mcp-toolbox
mcp1.4.0MCP Toolbox for Databases is an open source MCP server for databases.
By googleapis | 56 findings | Scanned 6/16/2026 | tooltrust-scanner/v0.3.17 | 15.6k
Risk Summary
Safe With Normal ControlsSecret Handling is the main signal, but overall risk remains within an acceptable range.
Potential impact: Sensitive credentials may be read, logged, or leaked to external systems.
Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (56)
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
confirm_termshcs_queryhcs_write_recordcontract_readcontract_callFix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
get_termsconfirm_termsaccount_infohcs_monitorhcs_queryhcs_understandhcs_write_recordhcs_verify_recordhcs_audit_trailgovernance_monitorgovernance_analyzetoken_pricetoken_analyzetoken_monitoridentity_resolveidentity_verify_kycidentity_check_sanctionscontract_readcontract_callcontract_analyzeFix: Review and remediate the identified issue.
declared capabilities: code/command execution
confirm_termscontract_readcontract_calldeclared capabilities: network access, database access
hcs_querydeclared capabilities: filesystem access, HTTP requests
hcs_write_recorddeclared capabilities: filesystem access
identity_resolveFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
input parameter "api_key" accepts a credential (informational; not evidence of insecure handling)
confirm_termsaccount_infohcs_monitorhcs_queryhcs_understandhcs_write_recordhcs_verify_recordhcs_audit_trailgovernance_monitorgovernance_analyzetoken_pricetoken_analyzetoken_monitoridentity_resolveidentity_verify_kycidentity_check_sanctionscontract_readcontract_callcontract_analyzeinput parameter "token_id" accepts a credential (informational; not evidence of insecure handling)
governance_monitorgovernance_analyzetoken_pricetoken_analyzetoken_monitoridentity_verify_kycFix: Avoid accepting raw credentials as input parameters. Use secret managers (e.g. 1Password CLI, AWS Secrets Manager) and ensure credentials are never logged or stored in agent traces.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y mcp-toolbox"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)