Search BC knowledge topics, find specialists, or discover workflows. Use this when users want to find information about BC development.

Get detailed content for a specific BC knowledge topic with examples and best practices.

Consult a BC specialist for direct expert guidance. Returns specialist instructions and relevant BC knowledge. Auto-selects best specialist or use preferred_specialist parameter. Set autonomous_mode=true for structured action plans instead of conversational responses.

Analyze AL code files in a workspace or specific files. IMPORTANT: Use workspace_path or file_path parameters - the MCP reads files directly. Do NOT pass code content unless you have inline code that is not in a file.

Browse available BC specialists and their expertise areas. Useful for discovering the specialist team and understanding who helps with what. After browsing, use ask_bc_expert with preferred_specialist parameter to connect with a specific specialist.

Extract a Business Central snapshot (.snap) file to analyze debug traces, AL source code, and execution flow. Snapshots are ZIP archives containing .mdc debug trace files and .al source files. Returns temp directory path where files can be read using standard file tools.

Set workspace root directory and available MCP server IDs. Enables project-specific knowledge layers and ecosystem-aware specialist recommendations. Call before other BC tools to activate workspace context.

Get the currently configured workspace root directory and available MCP servers, if any.

List all available BC Code Intelligence workflows.

Use this tool to discover structured workflows that can guide the user through complex processes like code reviews, debugging, or app development.

Returns a list of available workflows with:

• workflow_type: The ID to pass to workflow_start

• name: Human-readable workflow name

• description: What the workflow helps with

• specialist: The recommended specialist for this workflow

• phases: The phases/steps in the workflow

Call this early in conversations to see if a workflow matches the user's intent.

Start a workflow session - a stateful checklist management system that drives agents through systematic, file-by-file processing.

Workflows provide:

• File inventory with per-file checklists

• Dynamic checklist expansion based on analysis

• Pattern scanning for migrations (e.g., Error→ErrorInfo)

• Batch operations for large-scale changes

• Progress tracking and session persistence

The workflow drives the agent with explicit next-action instructions.

Example usage:

• Start a code review: workflow_type="code-review"

• Start an error migration: workflow_type="error-to-errorinfo-migration"

• Start a BC upgrade: workflow_type="bc-version-upgrade" with source_version and target_version

Get the next action to perform in a workflow session.

Call this when you're ready for the next task. The engine returns:

• Current progress (phase, files completed, percent)

• Current file's checklist status

• Next action with explicit instructions

• Tool call suggestions for the action

The agent MUST follow the next_action instructions exactly.

Report progress on current workflow action and get the next action.

Call this after completing each action (analyzing a file, applying a topic, converting an instance). Include any findings, proposed changes, and topics to add to the checklist.

The engine updates session state and returns the next action to perform.

Get current workflow v2 session status without advancing.

Returns:

• Overall progress (phase, percent complete)

• Summary of findings by severity

• Summary of proposed changes

• Optionally: status of all files

Use this to check on workflow progress or recover context after interruption.

Complete a Workflow Engine v2 session and generate the final report.

Call this when all files have been processed (next_action.type === "complete_workflow").

Options:

• generate_report: Create a summary report (default: true)

• apply_changes: Apply all auto-applicable proposed changes (default: false)

• report_format: markdown, json, or html (default: markdown)

Returns the final summary and report content.

Apply batch operations to multiple pattern instances in a Workflow Engine v2 session.

For pattern-based workflows (like error-to-errorinfo-migration), this allows efficient bulk operations:

• apply_fixes: Apply auto-fixes to matching instances

• skip_instances: Mark instances as skipped

• flag_for_review: Mark instances for manual review

• group_by_type: Get instances grouped by type

Use dry_run=true (default) to preview changes before applying. Use confirmation_token from dry_run to execute the operation.

Cancel a workflow session or clear all workflow sessions.

Use cases:

• Cancel a stale/orphaned workflow from a previous session

• Reset workflow state when restarting work

• Clear all workflows to start fresh

Options:

• session_id: Cancel a specific workflow session

• cancel_all: true to cancel ALL active workflow sessions

Get merged CodeLens pattern-to-specialist mappings from all active layers. Used by VSCode extension to show inline specialist suggestions in AL code.

Check if a directory has valid BC Code Intelligence layer structure. Returns validation status, missing items, and suggestions for fixing.

Create BC Code Intelligence layer folder structure with templates. Use this to bootstrap a new company, team, or project layer.

Create a new topic, specialist, or prompt in a BC Code Intelligence layer with proper frontmatter formatting.

List all available prompts from all active layers. Returns prompt metadata for UI display.