
log-ai-compressor
io.github.hu-chenyuPublished by GitHub account hu-chenyuv2.13.1Updated Oct 29, 2026
Local log forensics: compress logs into citable evidence with root-cause confidence tiers.
Overview
Local MCP server that compresses log files into citable evidence with root-cause confidence tiers for forensic analysis.
- What you can do
- Compress log data into condensed, citable evidence rather than raw dumps.
- Attach confidence tiers to suspected root causes so findings can be weighed.
- Support local log forensics work driven by an assistant.
- No individual tools are documented in the supplied listing, so exact operations are unclear.
- When to use it
- Useful when an assistant needs to triage large or noisy log files on the local machine and produce compact, evidence-backed root-cause findings instead of pasting raw logs into context.
- Requirements
- Runs as a local process over stdio, installed from the PyPI package log-ai-compressor and launched with uvx, so a Python/uv toolchain is needed. No authentication, environment variables or headers are declared.
Installation
In SourceWeft
- Open log-ai-compressor 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
This repository has no README.
Tools
0Version history
12- v2.13.1LatestOct 29, 2026
- v2.12.9Oct 24, 2026
- v2.12.8Oct 23, 2026
- v2.12.7Oct 23, 2026
- v2.12.6Oct 23, 2026
- v2.12.5Oct 20, 2026
- v2.12.3Oct 19, 2026
- v2.12.1Oct 19, 2026
- v2.12.0Oct 19, 2026
- v2.11.4Oct 18, 2026
- v2.11.3Oct 18, 2026
- v2.11.2Oct 18, 2026
Score
25% 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
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
- License10 pts
Declare a license in the repository or the registry entry.