Skip to content
Bkper
app.header.homeapp.header.docsapp.header.apps
Open Bkper

CLI vs MCP

Choose how an AI assistant should use Bkper: MCP for conversational tool calls, or CLI local tools for repeatable command-line workflows.

Bkper offers two ways for AI assistants to use your data:

  • MCP tool calls connect an assistant directly to Bkper for conversational analysis.
  • CLI local tools let an assistant work through your terminal, files, scripts, tests, and app workflows.

Default rule: if your assistant can run terminal commands, prefer CLI local tools for Bkper work. Use MCP when terminal access is not available, or when you specifically want conversational connector access.

CLI local tools can do the same Bkper operations as MCP, plus scripts, files, tests, builds, app workflows, and reusable artifacts. They are usually more efficient, cost-effective, and scalable for multi-turn or repeatable work because more execution happens outside the LLM context.

Quick choice

Choose…When you need…
MCP tool callsconversational exploration, suspicious-transaction review, book-structure questions, guided analysis, or assistant access without a terminal
CLI local toolssetup scripting, app creation and management, build/deploy workflows, CSVs, local files, tests, repeatable reports, or auditable artifacts

How the two paths differ

MCP tool calls

tooltooltoolLLMUsercontextcontextcontext

With MCP, the assistant calls Bkper tools directly. Each tool result returns to the LLM context before the next call, so context can grow across the session. This is useful for conversational analysis, but less efficient for long, repeatable workflows.

CLI local tools

local workspacebashscriptscripttoolpipepipeUserLLMcontextcontext

With CLI local tools, the assistant works through a local environment. It can create or run scripts, call command-line tools, and receive selected output. Scripts and pipes can also run without sending every intermediate result back to the LLM context.

When CLI local tools fit best

CLI local tools give the agent more than Bkper access. They give it a working environment:

  • App lifecycle work — setup, app creation, build, sync, deploy, and management workflows belong in the CLI local-tool path. MCP can help discuss app design, but it is not the app build/deploy environment.
  • Durable context — files, exports, fixtures, scripts, and reports stay in the workspace.
  • Tool chaining — commands can be piped together without adding every intermediate result to the LLM context.
  • Deterministic runs — scripts and build engines can be run again with the same inputs and reviewed outputs.
  • Reusable work — a report, app, migration, or reconciliation helper can be rerun, tested, improved, and committed.
  • Better review — proposed changes can be shown as commands, diffs, CSVs, or generated artifacts before anything is applied.

Example:

bkper transaction list -b <bookId> -q 'on:2026-06' --format json \
  | jq '.items[] | {date, description, amount}'

That matters for finance: raw LLM output should not be the final answer for accounting numbers. When a workflow produces balances, statements, reconciliations, taxes, or batch changes, prefer a deterministic route that can be rerun and reviewed.

Where MCP fits well

Use MCP when conversational access matters more than local files, scripts, or command-line workflows:

  • asking an AI assistant to summarize book structure;
  • listing books, accounts, groups, transactions, or balances;
  • exploring data before deciding what to do next;
  • reviewing or spotting suspicious transactions interactively;
  • working from a device or environment where a terminal is not practical;
  • giving an assistant controlled access through the Bkper connector.

MCP can also be useful inside local coding tools as an extra connector. But if the agent can already run shell commands, use the Bkper CLI for Bkper operations and app lifecycle work, and use MCP as a supplement when it fits the interaction.

  1. If your assistant can run terminal commands, install and authenticate the Bkper CLI.
  2. Use CLI local tools for multi-turn Bkper workflows, scripts, app lifecycle work, builds, tests, and auditable artifacts.
  3. Use MCP Server when terminal access is unavailable or when you specifically want conversational connector access.