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 mcp/phenomenoner/chatgpt-codex-app-plus/context-canvas-codex-context-canvasgit clone --depth 1 https://github.com/phenomenoner/Chatgpt-Codex-App-PlusWrote 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/phenomenoner/chatgpt-codex-app-plus/context-canvas-codex-context-canvas)<a href="https://agentmods.dev/mcp/phenomenoner/chatgpt-codex-app-plus/context-canvas-codex-context-canvas"><img src="https://agentmods.dev/badge/mcp/phenomenoner/chatgpt-codex-app-plus/context-canvas-codex-context-canvas.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
context-canvas 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 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.
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
{
"context-canvas": {
"command": "python",
"args": [
"-B",
"-I",
"./scripts/context_canvas_mcp.py"
],
"cwd": ".",
"startup_timeout_sec": 10,
"tool_timeout_sec": 30
}
}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 · 13 lines scan A 54120ade22b9
context-canvas is an MCP server published in the GitHub repository phenomenoner/Chatgpt-Codex-App-Plus (2 stars, last pushed 11d 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 2026-08-31.
Other mcp servers, from other repositories
workforge
MCP server "workforge" as configured in NotNull92/workforge-mcp. Launched with ./bin/workforge-stdio.cmd -ProfileId workstation.
packet-tracer-mcp
MCP server for Cisco Packet Tracer 9 — live IOS, OSPF, BGP, NAT, VLAN, VoIP, QoS, IPv6, wireless. Runs locally from the packet-tracer-mcp npm package. Needs 1 environment variable to run.
electron-driver
MCP server that lets AI agents drive Electron apps — click, type, drag, screenshot, eval JS in the renderer or main process, capture console logs, handle multi-window apps, and more. Runs locally from the electron-driver npm package.
chatgpt-webui-mcp
Standalone MCP server for ChatGPT Web UI via session token. Runs locally from the chatgpt-webui-mcp npm package.
docs-langchain
MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/langchain.
reference-langchain
MCP server "reference-langchain", hosted remotely at reference.langchain.com, as configured in langchain-ai/langchain.