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 skills add 123pc/Geogebra_mcp --skill geogebra-setupgit clone --depth 1 https://github.com/123pc/Geogebra_mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/123pc/geogebra_mcp/geogebra-setup)<a href="https://agentmods.dev/skills/123pc/geogebra_mcp/geogebra-setup"><img src="https://agentmods.dev/badge/skills/123pc/geogebra_mcp/geogebra-setup.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00072 | $0.00994 |
| Opus 5 | $0.00036 | $0.00497 |
| Sonnet 5 | $0.00014 | $0.00199 |
| Haiku 4.5 | $0.00007 | $0.00099 |
Grade B, and why
geogebra-setup scanned grade B with 1 finding 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 6d ago.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Adds `geogebra` to Claude Code `~/.claude/settings.json` allowlist. How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GeoGebra Setup
Set up GeoGebra MCP from a freshly cloned repository so the user does not need to hand-edit MCP JSON/TOML files.
Workflow
-
Confirm you are in the GeoGebra MCP repository root. It should contain
pyproject.toml,package.json,geogebra_mcp/, andscripts/setup_geogebra_mcp.py. -
Ask the user which AI agent(s) to configure. Present the options in natural language:
- Claude Code
- Codex
- Both (default)
For example: "Which AI agent would you like me to set up GeoGebra MCP for? Claude Code, Codex, or both?" Wait for the user's response before proceeding.
-
Run the setup script with the appropriate
--agentflag based on the user's choice:- Claude Code only:
python scripts/setup_geogebra_mcp.py --agent claude - Codex only:
python scripts/setup_geogebra_mcp.py --agent codex - Both:
python scripts/setup_geogebra_mcp.py --agent all
- Claude Code only:
-
If dependencies are already installed, pass
--skip-deps. -
If the environment blocks network or package installation, request approval and rerun the same script.
-
Treat
geogebra-mcp-doctorreturning non-zero as acceptable when the only failing check iscdp_port; GeoGebra may be closed until the first MCP tool call. -
Tell the user to restart their agent session after setup writes global config.
-
Verify in a new session by asking the agent to check GeoGebra status and draw a small construction.
What The Script Does
The setup script:
- Runs
npm install(installs Puppeteer + Chromium for Web Runtime). - Runs
python -m pip install -e .. - The default runtime is Web Runtime, which launches Chromium and loads GeoGebra Web — no Classic 6 install needed.
- Writes Claude Code MCP config to
~/.claude/.mcp.json. - Adds
geogebrato Claude Code~/.claude/settings.jsonallowlist. - Writes a managed Codex MCP block to
~/.codex/config.toml. - Copies bundled skills into common skill roots:
~/.codex/skills~/.agents/skills~/.claude/skills
- Runs
python -m geogebra_mcp.doctor.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 105 lines · 72 tokens per session scan B 679434d383f4
geogebra-setup is a skill published in the GitHub repository 123pc/Geogebra_mcp (4 stars, last pushed 3mo ago), licensed MIT. It adds 72 tokens to every session and 994 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
math-help
Guide to the math cognitive stack - what tools exist and when to use each.
math
Unified math capabilities - computation, solving, and explanation. I route to the right tool.
groups
Problem-solving strategies for groups in abstract algebra.
rings
Problem-solving strategies for rings in abstract algebra.
analytic-functions
Problem-solving strategies for analytic functions in complex analysis.
contour-integrals
Problem-solving strategies for contour integrals in complex analysis.