klypix-mcp
npm
v1.84.0
Source verified
Published by dahshanlabs — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
Every project gets a brain — one open .klypix file your AI agents read, write, and argue from, over MCP. Works with Claude, Codex, Cursor, Cline, any model.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 9.5 = 91. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −9.5 | Untrusted input concatenated into a command sink ×2 MTC-SRC-009 | injection |
2. Client adoption risk — 91 − 6 = 85. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
In the server's implementation (`bin/klypix-doctor.mjs:18`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: port { execSync } from 'child_process'; import { inspect, render, inspectAll } from '../src/brain-doctor.mjs'; // ARGV:
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/klypix-doctor.mjs
In the server's implementation (`bin/klypix-git-tools.mjs:29`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: port { execFile } from 'child_process'; import { createRequire } from 'module'; import { fileURLToPath } from 'url'; co
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/klypix-git-tools.mjs
In the server's implementation (`bin/klypix-install.mjs:22`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: FileSync, spawn } from 'child_process'; import { fileURLToPath } from 'url'; import { connectCodexMcpServer, dis
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/klypix-install.mjs
In the server's implementation (`bin/klypix-worker.mjs:902`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: eSync } = await import('child_process'); shipNotice = brainFormat.observeShipDrift(dir, { gitRun: (arg
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/klypix-worker.mjs
In the server's implementation (`src/bench.mjs:27`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from 'node:child_process'; import { buildKlypixMap, parseKlypix } from './klypix-format.mjs'; const nowMs
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/bench.mjs
In the server's implementation (`src/brain-evidence.mjs:7`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ecFileSync } from 'node:child_process'; const MAX_FILE_BYTES = 2 * 1024 * 1024; const KINDS = new Set(['file', 'pr', 'u
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/brain-evidence.mjs
In the server's implementation (`src/brain-git-hook.mjs:29`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: port { execSync } from 'child_process'; const CWD = process.argv[2] || process.cwd(); const BRAIN = path.resolve(CWD, '
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/brain-git-hook.mjs
In the server's implementation (`src/capture-gap.mjs:40`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFileSync } from 'child_process'; const MAX_RECEIPTS = 300; const hash = (value) => crypto.createHash('sha256').up
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/capture-gap.mjs
In the server's implementation (`src/codex-brain-hook.mjs:4`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFileSync } from 'child_process'; import fs from 'fs'; import path from 'path'; import { codexToolActionId, de
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/codex-brain-hook.mjs
In the server's implementation (`src/git-capture-install.mjs:22`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFileSync } from 'child_process'; import { fileURLToPath } from 'url'; const HOOK_NAMES = ['post-commit', 'post-m
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/git-capture-install.mjs
In the server's implementation (`src/brain-git-hook.mjs:40`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ds. const git = (a) => execSync(`git ${a}`, { cwd: CWD, encoding: 'utf8', stdio: ['ignore', 'pipe', 'ignore'], timeout:
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/brain-git-hook.mjs
In the server's implementation (`src/global-brain-hook.mjs:590`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: 1500) => { try { return execSync(`git ${args}`, { cwd: CWD, encoding: 'utf8', stdio: ['ignore', 'pipe', 'ignore'], timeo
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/global-brain-hook.mjs
In the server's implementation (`bin/klypix-worker.mjs:78`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: lways try { await import(moduleId); } catch (error) { // The flattened ~/.claude/project-brain bundle stages
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/klypix-worker.mjs
In the server's implementation (`src/bench.mjs:57`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: '1'; const core = await import(coreUrl); const fmt = await import(formatUrl); const lock = await import(lockUrl); fs.wri
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/bench.mjs
Each tool and what it can reach — statically extracted from the published source.
add_to_canvasno sensitive capabilitybrain_askno sensitive capabilitybrain_challengeno sensitive capabilitybrain_connectno sensitive capabilitybrain_doctorno sensitive capabilitybrain_gardenno sensitive capabilitybrain_insightsno sensitive capabilitybrain_lensno sensitive capabilitybrain_messageno sensitive capabilitybrain_message_receiptno sensitive capabilitybrain_noteno sensitive capabilitybrain_reconcileno sensitive capabilitybrain_syncno sensitive capabilitycanvas_viewno sensitive capabilitycreate_canvasno sensitive capabilitylist_canvasesno sensitive capabilityproject_map_contextno sensitive capabilityproject_map_driftno sensitive capabilityproject_map_scanno sensitive capabilityread_canvasno sensitive capabilitysearch_all_brainsno sensitive capabilitysearch_canvasesno sensitive capabilityScan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v1.84.0 latest |
B 85/100 | 14 | 1.13.0 | 2026-09-07 |
v1.82.2 |
B 85/100 | 14 | 1.13.0 | 2026-09-05 |
v1.82.0 |
B 85/100 | 14 | 1.13.0 | 2026-09-01 |
v1.81.0 |
B 85/100 | 14 | 1.13.0 | 2026-08-25 |
v1.79.0 |
B 85/100 | 14 | 1.12.1 | 2026-08-24 |
v1.77.0 |
B 85/100 | 14 | 1.12.1 | 2026-08-22 |
v1.73.2 |
B 85/100 | 14 | 1.12.1 | 2026-08-17 |
v1.72.0 |
B 85/100 | 14 | 1.12.1 | 2026-08-16 |
v1.70.0 |
B 85/100 | 14 | 1.12.1 | 2026-08-15 |
v1.67.2 |
B 85/100 | 14 | 1.12.1 | 2026-08-14 |
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan klypix-mcp --online
Authenticated MCP transport with HTTP Signatures for AAuth agents
Local-first MCP server for parallel AI coding agents to claim file ownership before edits, preventing stomping on each other in the same worktree.
Agent-agnostic intercommunication system — sessions, messaging, channels, shared state, and real-time events
MCP server for AI agent task communication and delegation with diagnostic lifecycle visibility
Programmatic add/link/unlink for MCP servers across 23 AI coding agents (Claude Code, Claude Desktop, Cursor, VS Code, Codex, Gemini CLI, Zed, Cline, OpenCode, Goose, Kiro, Windsurf, and more). Functional API with dry-run support.
MCP server layer exposing agent-mesh orchestrator as an MCP agent