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/codag-megalith/codag-visualizer/codaggit clone --depth 1 https://github.com/codag-megalith/codag-visualizerGrade A, and why
codag 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.
Copies of this mod
4 near-identical copies found in the catalogue:
- provenance-mcp — 88% identical, 5 lines differ
- brain — 86% identical, 5 lines differ
- 0 — 86% identical, 6 lines differ
- loopsy — 81% identical, 8 lines differ
What it actually says
{
"codag": {
"command": "node",
"args": [
"packages/mcp-server/dist/index.js",
"."
]
}
}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 · 9 lines scan A ae6c846f6087
codag is an MCP server published in the GitHub repository codag-megalith/codag-visualizer (669 stars, last pushed 6mo 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
visualtorch
Architecture visualization of Torch models. Runs locally from the visualtorch Python package.
playwright
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
blast-radius-mcp
MCP server "blast-radius-mcp" as configured in tspscale/blast-radius-mcp. Runs locally from the blast-radius-mcp npm package.
context7
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.
microsoft-learn
MCP server "microsoft-learn", hosted remotely at learn.microsoft.com, as configured in tae0y/python-project-template.
saas-tf-mcp-server
MCP server for saas.tf - Get 2 FREE subdomains forever with automatic DNS provisioning. Runs locally from the @benjp009/saas-tf-mcp-server npm package.