Live survey304 models · 14 providers · 23,592 auditsAudited implement · SAFE →What changedHow we verifyllms.txt

MCP server · Audited from source

kanzo MCP server

by emanuele-em/kanzoAGPL-3.0 licenceAudited 12 Nov 2026 · source 7a14e3cc1671

stdiostreamable-http★ 1,169
✕BLOCKGrade D · 61/100 · 12 Nov 2026 · 7a14e3c

Is it safe? No — BLOCK, grade D (61/100). The tool list is built at runtime, so we cannot read it from the source. The audit recorded 17 findings (0 critical, 3 high, 8 medium, 4 low). Maintainer's description: Self-hosted, sharable kanban for humans and agents. One 4.7 MB binary, 5 MB of RAM, 10 to 60 tokens per agent reply, starts in 3 ms, zero setup.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “kanzo MCP server (emanuele-em/kanzo)”. Retrieved 12 Nov 2026. https://modelsatlas.com/mcp/emanuele-em/kanzo

Why this is BLOCK. The audit found 0 critical and 3 high findings; the most severe is Code injection at src/stdio.rs:127. Each finding is listed below with its file and line.

Why this page is still public. People search for this server by name. Hiding it would leave them with the README's word alone; here they see what the code does. We list it so you can decide, and we do not show connect commands for BLOCK servers.

Trust audit

Audit 0.4.1 · full source read 12 Nov 2026

Trust score61/100✕BLOCK D
0 critical3 high8 medium4 low2 info

17 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

  • FilesystemDeclared2 observations
  • NetworkDeclared5 observations
  • ShellDeclared2 observations
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Findings (17)

Sorted by severity

HIGHCode injectioncode.eval_exec · src/stdio.rs:127
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
let e = update::exec(new, Some((HANDOVER, OsStr::from_bytes(&handover))));
Why
evaluates text as code
Fix
remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · src/update.rs:221
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
pub fn exec(exe: &Path, env: Option<(&str, &std::ffi::OsStr)>) -> std::io::Error {
Why
evaluates text as code
Fix
remove; use a parser or a dispatch table
HIGHPrivilege escalation / persistencepriv.escalate · src/service.rs:174
F-06 Privilege escalation / persistenceCWE-269 · CWE-250Layer L1
To start it at boot without logging in (a board with no screen): sudo loginctl enable-linger $USER",
Why
asks for elevated privileges
Fix
—
MEDIUMPrivilege escalation / persistencefs.persistence · src/service.rs:39
F-06 Privilege escalation / persistenceCWE-269 · CWE-250Layer L1
run("launchctl", &["kickstart", "-k", &format!("{}/{LABEL}", launchd_domain()?)])?;
Why
No further detail recorded for this rule.
Fix
—
MEDIUMPrivilege escalation / persistencefs.persistence · src/service.rs:111
F-06 Privilege escalation / persistenceCWE-269 · CWE-250Layer L1
let _ = Command::new("launchctl").args(["bootout", &format!("{domain}/{LABEL}")]).output();
Why
No further detail recorded for this rule.
Fix
—
MEDIUMPrivilege escalation / persistencefs.persistence · src/service.rs:113
F-06 Privilege escalation / persistenceCWE-269 · CWE-250Layer L1
run("launchctl", &["bootstrap", &domain, &path.to_string_lossy()])?;
Why
No further detail recorded for this rule.
Fix
—
MEDIUMPrivilege escalation / persistencefs.persistence · src/service.rs:124
F-06 Privilege escalation / persistenceCWE-269 · CWE-250Layer L1
let _ = Command::new("launchctl").args(["bootout", &format!("{}/{LABEL}", launchd_domain()?)]).output();
Why
No further detail recorded for this rule.
Fix
—
MEDIUMPrivilege escalation / persistencefs.persistence · src/service.rs:197
F-06 Privilege escalation / persistenceCWE-269 · CWE-250Layer L1
let line = format!("schtasks /end /tn {TASK} & ping -n 4 127.0.0.1 >nul & schtasks /run /tn {TASK}");
Why
No further detail recorded for this rule.
Fix
—
MEDIUMFilesystem / pathfs.system_paths · src/service.rs:301
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
let text = plist(Path::new("/usr/local/bin/kanzo"), Path::new("/Users/a & b/kanzo"), Path::new("/tmp/k.log"));
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.raw_ip · src/share.rs:436
F-04 Network egressCWE-200 · CWE-319Layer L1
assert_eq!(address(" http://192.168.0.12:4300/ ").unwrap(), "192.168.0.12:4300");
Why
No further detail recorded for this rule.
Fix
—
MEDIUMPrompt injectionscope.undeclared_system · <declared scope>
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
system use found in code, not declared in the description
Why
the description does not admit a capability the code has
Fix
declare system use in the description, or remove it
LOWFilesystem / pathfs.traversal · src/store.rs:1837
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
assert!(s.add_image(t.id, "../../etc/passwd").is_err());
Why
No further detail recorded for this rule.
Fix
—
LOWSupply chainprompt.pipe_to_shell · README.md:37
F-08 Supply chainCWE-829 · CWE-1357Layer L2
curl -LsSf https://github.com/emanuele-em/kanzo/releases/latest/download/kanzo-installer.sh | sh
Why
No further detail recorded for this rule.
Fix
—
LOWSupply chainprompt.pipe_to_shell · README.zh.md:37
F-08 Supply chainCWE-829 · CWE-1357Layer L2
curl -LsSf https://github.com/emanuele-em/kanzo/releases/latest/download/kanzo-installer.sh | sh
Why
No further detail recorded for this rule.
Fix
—
LOWInventory / provenancemcp.no_tools_extracted · server.json
F-13 Inventory / provenanceCWE-1104Layer L3
Why
the tool list is enumerated at runtime by tools/list, not declared in source
Fix
the page says so rather than showing an empty table
INFOInventory / provenanceinv.oversize · docs/img/board-dark.gif
F-13 Inventory / provenanceCWE-1104Layer L0
docs/img/board-dark.gif
Why
2197883 bytes not read
Fix
—
INFOInventory / provenanceinv.oversize · docs/img/board-light.gif
F-13 Inventory / provenanceCWE-1104Layer L0
docs/img/board-light.gif
Why
2528548 bytes not read
Fix
—

Tools it exposes

None declared in source

The tool list is built at runtime, so we cannot read it from the source.

Audit history

  1. ✕BLOCK D 61 / 100

    First audit · 7a14e3cc1671

README badge

Badges show the current verdict, BLOCK included

ModelsAtlas: BLOCK DMODELSATLASBLOCK · D

A badge cannot be hidden by the maintainer while the verdict is BLOCK. Fix the findings, push, and the re-audit updates it.

Questions about kanzo MCP server

What is the kanzo MCP server?
Self-hosted, sharable kanban for humans and agents. One 4.7 MB binary, 5 MB of RAM, 10 to 60 tokens per agent reply, starts in 3 ms, zero setup.
Is kanzo safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (61/100) and found 3 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does kanzo need?
It reads ANTHROPIC_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does kanzo run?
It speaks stdio and streamable-http, so it runs as a local process your client starts.
How current is this page?
The grade is for one exact copy of the source (7a14e3cc1671), read on 2026-11-12. The repository is watched and re-audited when it changes.
I already installed kanzo. What should I do?
Remove it from your client's MCP configuration, then rotate any API keys and tokens that were in your environment while it ran.
Can the verdict change?
Yes. The repository is watched and re-audited when its source changes. If the findings are removed the verdict updates, and the history on this page shows it.

Sources

  • emanuele-em/kanzo on GitHub — the source we read, its licence, stars and activityObserved · 12 Nov 2026
  • ModelsAtlas trust audit — BLOCK verdict for commit 7a14e3cc1671Observed · 12 Nov 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.