Flameox

This is an MCP server, not a DSH bundle. It is wired in through the official @deepseek-ai/dsh-mcp-client bridge: one plugin row in your config, pointing at either a stdio command or an http endpoint. Its tools then appear to the agent as mcp__flameox__<tool>, the same naming Claude Code and Codex use.

{
  "name": "@deepseek-ai/dsh-mcp-client",
  "config": {
    "server": "flameox",
    "command": "<stdio command from the README>",
    "url": "<or an http endpoint, if the server is remote>"
  }
}

Prerequisites

API key

Not required.

Network access

Not required at runtime.

Language

Python

Verdict reason

mcp-server uses its own install path, so bundle checks do not apply

package.json read

npm/package.json

Rules applied from

docs/user/develop/basic/publish.md

Checked at

2026-08-15

src="docs/assets/flameox-mascot-flamegraph.png" width="420" alt="flameox mascot: an ox with a flame graph between its horns" > Flameox connects profilers, benchmark tools, and trace processors to a local evidence record. It preserves their native artifacts and provenance, then exposes bounded evidence to the agent. The agent states what it wants to test; Flameox captures the measurements and preserves the experiment record for review. Install the local runtime and connect a supported MCP client through the guided setup: