mcpwatch

← All servers

Grade B

VEYA

io.github.veyanet/veya · v1.2.8 · score 89/100 · checked 2026-11-22

Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works

Check, limit, record and prove AI agent actions with 2-of-3 validators and onchain proofs.

Source: https://github.com/veyanet/veya-mcp

Findings

SeverityRuleDetail
LowMW005Remote endpoint lists 55 tool(s) to anyone, no credentials needed.
MediumMW1021 tool(s) can execute commands or delete data (veya_sealed_execute). Require confirmation before the agent calls them.

What was checked

Public tools: veya_describe, veya_ping_chain, veya_hash_blake3, veya_verify_transaction, veya_api_health, veya_prove, veya_seal_decision, veya_pq_keygen, veya_pq_sign, veya_pq_verify, veya_run_consensus, veya_sealed_execute, veya_set_tool_policy, veya_route_message, veya_route_secure_message, veya_verify_secure_message, veya_store_memory, veya_read_memory, veya_invalidate_memory, veya_client_run_consensus, veya_pq_fingerprint, veya_public_stats, veya_public_list_agents, veya_public_get_agent, veya_public_list_certificates, veya_public_get_certificate, veya_public_get_execution, veya_verify_commitment_onchain, veya_commitment_exists, veya_read_environment_onchain

Maintainer? Add the badge

Grades refresh daily. Think a finding is wrong? Dispute this grade.

[![mcpwatch](https://www.mcpwatch.io/badge/io-github-veyanet-veya-f5f8ebb4.svg)](https://www.mcpwatch.io/s/io-github-veyanet-veya-f5f8ebb4)