Toon Protocol Client MCP Server
@toon-protocol/client-mcp
npm
v0.36.9
Published by @toon-protocol — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
Always-on local daemon + MCP server letting a Claude agent (Desktop or Code) act as a TOON Protocol client: pay-to-write publishing, free reads, channel/balance management, and swaps.
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 − 8 = 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 |
| −2 | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read |
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 8
high Dynamic evaluation of a non-literal value (dist/chunk-6GXZ4KRO.js)MTC-SRC-010
In the server's implementation (`dist/chunk-6GXZ4KRO.js:1966`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: urn out; }, eval(a, x, brp = false) { checkLength(a); const idx = findOmegaIndex(x, a.length
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/chunk-6GXZ4KRO.js
high Dynamic code execution in server code (dist/chunk-6GXZ4KRO.js)MTC-SRC-001
In the server's implementation (`dist/chunk-6GXZ4KRO.js:1966`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: urn out; }, eval(a, x, brp = false) { checkLength(a); const idx = findOmegaIndex(x, a.length
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/chunk-6GXZ4KRO.js
high Dynamic code execution in server code (dist/lib-RZLOBGC4.js)MTC-SRC-001
In the server's implementation (`dist/lib-RZLOBGC4.js:7085`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ow Error(); Function(` 'use strict' const o = new Proxy({}, { get: () => o, set: ()
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/lib-RZLOBGC4.js
high Shell/command execution in server code (dist/chunk-3NXM53VC.js)MTC-SRC-002
In the server's implementation (`dist/chunk-3NXM53VC.js:844`): 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: execFile, spawn } from "child_process"; import { promisify } from "util"; import { execFile as execFile2, spawn as spawn
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/chunk-3NXM53VC.js
high Shell/command execution in server code (dist/chunk-ZRGYINDO.js)MTC-SRC-002
In the server's implementation (`dist/chunk-ZRGYINDO.js:18739`): 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: import { spawn } from "child_process"; import { existsSync as existsSync3, mkdirSync as mkdirSync3, openSync, r
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/chunk-ZRGYINDO.js
medium Dynamic module load from a non-literal (dist/lib-RZLOBGC4.js)MTC-SRC-005
In the server's implementation (`dist/lib-RZLOBGC4.js:16924`): 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: w Function("p", "return import(p)")(pkg); } catch (err) { const cause = err; const wrapped =
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/lib-RZLOBGC4.js
low Dynamic code execution in packaging/dev tooling (dist/e2e/run-journey.js)MTC-SRC-001
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/e2e/run-journey.js:3017`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ss(d, e); let m = Function(`${Uo.default.self}`, `${Uo.default.scope}`, d)(this, this.scope.get()); if (this
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/e2e/run-journey.js
low Shell/command execution in packaging/dev tooling (dist/e2e/run-journey.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/e2e/run-journey.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: execFile as Xre } from "child_process"; import { randomUUID as sw } from "crypto"; import { createReadStream as Yre, rea
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/e2e/run-journey.js
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 9
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 |
|---|---|---|---|---|
v0.36.9 latest |
A 92/100 | 8 | 1.13.0 | 2026-09-07 |
v0.36.6 |
A 92/100 | 8 | 1.12.1 | 2026-08-07 |
v0.36.5 |
A 92/100 | 8 | 1.12.1 | 2026-08-06 |
v0.36.4 |
A 92/100 | 8 | 1.12.1 | 2026-08-05 |
v0.36.0 |
A 92/100 | 8 | 1.12.1 | 2026-08-04 |
Show 4 more versions ↓
v0.35.1 |
A 92/100 | 8 | 1.12.1 | 2026-08-03 |
v0.21.2 |
A 92/100 | 8 | 1.12.1 | 2026-07-31 |
v0.20.7 |
A 92/100 | 8 | 1.12.1 | 2026-07-29 |
v0.20.5 |
B 83/100 | 5 | 1.5.0 | 2026-07-22 |
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 @toon-protocol/client-mcp --onlineMore in Content Management
Apify MCP Server
Model Context Protocol (MCP) Server for the *@inkeep/agents-mcp* API.
Medicare spending, chronic conditions, hospital quality, readmissions, and enrollment
Public read-only MCP for products, frameworks, guides, methodology, and blog metadata.
Community-maintained MCP server for Atlassian Confluence Data Center. Not affiliated with Atlassian.
MCP server for Contentful Content Management API integration