Open Websearch MCP Server
open-websearch
npm
v2.1.11
Published by an unidentified publisher — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
web search the internet
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 12
high Shell/command execution in server code (build/cli/runCli.js)MTC-SRC-002
In the server's implementation (`build/cli/runCli.js: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: rt { spawn } from 'node:child_process'; const COMMANDS_REQUIRING_RUNTIME = new Set([ 'search', 'fetch-web',
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 build/cli/runCli.js
high Shell/command execution in server code (build/tools/runCurrentTests.js)MTC-SRC-002
In the server's implementation (`build/tools/runCurrentTests.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: ync, spawn } from 'node:child_process'; import { existsSync, readdirSync } from 'node:fs'; import path from 'node:path';
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 build/tools/runCurrentTests.js
high Shell/command execution in server code (build/utils/playwrightClient.js)MTC-SRC-002
In the server's implementation (`build/utils/playwrightClient.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: FileSync, spawn } from 'child_process'; import { existsSync, mkdirSync, mkdtempSync, readFileSync, readdirSync, rmSync,
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 build/utils/playwrightClient.js
medium Hardcoded egress to an external endpoint (build/engines/baidu/baidu.js)MTC-SRC-003
In the server's implementation (`build/engines/baidu/baidu.js:8`): 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: const response = await axios.get('https://www.baidu.com/s', buildAxiosRequestOptions({ trustedStaticHost: t
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 build/engines/baidu/baidu.js
medium Hardcoded egress to an external endpoint (build/engines/brave/brave.js)MTC-SRC-003
In the server's implementation (`build/engines/brave/brave.js:28`): 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: const response = await axios.get(`https://search.brave.com/search?q=${encodedQuery}&source=web&offset=${pn}`, requestOp
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 build/engines/brave/brave.js
medium Hardcoded egress to an external endpoint (build/engines/csdn/csdn.js)MTC-SRC-003
In the server's implementation (`build/engines/csdn/csdn.js:7`): 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: const response = await axios.get('https://so.csdn.net/api/v3/search', buildAxiosRequestOptions({ trustedSta
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 build/engines/csdn/csdn.js
medium Hardcoded egress to an external endpoint (build/engines/exa/exa.js)MTC-SRC-003
In the server's implementation (`build/engines/exa/exa.js:37`): 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: const response = await axios.post(`https://exa.ai/search/api/search-fast`, data, requestOptions); const apiResu
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 build/engines/exa/exa.js
medium Hardcoded egress to an external endpoint (build/engines/juejin/juejin.js)MTC-SRC-003
In the server's implementation (`build/engines/juejin/juejin.js:9`): 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: const response = await axios.get('https://api.juejin.cn/search_api/v1/search', buildAxiosRequestOptions({
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 build/engines/juejin/juejin.js
medium Dynamic module load from a non-literal (build/engines/web/fetchWebContent.js)MTC-SRC-005
In the server's implementation (`build/engines/web/fetchWebContent.js:54`): 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: adabilityModule = await import(moduleName); const dom = new JSDOM(html, { url: finalUrl }); return new 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 build/engines/web/fetchWebContent.js
medium Dynamic module load from a non-literal (build/utils/playwrightClient.js)MTC-SRC-005
In the server's implementation (`build/utils/playwrightClient.js:1703`): 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 loaded = require(candidate.specifier); const normalized = normalizeLoadedPlaywrightMo
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 build/utils/playwrightClient.js
low Shell/command execution in packaging/dev tooling (build/test/test-bing-playwright-cross-restart-concurrency.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`build/test/test-bing-playwright-cross-restart-concurrency.js:10`): 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: ync, spawn } from 'node:child_process'; import { existsSync, readFileSync, readdirSync } from 'node:fs'; import { tmpdir
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 build/test/test-bing-playwright-cross-restart-concurrency.js
low Shell/command execution in packaging/dev tooling (build/test/test-mcp-adapter.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`build/test/test-mcp-adapter.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: ecFileSync } from 'node:child_process'; import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js'; import { cr
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 build/test/test-mcp-adapter.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 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 |
|---|---|---|---|---|
v2.1.11 latest |
A 92/100 | 12 | 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 open-websearch --onlineMore in Browser Automation
Model Context Protocol (MCP) server that integrates AgentQL data extraction capabilities.
Screenshot any URL or HTML as PNG/JPEG/WebP from your AI agent. Full-page, clean, no install.
MCP server for aria51 accessibility scanner
Bridge any browser web app to Claude Code via MCP
Browserbase’s official MCP server: cloud headless browsers for agents, with sessions and screenshots.
MCP server for AI web browser automation using Browserbase and Stagehand