kitty-hive
npm
v0.7.14
Source verified
Published by seangx — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
MCP server for multi-agent collaboration — DM, tasks, workflow, federation
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 − 11 = 89. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −11 | Untrusted input concatenated into a command sink ×3 MTC-SRC-009 | injection |
2. Client adoption risk — 89 − 10 = 79. 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 |
|---|---|
| −10 | capability blast radius (critical) — 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 (`codex-channel.ts:36`): 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: ildProcess } from 'node:child_process'; import { execSync } from 'node:child_process'; import { createServer } from 'nod
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 codex-channel.ts
In the server's implementation (`dist/codex-supervisor.js: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: rt { spawn } from 'node:child_process'; import { existsSync } from 'node:fs'; import { dirname, join, resolve } from 'no
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 dist/codex-supervisor.js
In the server's implementation (`dist/index.js:12`): 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: { execSync } from 'node:child_process'; import { buildPushMessage } from './preview.js'; import { AGENT_EVENT_MODES } fr
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 dist/index.js
In the server's implementation (`dist/opencode-supervisor.js:1`): 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: ync, spawn } from 'node:child_process'; import { existsSync } from 'node:fs'; import { dirname, join } from 'node:path';
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 dist/opencode-supervisor.js
In the server's implementation (`dist/tunnel.js:5`): 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: , execSync } from 'node:child_process'; import { existsSync } from 'node:fs'; const URL_REGEX = /https:\/\/[a-z0-9-]+\.t
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 dist/tunnel.js
In the server's implementation (`opencode-channel.ts:13`): 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: ildProcess } from 'node:child_process'; import { createServer, type Server as HttpServer } from 'node:http'; import { cr
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 opencode-channel.ts
In the server's implementation (`codex-channel.ts:100`): 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: EX_CMD set) try { execSync(`${CODEX_CMD} --version`, { stdio: 'pipe' }); } catch { console.error(`[codex-cha
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server codex-channel.ts
In the server's implementation (`dist/index.js:378`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try { execSync(`${codex} mcp add hive --url ${url}`, { stdio: 'pipe' }); return { ok: true
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 dist/index.js
In the server's implementation (`dist/tunnel.js:16`): 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: const out = execSync(`where ${name}`, { encoding: 'utf8' }).trim().split(/\r?\n/)[0]; if (ou
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 dist/tunnel.js
Each tool and what it can reach — statically extracted from the published source.
hive_file_fetchingests untrusted inputhive_inboxingests untrusted inputhive_agentsno sensitive capabilityhive_checkno sensitive capabilityhive_codex_pane_wsno sensitive capabilityhive_dmno sensitive capabilityhive_dm_readno sensitive capabilityhive_opencode_pane_serverno sensitive capabilityhive_peersno sensitive capabilityhive_remote_agentsno sensitive capabilityhive_renameno sensitive capabilityhive_startno sensitive capabilityhive_taskno sensitive capabilityhive_task_cancelno sensitive capabilityhive_task_claimno sensitive capabilityhive_task_completeno sensitive capabilityhive_tasksno sensitive capabilityhive_team_createno sensitive capabilityhive_team_eventsno sensitive capabilityhive_team_infono sensitive capabilityhive_team_joinno sensitive capabilityhive_team_leaveno sensitive capabilityhive_team_listno sensitive capabilityhive_team_messageno sensitive capabilityhive_team_rename_nicknameno sensitive capabilityhive_team_set_rulesno sensitive capabilityhive_teamsno sensitive capabilityhive_update_roleno sensitive capabilityhive_whoamino sensitive capabilityhive_workflow_approveno sensitive capabilityhive_workflow_proposeno sensitive capabilityhive_workflow_rejectno sensitive capabilityhive_workflow_step_approveno sensitive capabilityhive_workflow_step_completeno sensitive capabilityhive-whoamino 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 |
|---|---|---|---|---|
v0.7.14 latest |
C 79/100 | 9 | 1.13.0 | 2026-09-07 |
v0.7.12 |
C 79/100 | 9 | 1.12.1 | 2026-08-03 |
v0.7.11 |
C 79/100 | 9 | 1.12.1 | 2026-07-28 |
v0.7.10 |
C 79/100 | 9 | 1.10.0 | 2026-07-25 |
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 kitty-hive --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