Flameox

io.github.morlutoPublished by GitHub account morlutov0.2.9Updated Oct 24, 2026

Bounded local runtime evidence from explicit artifacts and typed direct targets.

VerifiedSTDIODesktop onlyDeveloper ToolsData & Analytics

Overview

AI-generated overview

Local MCP server that runs profilers, benchmarks and trace processors on explicit artifacts or commands and returns bounded, provenance-tagged evidence.

What you can do
  • Analyze explicit artifact paths with named analysis tools and get bounded results inline
  • Capture a typed local target by argv and absolute working directory, with bounded environment overrides
  • Inspect preserved evidence by evidence_id and read redacted metadata and replay sources
  • Continue long results by replaying the returned next_page tool and arguments unchanged
  • Record observed inputs, execution provenance, coverage and limitations alongside results
When to use it
Useful for coding agents that need measured runtime evidence — profiling, benchmarking or trace analysis — from a specific artifact or command, without setting up a workspace or project configuration. It suits investigations where the agent picks hypotheses and experiments and wants provenance and limits recorded.
Requirements
Runs as a local stdio process, typically launched with uvx from the PyPI package (Python 3.12 or newer). No accounts, API keys or headers are declared. Optional preservation writes to a user-level data directory, which can be relocated with FLAMEOX_DATA_DIR. Client setup is done with the package's setup command.
Before you install
Capture executes a local command with the argv and working directory you supply, so only run targets you trust. Preservation writes evidence to a user-level data directory and is optional; session analysis IDs expire when evicted or when the server stops. Profiles guide exploration but do not establish causality or performance improvement.

Installation

In SourceWeft

  1. Open Flameox in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

flameox

[flameox mascot: an ox with a flame graph between its horns]

Bounded local runtime evidence for coding agents.

Flameox coordinates profilers, benchmark tools, trace processors, and direct local targets. It turns an explicit artifact or command into bounded evidence while keeping durable preservation optional. The agent chooses hypotheses and experiments; Flameox records observed inputs, execution provenance, typed evidence, coverage, and limitations.

There is no workspace to initialize or project configuration to maintain. Pass exact artifact paths to analysis and an explicit argv plus absolute working directory to capture. Flameox does not search parent directories, edit project files, or provide a hosted service.

Quick start

Configure an MCP client with the global setup command:

console
npx flameox@latest setup

Setup detects supported clients and asks which configurations to update. For automation, select clients explicitly, for example --client codex --yes or --all --yes; --dry-run reports the paths and actions without writing. Setup preserves unrelated client configuration and does not change project files. See the npm package guide for details.

Update existing MCP registrations with:

console
npx flameox@latest update

update --check reports available updates without changing configuration. Updates preserve each client's provider extras and settings, verify the new environment before changing release pins, and report which clients need a restart or reconnect. Use --client codex to select one client, or --version 0.2.8 to select a specific release, including for rollback. The Python CLI exposes the same flameox update command.

For direct CLI use, pass exact artifact paths or an explicit command:

console
uvx flameox analyze preview_artifact /absolute/path/to/artifact.jsonuvx flameox capture --provider direct --cwd "$PWD" -- python benchmark.py

To launch the stdio MCP server manually:

console
uvx flameox mcp serve

For local development, clone the repository, install its development dependencies, and inspect the available tools:

console
git clone https://github.com/morluto/flameox.gitcd flameoxuv sync --extra dev --extra memory --extra trace --extra cpuuv run flameox mcp inspect

Evidence and storage

Analysis and unpreserved capture use bounded session scratch. Session analysis_id values expire when evicted or when the server stops. Explicit preservation creates the user-level Flameox data directory and stores native bytes and a canonical evidence bundle by SHA-256. Set FLAMEOX_DATA_DIR to choose another location. Preservation is optional; it does not imply full console-output retention.

Flameox distinguishes observed, derived, and inferred claims. Profiles guide exploration but do not establish causality or performance improvement. Confirmatory claims require representative workloads, declared metrics and estimands, compatible identities, preserved samples, and a semantic oracle.

MCP

The MCP server has no workspace binding. It exposes named analysis and capture tools through the same operation registry as the CLI. Analysis tools accept explicit sources; capture tools accept a typed target and provider. Tool schemas expose operation-specific fields directly. Inspect the catalog with flameox mcp inspect; use --tool TOOL_NAME for focused schemas and examples. The complete contract and current tool catalog are in the interface guide.

Tools return their full bounded results inline, including failures and recovery actions. Preserved evidence has a durable evidence_id; inspect_evidence returns its redacted metadata and replay sources inline.

Capture takes argv, not a shell string. A direct target supplies an absolute working directory and bounded environment overrides. Results may include next_page; replay its named analysis tool and arguments unchanged. Capture continuations read collected artifacts and do not rerun the target. MCP work belongs to the live request, so cancellation applies directly and no detached job survives a restart.

Documentation

Development

Flameox requires Python 3.12 or newer and uses the committed uv.lock. See CONTRIBUTING.md for development setup and contribution guidance.

console
uv run ruff check src tests toolsuv run ruff format --check src tests toolsuv run mypy src tests toolsuv run pytest -q

Flameox is licensed under the MIT License.

Source: README.md at commit 2cc7de4

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

3
  1. v0.2.9LatestOct 11, 2026
  2. v0.2.8Oct 9, 2026
  3. v0.2.7Sep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts