Agent Bus Connect Cli MCP Server
@agent-bus-connect/cli
npm
v0.32.0
Published by @agent-bus-connect — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Local message bus that lets Claude Code, Codex and other MCP agents talk to each other through one SQLite file.
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 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. 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 |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
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.
Findings 7
high Tool "record_test_result" exposes command/code executionMTC-CAP-001
Tool "record_test_result" appears to run shell commands or evaluate code (parameter "command"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool record_test_result
high Shell/command execution in server code (dist/cli/index.js)MTC-SRC-002
In the server's implementation (`dist/cli/index.js:2`): 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"; import { existsSync, readFileSync } from "node:fs"; import { homedir } 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 dist/cli/index.js
high Shell/command execution in server code (dist/cli/ui.js)MTC-SRC-002
In the server's implementation (`dist/cli/ui.js:30`): 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: void import("node:child_process").then(({ spawn }) => { const child = spawn("open", [url], { stdio: "i
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/cli/ui.js
high Shell/command execution in server code (dist/util/hooks.js)MTC-SRC-002
In the server's implementation (`dist/util/hooks.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: spawnSync } from "node:child_process"; import { readScopeConfig } from "./project.js"; export function runLocalHook(eve
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/util/hooks.js
medium Untrusted input can drive an external actionMTC-FLOW-005
Untrusted-input tools ([get_message, task_result, get_task]) co-exist with external-action tools ([record_test_result]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [get_message, task_result, get_task] → sinks [record_test_result]
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow get_message → record_test_result
medium Unconstrained command parameter "command" on "record_test_result"MTC-CAP-006
Tool "record_test_result" takes a command-shaped parameter "command" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool record_test_result · inputSchema.properties.command
low Mutating tool "record_test_result" declares no destructiveHintMTC-CAP-005
Tool "record_test_result" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool record_test_result
Tools 65
Each tool and what it can reach — statically extracted from the published source.
get_messageingests untrusted inputget_taskingests untrusted inputrecord_test_resultruns code / shelltask_resultingests untrusted inputackno sensitive capabilityacknowledge_taskno sensitive capabilityactivityno sensitive capabilityaskno sensitive capabilityask_asyncno sensitive capabilityask_bestno sensitive capability
Show 55 more tools ↓
ask_teamno sensitive capabilityassign_taskno sensitive capabilitycancel_taskno sensitive capabilitycheck_scope_conflictsno sensitive capabilityclaim_best_taskno sensitive capabilityclaim_taskno sensitive capabilitycockpitno sensitive capabilitycreate_taskno sensitive capabilitydelegateno sensitive capabilitydelegate_teamno sensitive capabilitydelete_teamno sensitive capabilitydirectoryno sensitive capabilityfinal_reportno sensitive capabilityhandoff_taskno sensitive capabilityinboxno sensitive capabilityinbox_previewsno sensitive capabilityinbox_statusno sensitive capabilitylist_decisionsno sensitive capabilitylist_memoriesno sensitive capabilitylist_task_eventsno sensitive capabilitylist_tasksno sensitive capabilitylist_test_resultsno sensitive capabilitymessage_statusno sensitive capabilitynowno sensitive capabilitypin_memoryno sensitive capabilityproject_boardno sensitive capabilityrecentno sensitive capabilityrecord_decisionno sensitive capabilityrecord_task_eventno sensitive capabilityregisterno sensitive capabilityrelease_taskno sensitive capabilityrememberno sensitive capabilityremove_agentno sensitive capabilityreplyno sensitive capabilityreply_threadno sensitive capabilityreview_gateno sensitive capabilitysendno sensitive capabilitysend_channelno sensitive capabilitysend_teamno sensitive capabilitysession_briefno sensitive capabilityset_agent_statusno sensitive capabilitysleep_agentno sensitive capabilitysubmit_reviewno sensitive capabilitysubscribeno sensitive capabilitysubscribersno sensitive capabilityteam_boardno sensitive capabilitythreadno sensitive capabilityunpin_memoryno sensitive capabilityunsubscribeno sensitive capabilityupdate_taskno sensitive capabilitywait_for_agentsno sensitive capabilitywait_for_taskno sensitive capabilitywake_agentno sensitive capabilitywhoisno sensitive capabilitywhy_no_replyno sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (65 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan 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 |
|---|---|---|---|---|
v0.32.0 latest |
A 93/100 | 7 | 1.13.0 | 2026-09-07 |
Embed this score
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.
Verify this score yourself
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 @agent-bus-connect/cli --onlineMore in AI & Agents
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