Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/code-and-crypto/inkscape-mcp-server/agents-mdgit clone --depth 1 https://github.com/code-and-crypto/inkscape-mcp-serverWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01192 | $0.01192 |
| Opus 5 | $0.00596 | $0.00596 |
| Sonnet 5 | $0.00238 | $0.00238 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade A, and why
inkscape-mcp-server AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for coding agents and contributors working in this repository. Read this before changing anything.
What this is
inkscape-mcp-server is a dependency-free MCP server for Inkscape 1.2+. Standard
library only — no pip install, no FastMCP, no pydantic. 23 tools, ~5,600 lines of
Python, speaking MCP over stdio.
- Entry point:
server.py— bootstrap only; everything lives ininkscape_mcp/ - Run it:
python server.py(stdio) ·python server.py --check(self-test) - Health check:
server_info operation="selftest"before debugging anything
The one rule that matters
Verify against the running Inkscape binary. Never trust the action registry, the documentation, or the source.
This project exists because the other Inkscape MCP servers call actions that do not
exist, and Inkscape exits 0 anyway — so they report success while doing nothing.
Every capability here was confirmed by running it and inspecting the output file.
data/inkscape_actions.json is extracted from the Inkscape source and lists 348
actions. It is an index, not a contract: fit-canvas-to-drawing is in it, is marked
app-scoped, and is absent from the shipped 1.4.2 binary entirely. See
docs/inkscape-findings.md for every verified trap.
When you add a capability:
- Run the action chain by hand against a real file first.
- Check the output file, not the exit code.
- If it silently does nothing, do it in an engine instead and say so in the docstring.
- Add a check to
server_info operation="selftest"if it is core.
Architecture in one paragraph
Layered so each layer can be replaced without disturbing the others: protocol.py
(MCP framing, knows nothing about Inkscape) → toolkit.py (the @tool registry, knows
nothing about what tools do) → tools/ (thin adapters, grouped by domain) →
runner.py (the only place Inkscape is invoked, behind a swappable Backend) and
engines/ (pure Python that does the work, importable and testable alone). Full
picture in docs/architecture.md.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 99 lines · 1,192 tokens per session scan A ea869a96e4d4
inkscape-mcp-server AGENTS.md is an instructions file published in the GitHub repository code-and-crypto/inkscape-mcp-server (0 stars, last pushed 3d ago), licensed MIT. It adds 1,192 tokens to every session, about $0.0060 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.