ServiceNow MCP server — 67 tools over the full REST surface, with plan-and-apply write safety, capability preflight and an ACL security scan.
- capability exposure inferred + 32
- tool safety inferred + 10
- trust mitigators mixed − 11
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 6d ago · see ecosystem CVEs →
- B · 29 → B · 31
- C · 37 → B · 29
- C · 49 → C · 37
- C · 57 → C · 49
- D · 62 → C · 57
- D · 69 → D · 62
- D · 71 → D · 69
- D · 63 → D · 71
- D · 66 → D · 63
- C · 39 → D · 66
- C · 46 → C · 39
No known CVEs for this server.
- medium dangerous code
dynamic exec: new Function()
- medium toxic flow (lethal trifecta)
lethal trifecta reachable across this server's tools: private-data access + untrusted-content ingestion + network exfil
analyzed commit 5acdcc7 · analyzer v33 · 1w ago
skills & prompt files 1
danger signals3
- dynamic code execution new Function() IvanBBaev-servicenow-mcp-ai-5acdcc7/src/api/codecheck.ts :177
new Function(source); - suspicious endpoint 169.254.169.254 (cloud metadata) IvanBBaev-servicenow-mcp-ai-5acdcc7/test/jira-host.test.js :29
"http://169.254.169.254/latest/meta-data", - suspicious endpoint 169.254.169.254 (cloud metadata) IvanBBaev-servicenow-mcp-ai-5acdcc7/test/servicenow.test.js :32
"http://169.254.169.254/latest/meta-data",
[](https://mcpobservatory.com/servers/github:LeassTaTT/servicenow-mcp-ai/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 LeassTaTT.