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.

DimensionCLIO ParaViewMCP server for ParaView scientific visualizationMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS53 / 100 · D79 / 100 · B
Reliability9 / 2012 / 20
Security and permissions12 / 2018 / 20
Maintenance12 / 2016 / 20
Documentation9 / 2018 / 20
Setup experience11 / 2015 / 20
Best for
  • Researchers in HPC and scientific computing fields
  • Scientists working with large-scale 3D scientific datasets needing visualization
  • AI agent developers wanting to add scientific visualization tools
  • Individuals using Python-based toolchains in HPC environments
  • 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
  • Basic data plotting that does not require advanced or interactive ParaView features (consider the plot MCP).
  • General-purpose 3D modeling or rendering outside scientific contexts.
  • Interactive GUI-driven workflows rather than scripted automation.
  • Users without technical background in Python or HPC environments.
  • 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
  • Runs the `clio-kit` command to access the MCP server.
  • Reads and writes the file system to load data and save outputs (e.g., STL, screenshots).
  • May interact with local ParaView processes to perform visualization operations.
  • Accesses environment variables and Python environments due to its Python-based nature.
  • 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
  • May require ParaView or its Python bindings to be installed on the system; failure to do so could lead to errors.
  • File read/write operations could overwrite or export files unexpectedly if unrestricted; ensure appropriate permissions.
  • Automated visualizations can be computationally intensive (especially for large datasets), impacting performance.
  • As part of a third-party package, it is not officially maintained by ParaView, and updates may lag.
  • 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, Cursor, Claude Code, VS CodeClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools260