Web Fetcher MCP Server
web-fetcher-mcp
npm
v1.0.28
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.
MCP Server for fetching any web page content with login support
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 11
high Tool "execute-js" exposes command/code executionMTC-CAP-001
Tool "execute-js" appears to run shell commands or evaluate code (parameter "script"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool execute-js
high Dynamic code execution in server code (dist/tools/get-page-info.js)MTC-SRC-001
In the server's implementation (`dist/tools/get-page-info.js:34`): 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: const getHtmlSkeleton = eval(`(${skeletonFuncStr})`); // 查找目标元素 let targetElement = document.que
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/tools/get-page-info.js
high Dynamic code execution in server code (dist/utils/html-to-markdown.js)MTC-SRC-001
In the server's implementation (`dist/utils/html-to-markdown.js:14`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: win.__TurndownService = new Function(`${turndownSrc}\n;return TurndownService;`)(); } if (!win.__turndow
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/utils/html-to-markdown.js
high Dynamic code execution in server code (dist/utils/page-content.js)MTC-SRC-001
In the server's implementation (`dist/utils/page-content.js:6`): 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: const getHtmlSkeleton = eval(`(${skeletonFuncStr})`); let detailElement = document.querySelector(selector);
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/utils/page-content.js
medium Untrusted input can drive an external actionMTC-FLOW-005
Untrusted-input tools ([fetch-web-page, get-page-info, fetch-web-page-markdown]) co-exist with external-action tools ([upload-file, execute-js]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [fetch-web-page, get-page-info, fetch-web-page-markdown] → sinks [upload-file, execute-js]
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow fetch-web-page → upload-file
medium Unconstrained URL/host parameter "url" on "fetch-web-page"MTC-CAP-007
Tool "fetch-web-page" takes a URL/host parameter "url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool fetch-web-page · inputSchema.properties.url
medium Unconstrained URL/host parameter "url" on "get-page-info"MTC-CAP-007
Tool "get-page-info" takes a URL/host parameter "url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool get-page-info · inputSchema.properties.url
medium Unconstrained URL/host parameter "url" on "upload-file"MTC-CAP-007
Tool "upload-file" takes a URL/host parameter "url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool upload-file · inputSchema.properties.url
medium Unconstrained URL/host parameter "url" on "fetch-web-page-markdown"MTC-CAP-007
Tool "fetch-web-page-markdown" takes a URL/host parameter "url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool fetch-web-page-markdown · inputSchema.properties.url
medium Unconstrained command parameter "script" on "execute-js"MTC-CAP-006
Tool "execute-js" takes a command-shaped parameter "script" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool execute-js · inputSchema.properties.script
low Mutating tool "execute-js" declares no destructiveHintMTC-CAP-005
Tool "execute-js" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool execute-js
Tools 20
Each tool and what it can reach — statically extracted from the published source.
execute-jsruns code / shellfetch-web-pageingests untrusted inputfetch-web-page-markdowningests untrusted inputget-page-infoingests untrusted inputupload-filenetwork egresscapture-elementno sensitive capabilityclick-elementno sensitive capabilityclose-browserno sensitive capabilityfocus-input-elementno sensitive capabilityget-console-logsno sensitive capability
Show 10 more tools ↓
get-element-attributesno sensitive capabilityhover-elementno sensitive capabilitylist-tabsno sensitive capabilitynavigate-historyno sensitive capabilityopen-devtoolsno sensitive capabilityscroll-pageno sensitive capabilityselect-optionno sensitive capabilityswitch-tabno sensitive capabilitytype-input-elementno sensitive capabilitywait-for-elementno sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (20 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 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 |
|---|---|---|---|---|
v1.0.28 latest |
A 92/100 | 11 | 1.13.0 | 2026-09-07 |
v1.0.27 |
A 92/100 | 9 | 1.12.1 | 2026-08-15 |
v1.0.26 |
A 92/100 | 9 | 1.12.1 | 2026-08-12 |
v1.0.21 |
A 92/100 | 9 | 1.12.1 | 2026-08-10 |
v1.0.18 |
A 98/100 | 3 | 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 web-fetcher-mcp --onlineMore in Web, Search & Scraping
Agent IP: MCP server with patents search tools
MCP server for searching the Agent Almanac — the public catalog of 9,000+ Model Context Protocol servers. Find, install, and discover MCP servers from inside Claude Desktop, Cursor, Continue, Zed, or any MCP-aware agent.
Search agents & MCP servers by capability, with daily-observed pricing, liveness and market data.
Verified merchants accepting agentic payments on Lightning/L402/BOLT12/USDT — search, verify, pay.
Airframe MCP Client - Connect agents to Airframe's product intelligence
Amazon product search demand over time, with growth for any keyword. Free key at trendsmcp.ai