Hypertab API Documentation

The live operational workspace between you and MCP — where connected work is stored, webhook routes keep it flowing while your computer is off, and you see, run, and steer it.

For AI Tools

Hypertab exposes 86 MCP tools. Connect via the MCP endpoint, read hypertab://tables to see your workspace, and start operating. Every response includes a hints array with the recommended next step.

Activity

For visible long-running work, register a client, start a session, create an agent run, and append events as you work. The Activity screen shows the durable run, artifact, approval, and command records.

1. Get your API key

Open workspace Settings → MCP connections at app.hypertab.ai. It generates a revealed setup key, a full .mcp.json block, and a chat-ready MCP install prompt. Keys start with ht_sk_ and authenticate both REST API and MCP connections.

Your API Key

ht_sk_your_api_key_here

2. Install Hypertab MCP

Run npx @hypertabai/mcp install once. It writes the MCP config to the right location and installs the Hypertab skill where supported. No JSON editing, no skill-file hunting — one credential-free command, a hidden terminal prompt, and a restart.

Pick your MCP client on the right. The command prints what it wrote and what to do next.

Do not put the key in the command or an inline environment assignment; shells can retain command text in history. Run the command without a credential and enter the key only at the installer's hidden terminal prompt. Skill file: https://app.hypertab.ai/skill.md

npx @hypertabai/mcp install

npx @hypertabai/mcp install --client claude-code --scope project

3. Add a local bridge wrapper

For visible local-agent work, scaffold a conservative wrapper, mint a client-bound bridge token, check local readiness, then run the wrapper. It reports bridge events, artifacts, command results, and health while checking the safe command contract.

Bridge wrapper

npx @hypertabai/mcp bridge wrapper init --type node --out .hypertab/bridge-wrapper.mjs
printf 'Hypertab admin API key: ' >&2; read -rs HYPERTAB_API_KEY; printf '\n' >&2; export HYPERTAB_API_KEY
npx @hypertabai/mcp bridge token create --client-name "$(hostname)-codex" --client-type codex --expires-in-days 30 --json
printf 'Bridge token: ' >&2; read -rs HYPERTAB_API_KEY; printf '\n' >&2; export HYPERTAB_API_KEY
npx @hypertabai/mcp bridge wrapper doctor --path .hypertab/bridge-wrapper.mjs --json
HYPERTAB_BRIDGE_CLIENT_NAME="$(hostname)-codex" HYPERTAB_BRIDGE_CLIENT_TYPE=codex node .hypertab/bridge-wrapper.mjs "Report local bridge health"

4. Create a table

Tables live inside Projects. Reuse an existing Project when it fits, or create one, then pass itsproject_id when creating the Table.

MCP Tool Calls

[
  { "tool": "hypertab_list_projects", "arguments": {} },
  {
    "tool": "hypertab_create_project",
    "arguments": { "title": "Growth ops" }
  },
  {
    "tool": "hypertab_create_table",
    "arguments": {
	  "project_id": "pg_project_id",
      "name": "leads",
      "columns": [
        { "name": "company", "type": "text" },
        { "name": "website", "type": "url" },
        { "name": "size", "type": "number" }
      ]
	}
  }
]

5. Insert records

Insert up to 10,000 records per call. Column names are fuzzy-matched — if you type companey instead of company, Hypertab auto-corrects it and tells you in the response.

MCP Tool Call

{
  "tool": "hypertab_insert_rows",
  "arguments": {
    "table": "leads",
    "rows": [
      { "company": "Acme Corp", "website": "https://acme.com", "size": 500 },
      { "company": "Globex", "website": "https://globex.com", "size": 1200 }
    ]
  }
}

6. Add a smart column

Smart columns process data per record. Use {{column_name}} to reference other columns as input. Save the service key in an encrypted API account, then reference the returned account ID. Inline keys and credential-bearing URLs are rejected.

{
  "tool": "hypertab_save_api_account",
  "arguments": {
	"name": "Company data API",
	"service": "company-data",
	"auth_type": "api_key",
	"header_name": "X-API-Key",
	"token": "<api-key>",
	"base_url": "https://api.example.com"
  }
}

7. Run the smart column

After adding a smart column, trigger it to process all existing records. New records will be processed automatically if auto_run is enabled.

MCP Tool Call

{
  "tool": "hypertab_run_column",
  "arguments": {
    "table": "leads",
    "column": "industry"
  }
}

8. Check progress

Monitor the run status to see how many records have been processed. The response includes total records, processed count, error count, and completion percentage.

MCP Tool Call

{
  "tool": "hypertab_get_column_run_status",
  "arguments": {
    "run_id": "run_abc123"
  }
}

9. Query results

Once complete, query the table to see the smart column values populated for each record.

MCP Tool Call

{
  "tool": "hypertab_query_rows",
  "arguments": {
    "table": "leads",
    "columns": ["company", "website", "size", "industry"],
    "limit": 10
  }
}

Next steps

Authentication

API keys, headers, and MCP connection

Tables API

Create, list, update, and delete tables

Smart Columns

HTTP, Formula, Integration — columns that DO things

Error Codes

Every error code with fix suggestions

Authentication