agentmods.dev

flameox

A local tool that provides runtime evidence for tracing and profiling software, GPU code, and machine-learning inference systems.

In plain words
What is it for?
Use it to investigate slow application code, native programs, GPU kernels, or inference workloads.
Why use it?
It helps show where an application is spending time or encountering performance hotspots instead of relying only on code inspection.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

49 2d ago A scan tokens not measured original MIT
View the source file morluto/flameox
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/morluto/flameox/flameox
Clone the repo
git clone --depth 1 https://github.com/morluto/flameox

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

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

flameox 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 2d 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 · 9 lines

What it actually says

{
  "flameox": {
    "command": "uvx",
    "args": [
      "flameox"
    ],
    "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.

  1. 2d ago First seen · 9 lines scan A d42dacad611a

Subscribe to this mod's changes

flameox is an MCP server published in the GitHub repository morluto/flameox (49 stars, last pushed 2d 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.

Debuggingbenchmarkingcoding-agentslocal-firstmcpperformance
Related

Other mcp servers, from other repositories

reporelay

Bounded local MCP access to one approved repository for AI read/search and structured handoffs. Runs locally from the reporelay-mcp npm package.

Lukie-81/RepoRelay · not measured

dreamd

Local-first, cross-harness memory for AI coding agents. Runs locally from the dreamd-mcp npm package.

botzrDev/dreamd · not measured

chimeraforge

LLM deployment optimizer (performance, cost, and safety) — backed by 204,000 real measurements on consumer GPUs. Runs locally from the chimeraforge Python package.

Sahil170595/Chimeraforge · not measured

grape

MCP server "grape" as configured in gael55x/Grape. Launched with grape mcp --stdio.

gael55x/Grape · not measured

mcp-light-memory

MCP server "mcp-light-memory" as configured in PeterPirog/mcp-light-memory. Launched with https://github.com/PeterPirog/mcp-light-memory/releases/download/v1.8.1/mcp-ligh.

PeterPirog/mcp-light-memory · not measured

taskgrade

Local task classification for coding-agent model selection. Runs locally from the taskgrade npm package.

eddyvlad/taskgrade · not measured