Agentic Terminal Directory
by agenticterminal.ai · remote · no sign-in to list tools · v1.0.0 · published by ai.agenticterminal
Verified merchants accepting agentic payments on Lightning/L402/BOLT12/USDT — search, verify, pay.
6 tools: 1 do something that can't be undone and 5 only read.
Scanned Oct 21, 2026
- Deletes or cancels0Claude Code: deny
- Can't be undone1Claude Code: ask: see these tools
- Changes things0Claude Code: ask
- Only reads5Claude Code: allow: see these tools
2 checks matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http directory https://mcp.agenticterminal.ai/mcpFindings
Matches of fixed checks, with the text they matched.
- Infoget_merchant
The description mentions "credential".
What this check looks forMatched text
description: "...OP attestation. Tier 2+ requires an AT credential."
- Infowhoami
The description mentions "credential".
What this check looks forMatched text
description: "Report the resolved credential state and rate limits for the calling a..."
Tools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
6 tools
Can't be undone 1Claude Code: ask
verify_payment_endpointRun a live check against a merchant's declared payment endpoint for a rail.No findings
Why it is in this group
- The name "verify_payment_endpoint" says "payment": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it Run a live check against a merchant's declared payment endpoint for a rail. Returns health, detail, and rail-specific evidence.
Only reads 5Claude Code: allow
get_merchantGet the full record for one merchant including all rails, payment endpoints, and OP attestation.1 finding
Why it is in this group
- The name "get_merchant" says "get": a word for reading.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...OP attestation. Tier 2+ requires an AT credential."
Description, as the server wrote it Get the full record for one merchant including all rails, payment endpoints, and OP attestation. Tier 2+ requires an AT credential.
list_categoriesList the category taxonomy with merchant counts.No findings
Why it is in this group
- The name "list_categories" says "list": a word for reading.
Description, as the server wrote it List the category taxonomy with merchant counts.
list_railsList supported payment rails and their current merchant counts.No findings
Why it is in this group
- The name "list_rails" says "list": a word for reading.
Description, as the server wrote it List supported payment rails and their current merchant counts.
search_merchantsSearch OP-verified merchants by rail, chain, category, agent-callable tier, trust tier, and free text.No findings
Why it is in this group
- The name "search_merchants" says "search": a word for reading.
Description, as the server wrote it Search OP-verified merchants by rail, chain, category, agent-callable tier, trust tier, and free text. Ranked by trust tier then verification recency.
whoamiReport the resolved credential state and rate limits for the calling agent.1 finding
Why it is in this group
- The name "whoami" says "whoami": a word for reading.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "Report the resolved credential state and rate limits for the calling a..."
Description, as the server wrote it Report the resolved credential state and rate limits for the calling agent.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http directory https://mcp.agenticterminal.ai/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__directory__search_merchants",
"mcp__directory__get_merchant",
"mcp__directory__list_categories",
"mcp__directory__list_rails",
"mcp__directory__whoami"
],
"ask": [
"mcp__directory__verify_payment_endpoint"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as directory. Review it before you use it.