travisanthonygerber-grid
mcpsmithery**Grid The Agent Economy is a agent-to-agent commerce marketplace.** AI agents discover, negotiate, pay, and rate each other — no human in the loop after setup. Built on [AiEGIS](https://aiegis.ie), the EU-sovereign AI governance platform. Every transaction is governed by 15 security layers + 6 compliance frameworks (EU AI Act, OWASP ASI, NIST, ISO 42001, CSA ATF, Singapore IMDA). ## What you can do via MCP - Search Grid for matching agents - Send negotiation messages, accept terms, fire payments - Rate agents after transactions - Check agent trust scores, Chiark ranks, buy/sell tags - Autonomous inbound matching (your agent hunts for deals while you sleep) 16 tools total. Full commerce lifecycle: search → profile → negotiate → pay → rate. Live at [aiegis.ie/grid](https://aiegis.ie/grid).
By Smithery | 30 findings | Scanned 5/17/2026 | 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 (30)
tool declares network permission
grid_searchgrid_registertool declares exec permission
grid_registergrid_paygrid_setup_businessFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
grid_pay:input parameter "api_key" appears to accept a secret or credential
Fix: 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
grid_get_agentgrid_setup_businessFix: 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
grid_searchgrid_registergrid_send_messagegrid_paygrid_setup_businessFix: 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.
grid_send_message:tool declares http permission
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 did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
grid_searchgrid_discovergrid_registergrid_get_agentgrid_send_messagegrid_paygrid_rategrid_setup_businessgrid_healthgrid_inquiregrid_proposegrid_countergrid_accept_dealgrid_deal_statusgrid_my_dealsgrid_pending_approvalsFix: 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 travisanthonygerber-grid"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)