MCP server · Audited from source

Interactive Feedback MCP server

by minidoracat/mcp-feedback-enhancedNOASSERTION licenceAudited 21 Sep 2026 · source e990a29086d8

PyPI mcp-feedback-enhanced-desktop★ 3,765

✓SAFEGrade B · 84/100 · 21 Sep 2026 · e990a29

3,765GitHub stars

Is it safe? Yes — SAFE, grade B (84/100). It exposes 1 tool: 1 read, 0 write and 0 destructive. The audit recorded 25 findings (0 critical, 0 high, 1 medium, 20 low). Maintainer's description: Enhanced MCP server for interactive user feedback and command execution in AI-assisted development, featuring dual interface support (Web UI and Desktop Application) with intelligent environment detection and cross-platform compatibility.

Ask an AI about this pageGChatGPT CClaude PPerplexity GeGemini XGrok

CoCopilot AIGoogle AI Mode

Cite

Cite this page

ModelsAtlas. “Interactive Feedback MCP server (minidoracat/mcp-feedback-enhanced)”. Retrieved 21 Sep 2026. https://modelsatlas.com/mcp/minidoracat/interactive-feedback-4

Trust audit

Audit 0.4.1 · full source read 21 Sep 2026

Trust score84/100✓SAFE B

0 critical0 high1 medium20 low4 info

25 findings, listed below with the file and line each was found on. Grade A needs a sandboxed behavioural run too; this audit read the source only.

What the source does

FilesystemDeclared5 observations
NetworkDeclared5 observations
ShellDeclared1 observation
DependenciesPinnedNothing floats
SecretsNone foundNo keys in source

“Declared” means the server says it does this and the source agrees. Browser, file and shell access are expected of some kinds of server.

Five audit layers

Layer	What we check	Result
`L0` Provenance	Repo owner, licence, archive status, activity	WARN 7 findings
`L1` Static source	Secrets, path traversal, supply chain	PASS 15 findings
`L2` Instructions	Prompt injection and authority framing in docs and tool descriptions	PASS 3 findings
`L3` Inventory	Declared tools match the source	PASS
`L4` Sandbox	Run in isolation and watch behaviour	SKIPPED

Provenance & runtime

Who published it, and what the audit could and could not run

Provenance

Repository owner minidoracatUser accountAccount type recorded when we read the repository.
PackagePublished on PyPImcp-feedback-enhanced-desktop, no version recorded
LicenceNOASSERTIONFrom the repository, as read at the audited commit.
Last push14 days agoActivity of the repository when we read it.
Source commit reade990a29086d8The audit covers exactly this commit, read on 21 Sep 2026.

Runtime

Sandbox runNot run yetThis audit read the source only; it did not execute the server.
Tool inventory1 declaredRead from the source and classed read, write or destructive.

Every value here is read from the record's own repository and audit.Suggest a correction

Findings (25)

Sorted by severity

MEDIUMInventory / provenanceinv.binary · src-tauri/icons/icon.icns

F-13 Inventory / provenanceCWE-1104Layer L0

icon.icns

Why: a compiled or binary member cannot be reviewed from source
Fix: ship source, or explain the binary in the README

LOWInventory / provenanceinv.hidden_file · .bumpversion.cfg

F-13 Inventory / provenanceCWE-1104Layer L0

.bumpversion.cfg

Why: hidden member outside the usual dotfiles
Fix: review its purpose

LOWInventory / provenanceinv.hidden_file · .pre-commit-config.yaml

F-13 Inventory / provenanceCWE-1104Layer L0

.pre-commit-config.yaml

Why: hidden member outside the usual dotfiles
Fix: review its purpose

LOWNetwork egressnet.raw_ip · docs/architecture/component-details.md:438

F-04 Network egressCWE-200 · CWE-319Layer L1

allow_origins=["http://127.0.0.1:*", "http://localhost:*"],

Why: No further detail recorded for this rule.
Fix: —

LOWNetwork egressnet.raw_ip · src/mcp_feedback_enhanced/web/static/index.html:91

F-04 Network egressCWE-200 · CWE-319Layer L1

const backendUrl = 'http://127.0.0.1:8765';

Why: No further detail recorded for this rule.
Fix: —

LOWNetwork egressnet.raw_ip · tests/unit/test_desktop_fallback.py:186

F-04 Network egressCWE-200 · CWE-319Layer L1

await app.launch_tauri_app("http://127.0.0.1:8765")

Why: No further detail recorded for this rule.
Fix: —

LOWNetwork egressnet.raw_ip · tests/unit/test_desktop_fallback.py:215

F-04 Network egressCWE-200 · CWE-319Layer L1

await app.launch_tauri_app("http://127.0.0.1:8765")

Why: No further detail recorded for this rule.
Fix: —

LOWNetwork egressnet.raw_ip · tests/unit/test_desktop_fallback.py:233

F-04 Network egressCWE-200 · CWE-319Layer L1

await app.launch_tauri_app("http://127.0.0.1:8765")

Why: No further detail recorded for this rule.
Fix: —

LOWObfuscation / stealthobf.base64_blob · src/mcp_feedback_enhanced/web/templates/feedback.html:10

F-07 Obfuscation / stealthCWE-506 · CWE-94Layer L1

<link rel="icon" type="image/x-icon" href="data:image/x-icon;base64,AAABAAEAEBAAAAEAIABoBAAAFgAAACgAAAAQAAAAIAAAAAEAIAAAAAAAAAQAABILAAASCwAAAAAAAAAAAAD///8A////AP///wD///8A////AP///wD///8A////AP///wD/

Why: No further detail recorded for this rule.
Fix: —

LOWObfuscation / stealthobf.decode_call · src/mcp_feedback_enhanced/server.py:394

F-07 Obfuscation / stealthCWE-506 · CWE-94Layer L1

image_bytes = base64.b64decode(img["data"], validate=True)

Why: No further detail recorded for this rule.
Fix: —

LOWObfuscation / stealthobf.decode_call · src/mcp_feedback_enhanced/web/models/feedback_session.py:644

F-07 Obfuscation / stealthCWE-506 · CWE-94Layer L1

image_bytes = base64.b64decode(img["data"])

Why: No further detail recorded for this rule.
Fix: —

LOWObfuscation / stealthobf.decode_call · tests/unit/test_image_content.py:23

F-07 Obfuscation / stealthCWE-506 · CWE-94Layer L1

PNG_BYTES = base64.b64decode(

Why: No further detail recorded for this rule.
Fix: —

LOWObfuscation / stealthobf.decode_call · tests/unit/test_image_content.py:62

F-07 Obfuscation / stealthCWE-506 · CWE-94Layer L1

assert base64.b64decode(result[0].data) == PNG_BYTES

Why: No further detail recorded for this rule.
Fix: —

LOWObfuscation / stealthobf.decode_call · tests/unit/test_image_content.py:68

F-07 Obfuscation / stealthCWE-506 · CWE-94Layer L1

assert base64.b64decode(result[0].data) == PNG_BYTES

Why: No further detail recorded for this rule.
Fix: —

LOWPrivilege escalation / persistencepriv.escalate · .github/workflows/build-desktop.yml:135

F-06 Privilege escalation / persistenceCWE-269 · CWE-250Layer L1

sudo apt-get update

Why: asks for elevated privileges
Fix: —

LOWPrivilege escalation / persistencepriv.escalate · .github/workflows/build-desktop.yml:137

F-06 Privilege escalation / persistenceCWE-269 · CWE-250Layer L1

sudo apt-get install -y \

Why: asks for elevated privileges
Fix: —

LOWPrivilege escalation / persistencepriv.escalate · .github/workflows/build-desktop.yml:144

F-06 Privilege escalation / persistenceCWE-269 · CWE-250Layer L1

if ! sudo apt-get install -y libayatana-appindicator3-dev; then

Why: asks for elevated privileges
Fix: —

LOWPrivilege escalation / persistencepriv.escalate · .github/workflows/build-desktop.yml:146

F-06 Privilege escalation / persistenceCWE-269 · CWE-250Layer L1

sudo apt-get install -y libappindicator3-dev

Why: asks for elevated privileges
Fix: —

LOWSupply chainprompt.pipe_to_shell · docs/DESKTOP_BUILD.md:17

F-08 Supply chainCWE-829 · CWE-1357Layer L2

curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh

Why: No further detail recorded for this rule.
Fix: —

LOWPrompt injectionprompt.transfer_instruction · README.md:212

F-01 Prompt injectionCWE-94 · CWE-1427Layer L2

- `0.0.0.0`: Binds all interfaces. ⚠️ **Not recommended**: the Web UI and `/ws` endpoint have **no authentication**, so anyone who can reach the port can read session content (including project paths

Why: an instruction to move sensitive data to an outside destination
Fix: remove; a skill never needs the user's secrets off the machine

LOWPrompt injectionprompt.transfer_instruction · README.md:311

F-01 Prompt injectionCWE-94 · CWE-1427Layer L2

> the Web UI and `/ws` endpoint have no authentication, so binding publicly lets anyone on the network read your session and submit feedback.

Why: an instruction to move sensitive data to an outside destination
Fix: remove; a skill never needs the user's secrets off the machine

INFOInventory / provenanceinv.oversize · src/mcp_feedback_enhanced/desktop_release/mcp-feedback-enhanced-desktop-linux

F-13 Inventory / provenanceCWE-1104Layer L0

src/mcp_feedback_enhanced/desktop_release/mcp-feedback-enhanced-desktop-linux

Why: 5224304 bytes not read
Fix: —

INFOInventory / provenanceinv.oversize · src/mcp_feedback_enhanced/desktop_release/mcp-feedback-enhanced-desktop-macos-arm64

F-13 Inventory / provenanceCWE-1104Layer L0

src/mcp_feedback_enhanced/desktop_release/mcp-feedback-enhanced-desktop-macos-arm64

Why: 4444240 bytes not read
Fix: —

INFOInventory / provenanceinv.oversize · src/mcp_feedback_enhanced/desktop_release/mcp-feedback-enhanced-desktop-macos-intel

F-13 Inventory / provenanceCWE-1104Layer L0

src/mcp_feedback_enhanced/desktop_release/mcp-feedback-enhanced-desktop-macos-intel

Why: 4811992 bytes not read
Fix: —

INFOInventory / provenanceinv.oversize · src/mcp_feedback_enhanced/desktop_release/mcp-feedback-enhanced-desktop.exe

F-13 Inventory / provenanceCWE-1104Layer L0

src/mcp_feedback_enhanced/desktop_release/mcp-feedback-enhanced-desktop.exe

Why: 4574208 bytes not read
Fix: —

Tools it exposes

1 declared in source · 0 destructive

1 read0 write0 destructive

Tool	Risk	What it does
`get_system_info`	read	No description in the source

Install

audited commit e990a29

Add to Cursor Add to VS Code

One-click links open your editor with the config below filled in, exactly as the snippets show it. The audit covers commit e990a29 only.

claude mcp add mcp-feedback-enhanced-desktop -- uvx mcp-feedback-enhanced-desktop

{
  "mcpServers": {
    "mcp-feedback-enhanced-desktop": {
      "command": "uvx",
      "args": [
        "mcp-feedback-enhanced-desktop"
      ]
    }
  }
}

The command does not pin a version; the audit covers commit e990a29086d8. Transport: not declared. No environment variables required.

Audit history

2026-09-21
✓SAFE B 84 / 100
Source changed, verdict held · e990a29086d8

README badge

For maintainers · updates on every re-audit

[![ModelsAtlas: SAFE B](https://modelsatlas.com/mcp/minidoracat/interactive-feedback-4/badge.svg)](https://modelsatlas.com/mcp/minidoracat/interactive-feedback-4/)

The badge always shows the latest audit; a maintainer cannot pin an old verdict.

Other ratings

Cited, never blended into our score

No third-party security ratings are recorded for this server yet. When they exist they appear here with their source and date, beside, not inside, our grade.

Questions about Interactive Feedback MCP server

What is the Interactive Feedback MCP server?

Enhanced MCP server for interactive user feedback and command execution in AI-assisted development, featuring dual interface support (Web UI and Desktop Application) with intelligent environment detection and cross-platform compatibility.

What tools does Interactive Feedback 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 Interactive Feedback safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (84/100). 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 Interactive Feedback need?

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

How current is this page?

The grade is for one exact copy of the source (e990a29086d8), read on 2026-09-21. The repository is watched and re-audited when it changes.

Sources

minidoracat/mcp-feedback-enhanced on GitHub — the source we read, its licence, stars and activityObserved · 21 Sep 2026
ModelsAtlas trust audit — SAFE verdict for commit e990a29086d8Observed · 21 Sep 2026

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.

What is the Interactive Feedback MCP server?
GChatGPT CClaude PPerplexity
What tools does Interactive Feedback expose?
GChatGPT CClaude PPerplexity
Is Interactive Feedback safe to connect to an agent?
GChatGPT CClaude PPerplexity