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.

DimensionCodex SlidesThe open-source AI slide studio that lives inside CodexMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS67 / 100 · C79 / 100 · B
Reliability11 / 2012 / 20
Security and permissions12 / 2018 / 20
Maintenance14 / 2016 / 20
Documentation17 / 2018 / 20
Setup experience13 / 2015 / 20
Best for
  • Developers and teams already using Codex who want decks made inside their coding agent
  • Workflows that need image-native slides with high visual fidelity
  • Reports and launches that turn research, data, or documents into PPTX/PDF
  • Users who want project data on their own disk with no extra API keys
  • 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 who need individually editable PowerPoint shapes and text boxes (export is currently full-slide images)
  • Users on clients other than Codex, such as Claude Desktop (installation is a Codex plugin)
  • Users needing live collaboration or shareable read-only present links (not shipped)
  • Users needing video or animated slide export (still exploring)
  • 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
  • Read and write the local project data directory (default <repo>/data, or the OS app-data directory for desktop builds)
  • Access the local HTTP service (default http://127.0.0.1:4311)
  • Network access for deep web research and image generation
  • Reuse existing codex login credentials for text, research, and image generation
  • 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
  • Exported PPTX text is not editable because each slide is a full-slide image
  • Slide quality depends on the underlying models and prompts, so regeneration may be needed
  • Project data, uploaded sources, and generated images stay on disk and can contain sensitive material — do not commit them
  • Community-style previews keep their upstream licenses and attribution; the project's MIT license does not relicense them, so check source terms before redistributing
  • Downloaded desktop builds are not notarized, so macOS and Windows may require manual approval on first launch
  • 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 clientsCodexClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools380