Canary Lab MCP Server
canary-lab
npm
v2.2.1
Published by ferterahadi — 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.
The independent local harness for AI-repaired Playwright tests — it runs the tests itself, so a green run can't be faked.
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 − 1.2 = 99. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 99 − 7 = 92. 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 14
high Shell/command execution in server code (dist/apps/cli/init-project.js)MTC-SRC-002
In the server's implementation (`dist/apps/cli/init-project.js:17`): 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: require("path")); const child_process_1 = require("child_process"); const ui_1 = require("../../shared/cli-ui/ui"); cons
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/apps/cli/init-project.js
high Shell/command execution in server code (dist/apps/cli/install-browsers.js)MTC-SRC-002
In the server's implementation (`dist/apps/cli/install-browsers.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: require("path")); const child_process_1 = require("child_process"); const ui_1 = require("../../shared/cli-ui/ui"); cons
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/apps/cli/install-browsers.js
high Shell/command execution in server code (dist/apps/cli/mcp-client-kind.js)MTC-SRC-002
In the server's implementation (`dist/apps/cli/mcp-client-kind.js: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: readProcessEntry; const child_process_1 = require("child_process"); const run_mode_1 = require("../../shared/run-mode");
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/apps/cli/mcp-client-kind.js
high Shell/command execution in server code (dist/apps/cli/mcp-reachability.js)MTC-SRC-002
In the server's implementation (`dist/apps/cli/mcp-reachability.js:21`): 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: require("path")); const child_process_1 = require("child_process"); const project_root_1 = require("../../shared/runtime
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/apps/cli/mcp-reachability.js
high Shell/command execution in server code (dist/apps/cli/mcp-registration.js)MTC-SRC-002
In the server's implementation (`dist/apps/cli/mcp-registration.js: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: egisteredCliPath; const child_process_1 = require("child_process"); const path_1 = __importDefault(require("path")); con
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/apps/cli/mcp-registration.js
high Shell/command execution in server code (dist/apps/cli/mcp-verify.js)MTC-SRC-002
In the server's implementation (`dist/apps/cli/mcp-verify.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: yMcpRegistration; const child_process_1 = require("child_process"); // Turn the registered bridge command's `mcp doctor`
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/apps/cli/mcp-verify.js
high Shell/command execution in server code (dist/apps/cli/ui-command.js)MTC-SRC-002
In the server's implementation (`dist/apps/cli/ui-command.js:15`): 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: ire("readline")); const child_process_1 = require("child_process"); const server_1 = require("../web-server/src/server")
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/apps/cli/ui-command.js
high Shell/command execution in server code (dist/apps/cli/upgrade-migration.js)MTC-SRC-002
In the server's implementation (`dist/apps/cli/upgrade-migration.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: require("path")); const child_process_1 = require("child_process"); const upgrade_known_prompts_1 = require("./upgrade-k
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/apps/cli/upgrade-migration.js
high Shell/command execution in server code (dist/apps/web-server/src/features/agent-sessions/logic/agent-binary.js)MTC-SRC-002
In the server's implementation (`dist/apps/web-server/src/features/agent-sessions/logic/agent-binary.js: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: require("path")); const child_process_1 = require("child_process"); function isAgentKind(command) { return command =
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/apps/web-server/src/features/agent-sessions/logic/agent-binary.js
medium Dynamic module load from a non-literal (dist/apps/cli/upgrade-migration.js)MTC-SRC-005
In the server's implementation (`dist/apps/cli/upgrade-migration.js:97`): 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: igPath)]; mod = require(configPath); } catch (err) { issues.push(`failed to load: ${err.message}
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/apps/cli/upgrade-migration.js
medium Dynamic module load from a non-literal (dist/apps/web-server/src/shared/feature-loader.js)MTC-SRC-005
In the server's implementation (`dist/apps/web-server/src/shared/feature-loader.js:31`): 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 mod = require(candidate); const cfg = (mod.config ?? mod.default); if (cfg &&
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/apps/web-server/src/shared/feature-loader.js
low Shell/command execution in packaging/dev tooling (dist/apps/cli/setup.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/apps/cli/setup.js:14`): 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: require("path")); const child_process_1 = require("child_process"); const agent_1 = require("./agent"); const mcp_regist
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/apps/cli/setup.js
low Dynamic module load from a non-literal in packaging/dev tooling (tools/fix-node-pty-permissions.mjs)MTC-SRC-005
In a packaging/dev/install script (shipped, but not the server runtime) (`tools/fix-node-pty-permissions.mjs:17`): 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: perExecutable } = await import(distModule.href) ensureSpawnHelperExecutable() } catch { // not built, or node-pty ab
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 tools/fix-node-pty-permissions.mjs
low Package runs install-time scripts (postinstall)MTC-SUP-010
"canary-lab" 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 tools/fix-node-pty-permissions.mjs
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package canary-lab
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 5
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 |
|---|---|---|---|---|
v2.2.1 latest |
A 92/100 | 14 | 1.13.0 | 2026-09-07 |
v2.2.0 |
A 92/100 | 14 | 1.13.0 | 2026-08-31 |
v2.1.0 |
A 92/100 | 14 | 1.13.0 | 2026-08-30 |
v2.0.1 |
A 92/100 | 14 | 1.13.0 | 2026-08-28 |
v1.5.1 |
A 92/100 | 13 | 1.13.0 | 2026-08-25 |
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 canary-lab --onlineMore in Security & Testing
The Stripe Agent Toolkit enables popular agent frameworks including LangChain and Vercel's AI SDK to integrate with Stripe APIs through function calling.
MCP (Model Context Protocol) server for AgentGate. Enables Claude and other MCP-compatible AI assistants to request approvals.
Scan any website for AI agent readiness, payment protocols, and discovery endpoints
MCP server for aigently security guardrails — reads static catalog-data JSON, zero API dependency
Governed threat modeling, code threat verification, traceability & compliance, as MCP tools.
Governed threat modeling, code threat verification, traceability & compliance, as MCP tools.