Swarmclaw MCP Server
@swarmclawai/swarmclaw
npm
v1.9.39
Published by @swarmclawai — 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.
Build and run autonomous AI agents with OpenClaw, Hermes, multiple model providers, orchestration, delegation, memory, skills, schedules, and chat connectors.
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 − 7.5 = 93. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −6.3 | Untrusted input concatenated into a command sink MTC-SRC-009 | injection |
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 93 − 7 = 86. 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 15
high Shell/command execution in server code (bin/daemon-cmd.js)MTC-SRC-002
In the server's implementation (`bin/daemon-cmd.js:9`): 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: spawn } = require('node:child_process') const { BROWSER_PROFILES_DIR, DATA_DIR, PKG_ROOT, SWARMCLAW_HOME, WOR
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/daemon-cmd.js
high Shell/command execution in server code (bin/install-root.js)MTC-SRC-002
In the server's implementation (`bin/install-root.js:8`): 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 } = require('node:child_process') const PACKAGE_NAME = '@swarmclawai/swarmclaw' const CORE_PACKAGE_NAMES = new Se
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/install-root.js
high Shell/command execution in server code (bin/server-cmd.js)MTC-SRC-002
In the server's implementation (`bin/server-cmd.js:8`): 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 } = require('node:child_process') const { detectPackageManager, getInstallCommand, } = require('./package-mana
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/server-cmd.js
high Shell/command execution in server code (bin/swarmclaw.js)MTC-SRC-002
In the server's implementation (`bin/swarmclaw.js:8`): 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: nSync } = require('node:child_process') // Legacy TS CLI groups/actions that provide richer, command-specific options.
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/swarmclaw.js
high Shell/command execution in server code (bin/update-cmd.js)MTC-SRC-002
In the server's implementation (`bin/update-cmd.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: eSync } = require('node:child_process') const path = require('node:path') const { dependenciesChanged, detectPackage
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/update-cmd.js
high Shell/command execution in server code (bin/worker-cmd.js)MTC-SRC-002
In the server's implementation (`bin/worker-cmd.js: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: spawn } = require('node:child_process') const { BROWSER_PROFILES_DIR, DATA_DIR, PKG_ROOT, SWARMCLAW_HOME, WOR
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/worker-cmd.js
medium Hardcoded egress to an external endpoint (src/lib/server/embeddings.ts)MTC-SRC-003
In the server's implementation (`src/lib/server/embeddings.ts:76`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: s') const res = await fetch('https://api.openai.com/v1/embeddings', { method: 'POST', headers: { 'Conten
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/lib/server/embeddings.ts
medium Untrusted input concatenated into a command sink (src/lib/server/agents/guardian.ts)MTC-SRC-009
In the server's implementation (`src/lib/server/agents/guardian.ts:25`): 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: g[]): string { return execSync(`git ${args.join(' ')}`, { cwd, encoding: 'utf8', stdio: ['ignore', 'pipe',
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/lib/server/agents/guardian.ts
medium Dynamic module load from a non-literal (bin/swarmclaw.js)MTC-SRC-005
In the server's implementation (`bin/swarmclaw.js:240`): 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: const cliModule = await import(cliPath) const runCli = cliModule.runCli || (cliModule.default && cliModule.default.run
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/swarmclaw.js
low Shell/command execution in packaging/dev tooling (scripts/easy-setup.mjs)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/easy-setup.mjs: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: spawnSync } from 'node:child_process' const isWindows = process.platform === 'win32' const args = new Set(process.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 scripts/easy-setup.mjs
low Shell/command execution in packaging/dev tooling (scripts/easy-update.mjs)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/easy-update.mjs: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: spawnSync } from 'node:child_process' const args = new Set(process.argv.slice(2)) const skipBuild = args.has('--skip-b
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 scripts/easy-update.mjs
low Shell/command execution in packaging/dev tooling (scripts/ensure-sandbox-browser-image.mjs)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/ensure-sandbox-browser-image.mjs:6`): 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' const cwd = process.cwd() const args = new Set(process.argv.slice(2)) const quie
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 scripts/ensure-sandbox-browser-image.mjs
low Shell/command execution in packaging/dev tooling (scripts/postinstall.mjs)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/postinstall.mjs:6`): 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' const INSTALL_METADATA_FILE = '.swarmclaw-install.json' const scriptDir = path.di
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 scripts/postinstall.mjs
low Dynamic module load from a non-literal in packaging/dev tooling (src/cli/server-cmd.test.js)MTC-SRC-005
In a packaging/dev/install script (shipped, but not the server runtime) (`src/cli/server-cmd.test.js:15`): 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: dPath] const loaded = require(modPath) if (previousHome === undefined) delete process.env.SWARMCLAW_HOME else proc
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/cli/server-cmd.test.js
low Package runs install-time scripts (postinstall)MTC-SUP-010
"@swarmclawai/swarmclaw" executes postinstall script(s) at install time. An install hook runs at install time; most are routine build/setup, but review what it does before trusting it.
Evidence: node ./scripts/postinstall.mjs
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package @swarmclawai/swarmclaw
Tools 3
Each tool and what it can reach — statically extracted from the published source.
cwd_checkno sensitive capabilityechono sensitive capabilitypingno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (3 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 |
|---|---|---|---|---|
v1.9.39 latest |
B 86/100 | 15 | 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 @swarmclawai/swarmclaw --onlineMore in Productivity & Workflow
MCP AgentChat - 让 AI Agent 通过 Telegram 与用户实时交互：发送消息、图片，等待用户回复
A Model Context Protocol (MCP) server for Airthings Air Quality Monitor devices.
MCP server for Anki
TypeScript package for reading and searching Apple Notes on macOS via direct SQLite access. Includes markdown conversion, attachment support, and offers a local MCP server!
Verified biotech catalyst calendar (PDUFA/AdComm/trial readouts) anchored to official sources.
Appointment booking platform letting agents check provider availability and create bookings.