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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.