Integration

Tabrica integration

Tabrica (Табрика) is a Russian cloud no-code database and table builder. Through its Public API v1 an agent can list a table's records with server-side filters, sorting, paging and field selection, read one record, create records, change some fields of a record, and delete records. Databases, tables and fields themselves cannot be listed or changed through the API (their numeric ids come from the table's address in Tabrica), file fields are read-only, and the older pre-v1 record routes, retired after 1 August 2026, are not exposed. Every call counts toward the organization's monthly Public API quota (3,000 requests on the free plan). Authentication is an organization API token created in the organization settings, API tab, sent as a Bearer token: a read token can only list and read, a write (editor) token can also create, update and delete.

Connect Tabrica How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Tabrica.Built from the 5 Tabrica tools below, on the connection you add once.

What you can do with Tabrica

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Each badge shows the default agent permission of an endpoint (allowed: an agent calls it without asking; ask first: you are asked before an agent calls it, when the agent or chat asks permission for sensitive actions; never: no agent may call it), which every user can change endpoint by endpoint in their credential settings.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

create_recordCreate recordPOSTAgents: ask firstCreates a record in a table from data, an object of field values keyed by field name or system id, and returns the new id and stored values. Changes the table; needs a write token.
delete_recordDelete recordDELETEAgents: ask firstDeletes one record from a table. Changes the table; needs a write token. Pass row_id from list_records; the answer says how many records were deleted.
get_recordGet recordGETAgents: ask firstReturns one record of a table by its id: id plus one key per field, keyed by field name or system id (response_format). Pass row_id from list_records or create_record.
list_recordsList recordsGETAgents: ask firstLists one table's records, page by page (limit up to 1000, offset), with an optional filter (where), sort and field selection. Returns the records (id plus one key per field) and the total number matching.
update_recordUpdate recordPATCHAgents: ask firstChanges only the fields sent in data on one record (others keep their value) and returns the whole updated record. Changes the table; needs a write token. Pass row_id from list_records.

Use Tabrica from Claude Code, Cursor or Codex

Connect Tabrica in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Tabrica operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Tabrica

Create your workspace
Sign up free. Nothing to install.
Connect Tabrica once
Add your Tabrica connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.