Input schema
{}Risk classification
Inferred read-only · medium confidence · heuristic, not a guarantee.
- No write-capable action terms were found; this is not proof that invocation has no side effects.
Parent endpoint
CONNECT 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.gethal-ai]
url = "https://gethal.ai/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"gethal-ai": {
"type": "http",
"url": "https://gethal.ai/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: gethal-ai
Remote MCP URL: https://gethal.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": {
"gethal-ai": {
"url": "https://gethal.ai/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"gethal-ai": {
"type": "http",
"url": "https://gethal.ai/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "gethal-ai",
"transport": "streamable-http",
"url": "https://gethal.ai/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
Related tools
get_company_info— Returns the company name, operator, contact email, homepage, and a short description of gethal.get_features— Returns the six core features of gethal.get_use_cases— Returns representative B2B sales use cases (outbound prospecting, market expansion, partner-channel sales) with example prompts.describe_hal— Explains how the HAL autonomous sales agent works: the six-stage pipeline (find → research → qualify → quality control → draft → send) and key traits.get_customer_profile— Returns the target customer profile for gethal.book_demo— Submits a demo request.