
Flameox
io.github.morlutoPublished by GitHub account morlutov0.2.9Updated Oct 24, 2026
Bounded local runtime evidence from explicit artifacts and typed direct targets.
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.
Installation
In SourceWeft
- Open Flameox in the dashboard and add it to a workspace.
- 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:
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:
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:
To launch the stdio MCP server manually:
For local development, clone the repository, install its development dependencies, and inspect the available tools:
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
- Architecture describes process and package boundaries.
- Storage and evidence defines preservation and provenance.
- Investigations covers experiments, comparison, and evidence quality.
- Adapters documents provider compatibility and integration policy.
- Runtime safety covers limits, recovery, integrity, and privacy.
- Interfaces defines CLI and MCP contracts.
- Testing describes test selections and known proof gaps.
Development
Flameox requires Python 3.12 or newer and uses the committed uv.lock. See
CONTRIBUTING.md for development setup and contribution guidance.
Flameox is licensed under the MIT License.
Source: README.md at commit 2cc7de4
Tools
0Version history
3- v0.2.9LatestOct 11, 2026
- v0.2.8Oct 9, 2026
- 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