BC-Bench is a benchmark for measuring coding agents on real-world Microsoft Business Central development tasks written in AL. It helps compare models and agent configurations using reproducible evaluation data.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add microsoft/BC-Bench --skill bc-al-query-mcpgit clone --depth 1 https://github.com/microsoft/BC-BenchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/microsoft/bc-bench/bc-al-query-mcp)<a href="https://agentmods.dev/skills/microsoft/bc-bench/bc-al-query-mcp"><img src="https://agentmods.dev/badge/skills/microsoft/bc-bench/bc-al-query-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/microsoft/bc-bench/bc-al-query-mcp"><img src="https://agentmods.dev/badge/skills/microsoft/bc-bench/bc-al-query-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00064 | $0.02154 |
| Opus 5 | $0.00032 | $0.01077 |
| Sonnet 5 | $0.00013 | $0.00431 |
| Haiku 4.5 | $0.00006 | $0.00215 |
Grade A, and why
bc-al-query-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Business Central AL Query MCP
Use this skill when the user asks to query Business Central data, write or fix an AL query object, join BC tables, discover BC fields, validate an AL query, or use the bc_data MCP tools (optionally alongside Microsoft Learn).
Required Capabilities
The Business Central data MCP is required — it provides table search, table schema, table relations, and AL query compile/run. This skill cannot proceed without it.
Microsoft Learn MCP is optional (docs search, docs fetch, and code sample search for official AL query syntax and examples). Use it to ground AL syntax when it is available, but do not depend on it — if it is not in your tool list, proceed with the BC data MCP tools alone.
If tools are deferred, load them with tool search before use. Do not assume a tool is available until it has been loaded or returned by discovery.
Available BC data tools — use these EXACT names only
The Business Central data MCP exposes exactly these four tools. Call them by these exact names. Do NOT invent, abbreviate, or rename them (there is no find_tables, search_tables, list_tables, get_schema, query, or run_query).
| Tool | Purpose | Key parameters |
|---|---|---|
bc_data_find_tables |
Discover tables by name/concept | searchText (string), searchMode (keyword or semantic) |
bc_data_get_table_schema |
Fields of a table | tableId (int), nameContains (optional string[] to narrow) |
bc_data_get_table_relations |
Relations/joins of a table | tableId (int), relatedToTableIds (optional int[]) |
bc_data_query |
Compile and/or run an AL query | queryText (string, the full AL query object), returnData (bool) |
The tools may appear with a host-specific server prefix — mcp__bcmcp__bc_data_query (Claude Code) or bcmcp-bc_data_query (Copilot CLI). Invoke the exact name shown in your available tool list or returned by tool search; never guess a name that is not in that list. If a call fails with "no such tool", re-list your tools and use the exact registered name rather than trying a variant.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 179 lines · 64 tokens per session scan A 49d650c1a06d
bc-al-query-mcp is a skill published in the GitHub repository microsoft/BC-Bench (57 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 2,154 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
convex-explain-app
Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.
platform-custom-field-generate
Use this skill when users need to create, generate, or validate Salesforce Custom Field metadata. Trigger when users mention custom fields, field types, Roll-up Summary fields, Master-Detail relationships, Lookup relationships, formula fields, picklists, dependent (controlling) picklists, referencing a value set from…
field-service-sobject-create-configure
Headless 360 REST API deployment step for creating sObject records. Handles describe-based field discovery, required-field derivation, entity-relationship ordering, and composite graph transactions. Use this skill when a designer skill (or a user directly) needs to create sObject records after design confirmation…
durable-objects
Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.
nornicdb-grpc
Drive NornicDB over gRPC — the Qdrant-compatible surface (Collections, Points, Snapshots) plus the additive NornicSearch service. Use when ingesting via Qdrant SDKs, migrating from Qdrant, or running hybrid text+vector search from a non-Bolt client. Covers connection, RPC catalog, collection→database mapping…