A locally running knowledge base about failure modes, meaning common ways AI systems can fail or behave incorrectly. It is available to MCP-compatible AI tools.

Consulting a catalog of AI system failure modes.

It gives an agent a place to look up AI failure patterns when reviewing or designing a system. The description does not specify the taxonomy's categories or search features.

failmodes — MCP server for Claude Code and Codex by elyngved: A locally running knowledge base about failure modes, meaning…

Install

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.

agentmods

npx agentmods add mcp/elyngved/failmodes-mcp/failmodes

Clone the repo

git clone --depth 1 https://github.com/elyngved/failmodes-mcp

Made for: Claude Code, Codex, Cursor.

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.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/elyngved/failmodes-mcp/failmodes.svg)](https://agentmods.dev/mcp/elyngved/failmodes-mcp/failmodes)

Your own site

<a href="https://agentmods.dev/mcp/elyngved/failmodes-mcp/failmodes"><img src="https://agentmods.dev/badge/mcp/elyngved/failmodes-mcp/failmodes.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

failmodes 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 3d 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.

server.json · 10 lines

What it actually says

{
  "failmodes": {
    "command": "npx",
    "args": [
      "-y",
      "failmodes-mcp"
    ],
    "env": {}
  }
}

Changes

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.

3d ago First seen · 10 lines scan A ff8d17e37c54

Subscribe to this mod's changes

failmodes is an MCP server published in the GitHub repository elyngved/failmodes-mcp (0 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 2026-08-31.

Building agents

docs-langchain

MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/langchain.

langchain-ai/langchain · not measured

reference-langchain

MCP server "reference-langchain", hosted remotely at reference.langchain.com, as configured in langchain-ai/langchain.

langchain-ai/langchain · not measured

playwright-test

A high-level API to automate web browsers. Runs locally from the playwright npm package.

microsoft/playwright · not measured

supabase

Supabase's hosted MCP server: lets the agent manage projects, tables, SQL and migrations. Remote server at mcp.supabase.com.

supabase/supabase · not measured

mcp-search

MCP server "mcp-search" as configured in thedotmack/claude-mem. Runs const f=require('fs'),p=require('path'),o=require('os'),c=require('child_process');const h=o.homedir();const C=process.env.CLAUDE_CONFIG_DIR||p.join(h,'.claude');const E=process.env.CLAUDE_PLUGIN_ROOT||process.env.PLUGIN_ROOT||'';const…

thedotmack/claude-mem · not measured

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.

nextlevelbuilder/ui-ux-pro-max-skill · not measured