API Tools
agenticterminal.ai
MCP server for searching, verifying, and retrieving merchant payment endpoints and rails.
ENDPOINT 1
https://mcp.agenticterminal.ai/mcp
MCP server metadata
- Name
- at-directory
- Version
- 0.0.1
Known tools 6
search_merchantsSearch OP-verified merchants by rail, chain, category, agent-callable tier, trust tier, and free text.
Inferred read-onlyget_merchantGet the full record for one merchant including all rails, payment endpoints, and OP attestation.
Potential side effectsverify_payment_endpointRun a live check against a merchant's declared payment endpoint for a rail.
Potential side effectsCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.at-directory]
url = "https://mcp.agenticterminal.ai/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"at-directory": {
"type": "http",
"url": "https://mcp.agenticterminal.ai/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: at-directory
Remote MCP URL: https://mcp.agenticterminal.ai/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"at-directory": {
"url": "https://mcp.agenticterminal.ai/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"at-directory": {
"type": "http",
"url": "https://mcp.agenticterminal.ai/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "at-directory",
"transport": "streamable-http",
"url": "https://mcp.agenticterminal.ai/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for agenticterminal.ai was fetched 2026-07-25T19:36:25.375Z and is being refreshed.
agenticterminal.ai is assessed as Trusted: Domain runs a meaningful technology spend, consistent with a real business.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.