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.
git clone --depth 1 https://github.com/nexu-io/codex-slidesInstalling this writes the configuration, not the program: `node` runs a file from the repository, so clone it first and make the path in the command match where you put it.
Wrote 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/mcp/nexu-io/codex-slides/codex_slides)<a href="https://agentmods.dev/mcp/nexu-io/codex-slides/codex_slides"><img src="https://agentmods.dev/badge/mcp/nexu-io/codex-slides/codex_slides/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/nexu-io/codex-slides/codex_slides"><img src="https://agentmods.dev/badge/mcp/nexu-io/codex-slides/codex_slides.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
codex_slides 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 1mo 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.
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.
What it actually says
{
"codex_slides": {
"title": "Codex Slides",
"description": "Run a Browser-first guided deck workflow with durable projects, checkpoints, Design Files, brand systems, editing, presenting, and export from Codex.",
"command": "node",
"args": [
"./scripts/start-mcp.mjs"
],
"cwd": "."
}
}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.
- 1mo ago First seen · 11 lines scan A 1e7a22f3c061
codex_slides is an MCP server published in the GitHub repository nexu-io/codex-slides (939 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 2026-08-30.
Other mcp servers, from other repositories
workspace_visual_canvas
MCP server "workspacevisualcanvas" as configured in papperrollinggery/codex-workspace-enhancer. Runs ./dist/server.mjs with node.
icon_svg_select
MCP server "iconsvgselect" as configured in tetracoralla/armorial. Runs ./dist/adapters/mcp.js with node.
mindraw_mcp
MCP server "mindrawmcp" as configured in 17lang/mindraw4agent. Launched with bash ./scripts/start-mcp.sh.
vectorworks
MCP server "vectorworks" as configured in BhaveshY/vectorworks-mcp-codex-plugin. Launched with powershell.exe -NoLogo -NoProfile -ExecutionPolicy Bypass -File .\scripts\run-ve. Needs 6 environment variables to run.
figma-compaction-mcp
MCP bridge that prunes Figma design context into compact plain-text context for agents. Runs locally from the figma-compaction-mcp npm package.
jsoncanvas
Create, validate, edit, export (markdown/svg/png/mermaid), and search JSON Canvas files. Remote server at jsoncanvas.mcpcentral.io.