Categories › AI & Agents › Models, LLM APIs, routing, serving, training & GPUs
Public HTAG discovery for MCP tools, API endpoints, OpenAPI ops, and agents.
Remote server: your requests and data go to api.htagai.com. Claude Code: claude mcp add --transport http htag-docs https://api.htagai.com/mcp/v1/servers/htag-docs/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
list_guides — List the HtAG agent guides: name, uri, title, summary, updated date and source URL. Read 'calling-htag' with `get_guide` before planning HtAget_guide — Return the full markdown of one HtAG agent guide: 'calling-htag' (call order, cost rules, paging, address keys, property types; read it firsget_pricing — The HtAG data API rate card: list AUD per unit for each tier (Reference, Standard, Enhanced, Premium, Restricted) and each monthly volume balist_mcp_servers — List every MCP server HTAG currently exposes. Each entry includes the server name, a short description, its mount path, and whether it is pulist_mcp_tools — List every tool registered on a named MCP server. Use `list_mcp_servers` first to discover server names. Each entry includes the tool name, list_api_endpoints — List HTAG public REST endpoints. Optional `tag` (e.g. 'Markets', 'Property', 'Spatial') and `query` (substring against path / summary) filteget_api_endpoint — Return the full OpenAPI operation for one HTAG REST endpoint — parameters, requestBody, responses, examples. Use this BEFORE recommending anlist_micro_agents — List every callable HTAG micro-agent — turnkey agents that compose endpoint chains and apply HTAG methodology. Examples: 'suburb-analysis', Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.