BSL MCP Analyzer
An MCP analyzer for 1C BSL code: project-wide diagnostics, per-method complexity and refactor priorities, no Java
- 4 ★ on the repository
- Last commit
Extended access
Why this level
- Brings up a Docker stack that indexes a BSL project and serves MCP over HTTP with a token
- Computes complexity and diagnostics without changing project code
A similar tool with a larger community: BSL Analyzer, 117 ★ on the repository
Install
- Works in
- Services
In your terminal, with SkillFoxx CLI
npx skillfoxx add mcp/bsl-mcp-analyzerDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Brings up a Docker stack that indexes a BSL project and serves MCP over HTTP with a token
- Computes complexity and diagnostics without changing project code
This is third-party code. Review the repository files before installing.
What it does
The server builds three new tools on top of the onec-hbk-bsl engine (pure Python, no Java or LSP bridge): complexity computes cyclomatic and cognitive complexity per method with thresholds; module_health merges complexity with security, performance and SQL diagnostics into a ranked top_targets refactor list; workspace_diagnostics aggregates 180-plus lint rules project-wide, grouped by rule, severity and file. It also inherits the underlying engine's symbol navigation, definitions, references, callers and callees, search, rename and formatting. The server runs in Docker behind nginx, one container per project, reachable via a Bearer token at /bsl/<project>/mcp.
Who it is for. For 1C developers and tech leads who need quantitative BSL complexity metrics and refactor priorities without installing Java tooling.
Good fit when
- You need numeric cyclomatic and cognitive complexity metrics for BSL methods
- You need a ranked refactor list instead of just a pile of warnings
- You need project-wide lint diagnostics for 1C aggregated by file and rule
Not a fit when
- You have no Linux host with Docker Engine 24+ to deploy on
- You only need code browsing or search, not complexity and lint analysis
- Your project is too small for a refactor ranking to matter
Example request
Show the top modules to refactor in this 1C project and the cognitive complexity of the worst methodMCP
- Transport
- http
- Authentication
- API key
Environment variables
BSL_MCP_TOKENrequired, secret- Bearer token for accessing projects through nginx
Limitations
It only deploys in Docker on Linux, needs about 2 GB RAM and 2 CPUs per project, and indexing large configurations is CPU and disk heavy. The tool depends on the separate onec-hbk-bsl project as its engine. License is not machine-readable via the GitHub API, and the main README file is in English only.
How to disable. Stop the project container with docker compose down and remove the server from your MCP client config.
FAQ
Do I need Java?
No, the onec-hbk-bsl engine is pure Python and needs no Java or LSP bridge.
Can one server analyze several projects?
Each project gets its own bsl-<proj> container, all proxied by one nginx on different paths.
Discussion
No questions or reviews yet.
Related
All 1C:Enterprise toolsA Rust-based Language Server for BSL with code diagnostics, incremental analysis and a built-in MCP server for AI agents
onec-hbk-bsl: BSL linter and MCP
1C HBK BSL (onec-hbk-bsl)
A BSL CLI linter and formatter with 180 diagnostics, an LSP server for VS Code and Cursor, and MCP tools for local AI assistants
An MCP server that exposes the cloud 1C:Napparnik (1C.ai) assistant and a local BSL Language Server to agents in Cursor and other IDEs
A local stdio MCP server on Node.js: builds an in-memory call graph over a 1C BSL source export and finds definitions, callers, callees and the impact radius
MCP server with the 1C platform reference and validation of BSL code against the real API of a chosen platform version
An MCP server for BSL syntax checks on BSL Language Server in Docker: send code, get back JSON errors and warnings with no Java install needed
README in short
The English README (with a Russian README.ru.md) explains that the project reuses the onec-hbk-bsl engine and adds three missing tools: numeric complexity, a module health summary and project-wide aggregation. It shows an nginx architecture with Bearer auth, a Docker Compose quick start, a curl check for 200 versus 401, and config examples for opencode and mcpServers-style clients like Cursor.