude/Codex/Gemini CLIs, direct provider, or verifier-only)
Required permissions
  • Access Houdini's Python API to execute arbitrary hou.* calls
  • Run code on Houdini's main thread, potentially blocking the UI
  • Communicate with local Houdini over HTTP port (default 8100)
  • May read/write files depending on tools used (e.g., rendering, caching)
  • Read/write access to the configured repo root (writable scope restrictable via --allow-path/--deny-path)
  • Ability to invoke the chosen agent CLI (Claude/Codex/Gemini, etc.) and its underlying model account
  • Local disk writes for run records, receipts, and share outputs (share/run-receipt., etc.)
  • Execution of user-configured verifier commands (e.g. npm test)
Risks and side effects
  • Arbitrary Python execution: improper AI instructions could damage scenes or systems
  • Network port exposure: default binds to loopback, but widening could allow unauthorized access
  • Performance overhead: each call has ~50 ms main-thread latency; many calls can slow Houdini
  • Version compatibility: outdated plugins may cause malfunctions
  • Verifier commands are executed; poorly chosen verifier commands carry security risk despite preflight policy checks
  • Cost and token figures may be estimates (labeled with provenance) and should not be treated as settled accounting
  • Receipt integrity must be verified before use as trustworthy evidence; missing rollback evidence is flagged as EVIDENCE_BOUNDARY
  • Policy defaults come from martin.config.yaml and can be overridden by CLI flags; misconfiguration can loosen safety boundaries
Supported clientsClaude Desktop, Claude CodeClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools1000