inkscape-mcp

mcp
Guvenlik Denetimi
Basarisiz
Health Uyari
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 10 GitHub stars
Code Basarisiz
  • fs module — File system access in .github/workflows/dependencies.yml
  • child_process — Shell command execution capability in .github/workflows/pr-management.yml
  • fs module — File system access in .github/workflows/security.yml
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This is an MCP server that allows AI agents to control the Inkscape vector graphics editor via its command-line interface. It features a structured API and a companion web application, built using the FastMCP framework.

Security Assessment
The tool executes shell commands, which is its primary function—to drive the Inkscape CLI on the host machine. While the automated rule scan flagged shell execution and file system access in GitHub workflow files (`.github/workflows`), these are strictly used for CI/CD automation and do not pose a risk to the end-user. The application itself does not request dangerous overarching permissions, and no hardcoded secrets were identified. Because it is designed to execute local system commands and manage files, it inherently handles sensitive operations. Overall risk: Medium.

Quality Assessment
The project appears to be highly maintained and professionally structured. It was updated very recently, utilizes modern Python practices (requiring Python 3.12+), and employs a robust industrial-quality automation stack (Ruff, Biome, bandit, and safety checks). The CI/CD pipeline is comprehensive. Although the automated scan failed to locate the license file, the README explicitly states it is licensed under the MIT license (a standard permissive open-source license). It has moderate community traction with 10 GitHub stars.

Verdict
Use with caution—while the tool is professionally built and transparent, its core requirement of executing local shell commands via an AI agent demands a controlled execution environment.
SUMMARY

FastMCP 3.1 MCP server for controlling Inkscape svg editor. Includes Webapp

README.md

Inkscape MCP

FastMCP Version Ruff Linted with Biome Built with Just

MCP server for Inkscape: agents call portmanteau tools (inkscape_file, inkscape_vector, inkscape_analysis, inkscape_system) that drive the Inkscape CLI. Built with FastMCP 3.2.0+.

You need Python 3.12+, uv, and Inkscape on the same machine.

Doc What
docs/INSTALL.md Clone uv sync run; PyPI / uvx
docs/INKSCAPE.md Install Inkscape, PATH, CLI check
docs/IDE_MCP.md Cursor, VS Code, Windsurf, Glama-style config
docs/MCPB.md Claude Desktop .mcpb bundle
docs/USAGE.md How to use the tools from an agent
docs/AI_SAMPLING.md Agentic tools, ctx.sample(), Ollama env
docs/ARCHITECTURE.md Layout, transports, modules
llms.txt / llms-full.txt LLM index + full tool/env/run manifest (fleet)

More: Docs index API Features Troubleshooting Changelog

CI/CD
PyPI
Python 3.12+
License: MIT

🛡️ Industrial Quality Stack

This project adheres to SOTA 14.1 industrial standards for high-fidelity agentic orchestration:

  • Python (Core): Ruff for linting and formatting. Zero-tolerance for print statements in core handlers (T201).
  • Webapp (UI): Biome for sub-millisecond linting. Strict noConsoleLog enforcement.
  • Protocol Compliance: Hardened stdout/stderr isolation to ensure crash-resistant JSON-RPC communication.
  • Automation: Justfile recipes for all fleet operations (just lint, just fix, just dev).
  • Security: Automated audits via bandit and safety.

License

MIT see LICENSE.

Yorumlar (0)

Sonuc bulunamadi