Skip to content

Intelligent Coding

CODE mode is usually reliable when context and prompts are clear. This page shows how to get better results and how Genie fits with IDE agents through Local MCP.

  • Genie uses your attached context (scripts, selections, metadata).
  • Preflight questions reduce ambiguity before generation.
  • Output is aligned to FileMaker step/function vocabulary.
  • Larger or more complex CODE requests preserve essential FileMaker step patterns more consistently, which reduces incomplete first-pass output and follow-up repair cycles.
  • Sources may be shown so you can verify references.

Local MCP brings agentic development to FileMaker

Section titled “Local MCP brings agentic development to FileMaker”

The Local MCP Bridge turns Genie into the FileMaker-aware workbench for agents outside the app, such as Codex, Cursor, or another local MCP-aware IDE agent. It gives those agents grounded FileMaker context instead of asking them to guess from source files or loose prose.

Through MCP, an agent can:

  • read Genie resources for metadata, selected metadata, live context, and attached context
  • call read-only FileMaker metadata tools such as layout, table, field, and field-on-layout lookups
  • use genie_query for read-only SELECT preview or run workflows outside Workbench
  • ask genie_get_capabilities before choosing a route
  • prepare a metadata selection from known names
  • stage one supported CODE or DATA request into Workbench for user review
  • inspect staged Workbench items and job status

The bridge does not let the external agent silently generate, apply, or mutate FileMaker during the MCP tool call. It is the agentic workbench boundary: the agent can gather context and stage work, then Genie owns review, CODE safety, DATA confirmations, and apply behavior.

For CODE and DATA work, the intended external-agent flow is:

  1. Call genie_get_capabilities.
  2. Read the relevant metadata/context resources or use the read-only tools.
  3. Use genie_query only for read-only query work outside Workbench.
  4. Prepare any needed metadata selection with genie_prepare_metadata_selection.
  5. Stage exactly one supported item with genie_stage_new_script, genie_stage_edit_script, or genie_stage_data.
  6. Review and run the item from Workbench inside Genie.

Workbench staging is separated by intent. New script requests go through genie_stage_new_script; attached or selected script edits go through genie_stage_edit_script; reviewed SQL data/schema work goes through genie_stage_data. ASK/planning remains in the IDE or normal chat, and QUERY remains a read-only MCP tool path.

Calculation Quick AI is a separate native overlay inside FileMaker’s Specify Calculation dialog. It is for drafting one calculation expression from the current dialog context.

It does not use the CODE script workflow, QuickCode authority, script apply, or chat-mode apply actions. The calculation pipeline sends a tiny calculation-focused context to the Coding provider, validates the structured calculation draft, rejects script-looking output, checks known fields and functions where possible, and inserts only draft expression text after dialog drift checks pass.

Use it when you are already in a calculation dialog and want a fast draft expression. Use CODE when you need FileMaker scripts. Use MCP Workbench when an IDE agent is handing Genie a reviewed CODE or DATA task.

  1. Attach only relevant script and schema context.
  2. Use explicit names for tables, fields, and scripts.
  3. Answer preflight questions with concrete choices.
  4. Preview before applying high-impact changes.
  • Context is too broad or stale.
  • Prompt uses ambiguous names.
  • Required metadata was not selected.

Genie is better at carrying forward essential structural patterns in CODE mode, especially when prompts involve common control flow or save/commit behavior.

  • Fewer missing structural steps in larger outputs.
  • More stable first-pass results before repair is needed.
  • Better continuity when your request references branching, script exits, field updates, or record-commit behavior.

Example of a preflight clarification question that narrows intent.

Section titled “Example of a preflight clarification question that narrows intent.”

PreflightFollowUpofConvo.png