Integration

AccessEXL integration

AccessEXL (Access Analytic) exposes one Excel workbook stored in SharePoint as a controlled API: read what the workbook owner exposed, write input cells, recalculate and read the results in one what-if call, goal seek an input to hit a target output, and read or write the rows of exposed Excel tables. What can be read or written is set by configuration tables inside the workbook (APIConfigTable, APIBlocksConfigTable), so call get_schema first and use its names exactly. Every successful call except refresh_schema counts against the organisation's monthly quota (a table write once per row, a goal seek once per try), and paid plans bill calls beyond the allowance. Connecting workbooks, managing keys and AccessEXL's published AI agent capabilities are not part of this API. Authentication is a workbook API key sent in the X-API-Key header. Each key opens exactly one workbook, so each workbook needs its own connection; an org admin or the member who connected the workbook creates keys in AccessEXL on the Workbooks page (the workbook's settings icon, API keys), and each key is shown once.

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in AccessEXL.Built from the 8 AccessEXL tools below, on the connection you add once.

What you can do with AccessEXL

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.

Table row, 2 operations

  • list_table_rowsList table rowsGETAgents: ask firstReturns the rows of an Excel table the workbook exposes for reading, with only its configured columns. Refused (403) for a write-only table or one with more rows than the plan reads in one call. Counts as one API call.
  • write_table_rowsWrite table rowsPOSTAgents: ask firstWrites rows to an Excel table the workbook exposes for writing: appended, or replacing every existing row when the table's write_mode is overwrite (see get_schema). Billed one API call per row written; at most 1,000 rows.

Workbook schema, 2 operations

  • get_schemaGet schemaGETAgents: ask firstCall first: returns the workbook's writable inputs (type, min, max, allowed values, required), readable ranges, exposed tables with their columns, display names, descriptions, units and model status. Counts as one API call.
  • refresh_schemaRefresh schemaPOSTAgents: ask firstRe-reads the workbook's configuration tables now, bypassing the five-minute cache, and returns the same interface as get_schema. Use after the workbook owner edits them. Never counts against the quota.

Goal seek, 1 operation

  • goal_seekGoal seekPOSTAgents: ask firstGoal seek, like Excel's: varies one number input until one readable output reaches a target, recalculating each time, in one call. Each try is billed as one API call (vendor default 20 tries); returns the value found and every output at it.

Scenario, 1 operation

  • run_scenarioRun scenarioPOSTAgents: ask firstWhat-if in one call: writes the given input values into the workbook, recalculates and returns every readable output, atomically. Changes the workbook's inputs unless it resets after each call. Counts as one API call.

Workbook input, 1 operation

  • update_inputsUpdate inputsPOSTAgents: ask firstWrites the given input values into the workbook and recalculates, returning only what was written; use run_scenario to get the results in the same call. Changes the workbook's inputs unless it resets after each call. One API call.

Workbook output, 1 operation

  • get_outputsGet outputsGETAgents: ask firstReturns the current value of every readable range of the workbook, keyed by range name, plus display_names; writes and recalculates nothing. Counts as one API call.

Use AccessEXL from Claude Code, Cursor or Codex

Connect AccessEXL in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its AccessEXL 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 AccessEXL

  1. Create your workspace

    Sign up free. Nothing to install.

  2. Connect AccessEXL once

    Add your AccessEXL connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.

  3. 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.

AccessEXL integration FAQ

What can you do with the AccessEXL integration?

LiveContext exposes 8 operations on AccessEXL, covering table row, workbook schema, goal seek and scenario.

Popular integrations

Browse the whole catalog