Chinese Rag Toolkit MCP Server
@yiong/mcp-chinese-rag-toolkit
npm
v0.7.1
Source verified
Published by yiongq — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
Reusable MCP server + Chinese RAG pipeline toolkit (factory + Tool builder + error envelope + eval framework). Powers @yiong/mcp-hr, @yiong/mcp-modeling and third-party MCP servers.
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 − 6 = 94. 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 |
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 6
high Shell/command execution in server code (bin/scaffold.ts)MTC-SRC-002
In the server's implementation (`bin/scaffold.ts: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: rt { spawn } from 'node:child_process'; import { copyFileSync, existsSync, mkdirSync, readdirSync, readFileSyn
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/scaffold.ts
high Shell/command execution in server code (dist/cli/create-mcp-rag.cjs)MTC-SRC-002
In the server's implementation (`dist/cli/create-mcp-rag.cjs: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: e("node:url"); let node_child_process = require("node:child_process"); //#region bin/scaffold.ts /** * scaffold library
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/create-mcp-rag.cjs
high Shell/command execution in server code (dist/cli/create-mcp-rag.js)MTC-SRC-002
In the server's implementation (`dist/cli/create-mcp-rag.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: rt { spawn } from "node:child_process"; //#region bin/scaffold.ts /** * scaffold library — called by `bin/create-mcp-ra
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/create-mcp-rag.js
medium Dynamic module load from a non-literal (bin/run-vision-caption-demo.ts)MTC-SRC-005
In the server's implementation (`bin/run-vision-caption-demo.ts:61`): 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('s', 'return import(s)') as ( s: string, ) => Promise<{ default: new (opts: { apiKey: string }) =>
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/run-vision-caption-demo.ts
medium Dynamic module load from a non-literal (dist/index.cjs)MTC-SRC-005
In the server's implementation (`dist/index.cjs:5431`): 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("s", "return import(s)")("@napi-rs/canvas"); } /** * Ensure `@napi-rs/canvas` is available. Resolves to the l
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.cjs
medium Dynamic module load from a non-literal (dist/index.js)MTC-SRC-005
In the server's implementation (`dist/index.js:5425`): 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("s", "return import(s)")("@napi-rs/canvas"); } /** * Ensure `@napi-rs/canvas` is available. Resolves to the l
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
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 3
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 |
|---|---|---|---|---|
v0.7.1 latest |
A 94/100 | 6 | 1.13.0 | 2026-09-07 |
v0.6.0 |
A 94/100 | 6 | 1.12.1 | 2026-08-07 |
v0.5.0 |
A 94/100 | 6 | 1.12.1 | 2026-08-05 |
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 @yiong/mcp-chinese-rag-toolkit --onlineMore in Business & CRM
Free public tax reference data — GST/VAT, income, company and capital-gains tax rules for 50+ countries.
The approval gate for unattended UCP buying agents — a policy/approval MCP proxy in front of a merchant's UCP checkout endpoint.
Autotask PSA MCP server. Generic entity query/get/create/update across the full REST API plus convenience tools for tickets, companies, contacts, projects, tasks and time entries. AI-safe with readonly mode and destructive-action confirmation. stdio + opt
MCP server for B2C Commerce developer experience tools
Search, compare and contact real-world companies through a public MCP business directory.
Norwegian business register (Brønnøysundregistrene) as an MCP server — companies, roles, subunits and annual accounts, with the register's silent traps encoded as guards.