bc-code-intelligence-mcp
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Returns a result when called with no setup: 5 of 5 tools tried
Contacts while installing and starting: nothing
What it contacted
Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.
Starting it
npx -y -p bc-code-intelligence-mcp@1.7.7 bc-code-intelligence-mcp
Installing a package runs its code. Use a sandbox for anything you have not read.
Calling its tools
5 tools that take no input and look read-only were called once with nothing. 5 returned a result.
list_specialists | Returned a result under 0.1 s · 247 characters |
get_workspace_info | Returned a result under 0.1 s · 288 characters |
workflow_list | Returned a result under 0.1 s · 247 characters |
get_codelens_mappings | Returned a result under 0.1 s · 247 characters |
list_prompts | Returned a result under 0.1 s · 247 characters |
During the calls it contacted nothing it had not already contacted.
Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
2 tools with commands in capitals or very long text
- Gives the agent orders in
analyze_al_code: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 conten
- Gives the agent orders in
workflow_next:tructions - Tool call suggestions for the action The agent MUST follow the next_action instructions exactly.
Common and usually harmless: it is how many makers stress how a tool should be used.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
find_bc_knowledge query, search_type, bc_version, limit
Search BC knowledge topics, find specialists, or discover workflows. Use this when users want to find information about BC development.
get_bc_topic topic_id, include_samples, specialist_context
Get detailed content for a specific BC knowledge topic with examples and best practices.
ask_bc_expert question, context, preferred_specialist, autonomous_mode
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 workspace_path, file_path, file_paths, code, analysis_type, operation, bc_version, suggest_workflows
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.
list_specialists domain, expertise
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.
16 more tools
extract_bc_snapshot snapshot_path
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_info workspace_root, available_mcps
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_workspace_info
Get the currently configured workspace root directory and available MCP servers, if any.
workflow_list
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.
workflow_start workflow_type, scope, path, options, initial_processing
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
workflow_next session_id
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.
workflow_progress session_id, completed_action, findings, proposed_changes, expand_checklist
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.
workflow_status session_id, include_all_files
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.
workflow_complete session_id, generate_report, apply_changes, report_format
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.
workflow_batch session_id, operation, filter, dry_run, confirmation_token
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.
workflow_cancel session_id, cancel_all
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_codelens_mappings
Get merged CodeLens pattern-to-specialist mappings from all active layers. Used by VSCode extension to show inline specialist suggestions in AL code.
validate_layer_repo path
Check if a directory has valid BC Code Intelligence layer structure. Returns validation status, missing items, and suggestions for fixing.
scaffold_layer_repo path, layer_type, layer_name, include_examples
Create BC Code Intelligence layer folder structure with templates. Use this to bootstrap a new company, team, or project layer.
create_layer_content layer_path, content_type, name, title, domain, metadata
Create a new topic, specialist, or prompt in a BC Code Intelligence layer with proper frontmatter formatting.
list_prompts type, include_content
List all available prompts from all active layers. Returns prompt metadata for UI display.
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Install facts
| License | MIT |
|---|---|
| Needs | node >=20.0.0 |
| Source | github.com/JeremyVyska/bc-code-intelligence-mcp |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-0N3otI+dMuKtcN9DnU5uWZScmM53bBQxPdp7Odr6Zw79YJ+jDBQuqsYF9+KJvMiYzr26QdGQ8OI11mZVIEtohA== |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/bc-code-intelligence-mcp)
New version out? Ask for a fresh report.