Model Context Protocol server for Rollbar
Nothing to run from here
Log AI Compressor is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
99/100
trust score
3
downloads a day
local
runs on your machine
929
downloads in 30d
What it does
Local log forensics: compress logs into citable evidence with root-cause confidence tiers.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user log-ai-compressor-mcp '--' uvx --from 'log-ai-compressor[mcp]' log-ai-compressor-mcp
# 2 — ask your agent for something these tools do
# analyze_log_file, analyze_log_text, compare_log_files and 5 more
Log AI Compressor costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
HCAll 1 server
hu-chenyu1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Log AI Compressor as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user log-ai-compressor-mcp '--' uvx --from 'log-ai-compressor[mcp]' log-ai-compressor-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
8 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
分析一个或多个本机日志文件（按 mtime 从旧到新合并，适用于轮转日志），返回：统计概览 + 按优先级排序的错误簇 + 根因判定 + 异常标记。输出已经过聚类去重，token 消耗比读原始日志低几个数量级。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| paths | array | yes | 日志文件绝对路径；多个文件按修改时间从旧到新合并分析 |
| levels | array | no | 只统计这些级别，默认 ["ERROR", "FAIL"] |
| include | array | no | 包含关键词（子串） |
| exclude | array | no | 排除关键词（子串） |
| context_lines | integer | no | 每个错误保留的上下文行数，默认 50 |
| similarity | string | no | 聚类并簇激进度 strict(0.95) / standard(0.85) / lenient(0.70) |
| analysis_mode | string | no | full 完整 / deep 深度扫描（门槛低）/ fast 快速聚类 |
| rule | string | no | 解析规则 auto / generic / embedded / jenkins |
| top_n | integer | no | 返回前 N 个错误簇 |
| encoding | string | no | auto / utf-8 / gb18030 / utf-16 |
| max_lines | integer | no | 只分析前 N 行（超大文件提速） |
直接分析一段日志文本（用户粘贴的内容、命令输出、Agent 读到的片段）。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | 日志文本 |
| source | string | no | 来源标记，会出现在报告标题里 |
| levels | array | no | 只统计这些级别 |
| context_lines | integer | no | 上下文行数 |
| similarity | string | no | 聚类激进度 |
| analysis_mode | string | no | 完整 / 深度 / 快速 |
| rule | string | no | 解析规则 |
| top_n | integer | no | 返回前 N 个错误簇 |
对比 2~5 个日志文件，列出相对基准文件的「新增 / 消失 / 共同」错误，适配版本回归验证与修复前后对比。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| paths | array | yes | 日志文件路径，第一个为基准 |
| levels | array | no | 只统计这些级别 |
| include | array | no | 包含关键词 |
| exclude | array | no | 排除关键词 |
| context_lines | integer | no | 上下文行数 |
| rule | string | no | 解析规则 |
把指定日志文件导出为压缩报告。Markdown 格式专为投喂 LLM 优化（概览 + Top N 清单 + 典型样例详情），通常比原始日志小 50~500 倍。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| paths | array | yes | 日志文件路径 |
| format | string | no | md / json / txt / html / summary / json_full |
| levels | array | no | 只统计这些级别 |
| top_n | integer | no | Top N 错误 |
| context_lines | integer | no | 上下文行数（MCP 场景建议 10~20，控制 token） |
| similarity | string | no | 聚类激进度 |
| analysis_mode | string | no | 完整 / 深度 / 快速 |
| rule | string | no | 解析规则 |
| redact | boolean | no | 是否脱敏（邮箱/手机号/身份证/密钥） |
对某个日志文件取单个错误簇的完整证据：典型样例原始行、前后上下文、降噪堆栈（业务帧高亮、系统库帧已折叠）、变量取值分布、全部实例。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | 日志文件路径 |
| cluster_id | integer | yes | 簇号（先调 analyze_log_file 拿到） |
| levels | array | no | 只统计这些级别 |
| context_lines | integer | no | 上下文行数 |
| similarity | string | no | 聚类激进度 |
| analysis_mode | string | no | 完整 / 深度 / 快速 |
| rule | string | no | 解析规则 |
取证自校验：核对结论的出处是否仍与原始日志一致。传 report_path 复核一份已导出的 JSON 报告（推荐：报告发出后日志可能已被修改或轮转清理）；只传 path 是当场自检。返回 VERIFIED / TAMPERED / UNVERIFIABLE / NO_EVIDENCE。UNVERIFIABLE 不等于 TAMPERED：前者是「源读不到，验不了」，后者是「回读过了，对不上」。把它们混为一谈，等于指控一个没发生的篡改。本工具的立场是「你不必相信我，自己复核」—— 在把结论当成事实转述给用户之前跑这一步。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | no | 日志文件绝对路径 |
| report_path | string | no | 已导出的 JSON 报告路径。传它才是有意义的取证 —— 复核一份之前拿到的报告，确认它现在还对得上原文。 只传 path 是当场分析当场校验（同义反复，必然通过）， 证明不了「三天前那份报告还成不成立」。 |
| levels | array | no | 只统计这些级别 |
| context_lines | integer | no | 上下文行数（影响证据行区间） |
| similarity | string | no | 聚类并簇激进度 |
| analysis_mode | string | no | 完整 / 深度 / 快速 |
| rule | string | no | 解析规则 |
列出内置的日志解析规则模板及其适用场景。日志格式没被正确解析时先看这里。
No parameter schema on file.
确认工具是否可用、内置规则、AI 解读是否已配置。不传参数即可自检。
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Log AI Compressor or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 99 / 100
Release 2.13.1 · scanned 28 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score99
Findings12 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationrepo
Surface digest8d9ae5321a80acf27b175e7f1ff0a6935b10e8937bc4e600d494bdc610bd93ca
Score vectorthreat 100 → client 99
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (8 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| analyze_log_text | no tags | |
| list_rules | no tags | |
| check_environment | no tags | |
| analyze_log_file | no tags | |
| compare_log_files | no tags | |
| export_report | no tags | |
| get_cluster_detail | no tags | |
| verify_evidence | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest8d9ae5321a80acf2
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 2.13.1. Pin a release below and the command asks for exactly that one.
2.13.1
28 Oct 2026
latestNo release note was published with this version.
2.13.0
28 Oct 2026
No release note was published with this version.
2.12.9
24 Oct 2026
No release note was published with this version.
2.12.8
23 Oct 2026
No release note was published with this version.
2.12.7
23 Oct 2026
No release note was published with this version.
2.12.6
23 Oct 2026
No release note was published with this version.
2.12.5
20 Oct 2026
No release note was published with this version.
2.12.3
19 Oct 2026
No release note was published with this version.
2.12.1
19 Oct 2026
No release note was published with this version.
2.12.0
19 Oct 2026
No release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Log AI Compressor can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.