MCP server for the FourA web scraping API - four tools, six prompts, one API key.
- capability exposure inferred + 28
- trust mitigators mixed − 3
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 1w ago · see ecosystem CVEs →
- A · 0 → B · 25
- B · 17 → A · 0
- B · 20 → B · 17
- B · 27 → B · 20
- A · 0 → B · 27
No known CVEs for this server.
- low dangerous code
env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke
- low dangerous code
env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke
- low dangerous code
env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke
- low dangerous code
env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke
analyzed commit 77dbc25 · analyzer v33 · 2d ago
skills & prompt files 2
- agent-rules fouradata-mcp-77dbc25/AGENTS.md
- agent-rules fouradata-mcp-77dbc25/CLAUDE.md
danger signals7
- suspicious endpoint 172.32.0.0 fouradata-mcp-77dbc25/tests/helpers/sites.mjs :48
just_outside_172: "http://172.32.0.0", // public, must NOT block - suspicious endpoint 169.254.169.254 (cloud metadata) fouradata-mcp-77dbc25/tests/helpers/sites.mjs :51
aws_metadata: "http://169.254.169.254/latest/meta-data/", - suspicious endpoint 1.1.1.1 fouradata-mcp-77dbc25/tests/integration-stdio/browser-profile-contract.test.mjs :55
const target = { method: "GET", url: "https://1.1.1.1/" }; - suspicious endpoint 1.1.1.1 fouradata-mcp-77dbc25/tests/integration-stdio/proxy-exit-country-contract.test.mjs :56
const target = { method: "GET", url: "https://1.1.1.1/" }; - suspicious endpoint 1.1.1.1 fouradata-mcp-77dbc25/tests/unit/safe-target.test.mjs :18
test("2. 1.1.1.1 (Cloudflare)", async () => assert.equal(await isBlocked("https://1.1.1.1"), false)); - suspicious endpoint 8.8.8.8 fouradata-mcp-77dbc25/tests/unit/safe-target.test.mjs :19
test("3. 8.8.8.8 (Google DNS)", async () => assert.equal(await isBlocked("https://8.8.8.8"), false)); - suspicious endpoint 1.2.3.4 fouradata-mcp-77dbc25/tests/unit/schema/proxy-input.test.mjs :66
ignoreProxies: ["http://1.2.3.4:8080", "socks5://5.6.7.8:1080"],
[](https://mcpobservatory.com/servers/github:fouradata/mcp/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of fouradata.