Proof Holdings D
holdings.proof/mcp-server · v1.13.0 · score 49/100 · checked 2026-11-22
One API, all things verified — control, delegation, human approval, anti-impersonation.
Source: https://github.com/ProofHoldings/mcp-server
Findings
| Severity | Rule | Detail |
|---|---|---|
| low | AG005 | Remote endpoint lists 219 tool(s) to anyone, no credentials needed. |
| critical | AG101 | tool 'send_account_email': description contains instruction-like text aimed at the model ('Do not tell the user'). Possible tool poisoning. |
| medium | AG102 | 15 tool(s) can execute commands or delete data (delete_domain_verification, delete_template, delete_webhook_endpoint, delete_sub_account, delete_profile and 10 more). Require confirmation before the agent calls them. |
What was checked
- https://api.proof.holdings/mcp: answers without auth
- npm: @proof-holdings/mcp-server@1.13.0 (static checks only; code not executed)
Public tools: create_verification, get_verification, list_verifications, trigger_verification, submit_verification_code, resend_verification, test_verify, list_verified_users, get_verified_user, start_domain_verification, check_domain_verification, delete_domain_verification, wait_for_verification, create_multi_channel_verification, get_multi_channel_verification_status, create_verification_request, get_verification_request, get_request_proofs, list_verification_requests, get_request_by_reference, cancel_verification_request, wait_for_request, validate_proof, get_proof_status, revoke_proof, pause_proof, resume_proof, list_revoked_proofs, get_proof_token, list_reissued_proofs
Maintainer? Fix, then add the badge
Grades refresh daily.
[](https://agentguard-pi.vercel.app/s/holdings-proof-mcp-server-95b5fa3b)
agentguard: static and read-only checks. A grade is not a guarantee of safety. Index · Scanner