Atlas / MCP servers / cqfn / Aibolit

AibolitSAFE

mcp/cqfn/aibolit

MCP Server for Aibolit Java Static Analyzer: Helping Your AI Agent Identify Hotspots for Refactoring

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
1 1r · 0w · 0d
Transport
stdio
License
MIT
Stars
27
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://www.rultor.com/p/cqfn/aibolit-mcp-server)

[](https://github.com/cqfn/aibolit-mcp-server/actions/workflows/make.yml) [](https://codecov.io/gh/cqfn/aibolit-mcp-server) [](https://hitsofcode.com/view/github/cqfn/aibolit-mcp-server) [](https://github.com/cqfn/aibolit-mcp-server/blob/master/LICENSE.txt)

If you use AI agents, such as [Claude Code], [Cursor], or [Windsurf], for code refactoring, you may enjoy using this [MCP] server. Your AI agent, when you ask it to "make code better," may wonder what exactly needs to be improved. Sadly, it may often overlook important problems. AI agents, by design, pay more attention to cosmetic issues, which are "low-hanging fruits" for them. This [MCP] server will give your agent a hint: what is the most critical design issue in the code. Then, the agent will refactor it and fix the issue.

First, install [Node], [Npm], [Python], [Pip], and [aibolit]:

aibolit --version

Then, add this [MCP] server to [Claude Code] (or simply edit ~/claude.json, but it's not recommended):

claude mcp add aibolit npx [email protected]

Then, restart [Claude Code] and ask it something along these lines: "Find the most critical design issue in my code base and fix it."

How to Contribute

To test this project, simply run the following commands (you'll need [Node] 18+, [Npm], and [GNU make] installed):

npm install
make

If everything builds correctly after your changes, submit a pull request.

[MCP]: https://modelcontextprotocol.io/ [Npm]: https://www.npmjs.com/

Read from source at commit 838220e491b0OBSERVED · 2026-10-08
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add aibolit-mcp-server -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "aibolit-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
03

Exposed tools (1)

1 read · 0 write · 0 destructive.

ToolRiskDescription
find_the_most_critical_design_issueread
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
declared (2 observation(s))
Dependencies
not all pinned
Secrets in source
none-found

Findings (7)

LOWInventory / provenance · inv.hidden_file · CWE-1104
.0pdd.yml
.0pdd.yml
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
.pdd
.pdd
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
.rultor.yml
.rultor.yml
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
.xcop
.xcop
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
test/helpers/once.ts:8
import { server } from '../../src/server';
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
test/helpers/once.ts:9
import '../../src/tools';
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, commander, semver, @jest/globals, @types/jest, @types/semver, @typescript-eslint/eslint-plugin, @typescript-eslint/parser
Why it matters. 15 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 838220e491b0full audit observations/trust-audit/mcp-server/cqfn__aibolit.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-08838220e491b0SAFEB89first audit
06

Questions

What is the Aibolit MCP server?

MCP Server for Aibolit Java Static Analyzer: Helping Your AI Agent Identify Hotspots for Refactoring

What tools does Aibolit expose?

1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Aibolit safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Aibolit need?

No credential environment variables were found in its source, so it appears to need none.

How does Aibolit run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as aibolit-mcp-server at 0.0.0.

How current is this page?

The grade is for one exact copy of the source (838220e491b0), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement