firedbg-mcp
Enables discovery, execution, indexing, and querying of Rust program traces using FireDBG, scoped to a single Cargo workspace.
README
firedbg-mcp
A small, repository-scoped MCP server for FireDBG. It lets an agent discover Rust targets, run them under FireDBG, index traces, and inspect the complete SQLite trace without granting access to other workspaces.
Prerequisites
- Node.js 22 or newer
- A Rust Cargo workspace
firedbgandfiredbg-indexerinstalled and available onPATH
FireDBG provides installation instructions in its upstream repository. This server checks the base installation with firedbg_status; it does not replace the global FireDBG CLI, indexer, or bundled LLDB runtime.
If upstream does not publish a precompiled debugger for the active compiler, call firedbg_prepare_compatible. The tool installs the exact matching Rustup toolchain, builds only firedbg-debugger from a pinned upstream revision, smoke-tests it, and activates it under <workspace>/.firedbg-mcp/firedbg/<rust-major.minor>/. It reuses the installed FireDBG LLDB runtime and does not replace global FireDBG binaries.
Setup
npm install
npm run build
Configure an MCP client to launch the compiled server with its repository root:
{
"mcpServers": {
"firedbg": {
"command": "node",
"args": ["/absolute/path/to/firedbg-mcp/dist/index.js", "--workspace-root", "/absolute/path/to/rust-workspace"]
}
}
}
--workspace-root defaults to the server process's initial working directory. FIREDBG_BIN and FIREDBG_INDEXER_BIN may select non-default executable paths.
Every attempted tool call is appended to <workspace>/.firedbg-mcp/actions.jsonl. Raw target arguments, program output, SQL, and query parameters are excluded from the audit record; hashes are retained for correlation. In Git worktrees the directory is added to .git/info/exclude automatically.
Tools
firedbg_statusfiredbg_prepare_compatiblefiredbg_list_targetsfiredbg_runfiredbg_list_runsfiredbg_index_runfiredbg_trace_schemafiredbg_query_trace
Trace queries accept one parameterized SELECT or WITH statement. The database is opened read-only and responses are capped at 1,000 rows and 1 MiB. Use offset and limit for pagination.
Development
npm test
npm run typecheck
npm run build
npm run inspect -- --workspace-root /path/to/cargo/workspace
Debug runs are synchronous in v1. Background execution would require persisted job state, status and cancellation tools, process-tree cleanup, and restart recovery; that is intentionally outside this server's KISS-oriented scope.
Compatible-debugger builds use <workspace>/.firedbg-mcp/build only while compiling and remove that directory after success or failure. The resulting debugger is repository-local; future runs automatically pass its home to the FireDBG CLI when its embedded Rust minor version matches the workspace's active compiler.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器