plith-plith
mcpsmitheryThe base layer for AI agents. Five APIs: task deduplication, cost prediction, output validation, behavioral governance, and shared failure intelligence. 1,000 free credits/month, no card required.
By Smithery | 34 findings | Scanned 5/26/2026 | tooltrust-scanner/v0.3.12
Risk Summary
Needs ApprovalDep Visibility plus Excessive Permissions raises enough risk that this tool should not be auto-trusted.
Potential impact: This finding indicates the tool should be reviewed before it is trusted.
Recommended action: Keep this tool behind manual approval and avoid unattended runs until the risky capabilities are narrowed or removed.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (34)
tool declares exec permission
dedupq_checkdedupq_completeburnrate_estimateguardrail_checkguardrail_create_policypitfalldb_querypitfalldb_reporttool declares network permission
pitfalldb_queryFix: 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 "input_tokens" appears to accept a secret or credential
burnrate_trackinput parameter "output_tokens" appears to accept a secret or credential
burnrate_trackinput parameter "cache_read_tokens" appears to accept a secret or credential
burnrate_trackFix: 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.
tool declares fs permission
qualitygate_validateguardrail_create_policyFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
dedupq_checkdedupq_completeburnrate_estimateguardrail_checkguardrail_create_policypitfalldb_querypitfalldb_reportFix: 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.
dedupq_checkdedupq_completeburnrate_estimateburnrate_trackburnrate_optimizeburnrate_budgetqualitygate_validatequalitygate_trendsguardrail_checkguardrail_create_policyguardrail_list_policiespitfalldb_querypitfalldb_reportpitfalldb_statsFix: Review and remediate the identified issue.
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 plith-plith"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)