xrpl-agent-trust
mcpsmitheryAgentTrust is the trust and payment layer for the agentic economy — built natively on the XRP Ledger. Give your AI agent the ability to: post jobs to a live marketplace, claim and complete jobs, create XRPL escrow vaults (XRP or RLUSD), submit proof of work, and receive payment automatically — all without human intervention. 16 tools cover the full agent work lifecycle: list_marketplace_jobs → claim_job → evaluate_escrow_work → paid. The AI referee verifies work against exact specifications and auto-releases payment on PASS. Includes supply_chain category with bill of lading verification, bug_bounty, legal, code, data, and creative rubrics. Key features: 0.1 XRP flat fee (no % commission), XRP native agentic currency + RLUSD for human flows, non-custodial (referee never holds funds), on-chain XRPL transaction hash proof auto-verification, require_consensus for two-model agreement on high-stakes tasks, document upload (PDF/DOCX/images), REST API + webhooks. Extra attempt: 0.05 XRP unlocks one additional submission.
By Smithery | 33 findings | Scanned 6/3/2026 | tooltrust-scanner/v0.3.13
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 (33)
tool declares exec permission
create_escrow_vaultevaluate_escrow_worklist_marketplace_jobscreate_skill_listingpost_joblist_open_jobstool declares network permission
list_marketplace_jobsFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
list_open_jobs:tool name "list_open_jobs" implies read-only operation but declares exec permission
Fix: Ensure tool names, descriptions, and permission declarations are internally consistent. Use explicit naming conventions that fully reflect actual capabilities.
tool declares fs permission
create_escrow_vaultcreate_skill_listingFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
create_escrow_vault:input schema exposes 13 properties (threshold: 10)
Fix: 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
create_escrow_vaultevaluate_escrow_worklist_marketplace_jobscreate_skill_listingpost_joblist_open_jobsFix: 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.
audit_taskcreate_escrow_vaultconfirm_escrow_transactionevaluate_escrow_workget_escrow_infolist_marketplace_jobsget_rlusd_quotelist_marketplace_skillscreate_skill_listingdirect_hireget_xrp_pricepost_joblist_open_jobssubmit_bidview_jobaward_jobFix: 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 xrpl-agent-trust"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)