ida-mcp-rs: driving IDA Pro from an AI agent without the GUI
Headless IDA Pro MCP Server
At a glance
- What is it?
- blacktop/ida-mcp-rs wraps IDA Pro's idalib interface in an MCP server so an agent can open, disassemble and decompile binaries headlessly. It is a thin, useful bridge with a hard dependency on a paid IDA licence and a version-matched install.
- Who is it for?
- ida-mcp-rs exposes IDA's headless analysis and editing capabilities to MCP clients. Check the current release's compatibility with your IDA installation and license, and verify the required shared libraries and decompiler entitlement.
- Can I use it commercially?
- Yes. MIT is a permissive licence: you can use, modify and sell software built on it, as long as you keep its copyright and licence notices.
- Is it still maintained?
- Yes. The repository last received commits 14 days ago.
- What is it written in?
- Mainly Rust, according to GitHub's language statistics.
Answers come from the project's GitHub data, last synced on November 15, 2026, and from our analysis. They are not legal advice.
Star history
- blacktop/ida-mcp-rs907 ★ · +106
| Repository | 2026-09-11 | 2026-11-15 |
|---|---|---|
| blacktop/ida-mcp-rs | 801 | 907 |
106 Stars in the last 65 days, measured from the daily GitHub snapshot. Compare with other projects
Editorial analysis
The gap between IDA's GUI and an agent's tool loop
IDA Pro is normally a desktop application. You open a database, click through functions, and read the decompiler in a pane. An agent needs an appropriate integration to interact with those capabilities. It needs a callable interface with named operations and structured returns, and it needs the analysis to happen somewhere other than a window a human is watching. ida-mcp-rs fills that gap by exposing IDA's headless library (idalib) over the Model Context Protocol. The README describes the project as a headless IDA Pro MCP server for AI-powered reverse engineering, and the topic list confirms the stack: idalib, idapro, mcp, rust. The intended user is someone with a compatible licensed IDA installation, and who wants an agent to triage a binary before a human opens it. It is not a disassembler. Every capability it offers is IDA's, routed through a Rust binary that speaks MCP.
How the server talks to idalib and to the agent
The binary links against IDA's shared libraries at runtime rather than bundling them. The README's runtime requirements table lists libida.dylib on macOS, libida.so on Linux and ida.dll on Windows, with fallback configuration for each: DYLD_LIBRARY_PATH, IDADIR (read by the launcher) or LD_LIBRARY_PATH, and on Windows either placing the executable in the IDA directory or setting IDADIR and adding that directory to PATH. Standard install paths are auto-detected through baked RPATHs. That design keeps the release archive small and avoids redistributing Hex-Rays code, but it means the server is only as portable as the host's IDA install. On the agent side, the server registers under a name you choose, and the README shows the same command shape for Claude Code, Codex CLI and Gemini CLI, plus a JSON block for Cursor using .cursor/mcp.json with a command entry of ida-mcp. The data flow is: agent sends an MCP tool call, the Rust server translates it into an idalib operation, IDA performs the work against the open database, and the result comes back as structured output the agent can read.
Opening a database is fast because analysis is a separate step
The usage example is explicit that open_idb returns quickly and analysis runs separately. Some tools can be called before full analysis, but their results may be incomplete. The current README recommends checking `analysis_status` and running analysis when functions or cross-references are incomplete. That split matters on large binaries. The README recommends running analyze_funcs with background: true for cross-references and decompilation on big inputs, which returns a task_id that you poll with task_status. The example task identifier has the form analyze-<random>. Decompilation requires a suitable Hex-Rays entitlement; analysis readiness affects results, and the example call is decompile(address: "0x100000f00"). There is also a discovery tool, tool_catalog, shown queried with the string "find callers", which suggests the tool surface is larger than the README enumerates. That is worth noting: the README demonstrates a handful of tools but does not publish a complete list, so the catalog is the place to look rather than the documentation.
Where the database lands, and why the hash check exists
By default a raw input is loaded with IDA's normal loader and saved to <input>.i64. The idb_out parameter redirects that database elsewhere, which the README frames as useful for read-only input directories. The reuse rule is the interesting part: an existing output is reused only when IDA's recorded input SHA-256 matches the current file. The rebuild: true flag can overwrite a database only when its hash or recorded input path proves it belongs to the input. This is a deliberate guard against the classic mistake of pointing a tool at a path that has since been replaced by a different binary, then reading stale analysis as if it described the new file. The guard reduces accidental mismatch risk but does not replace backups: rebuild can overwrite a matching database, including edits. Check the exact output path and preserve a copy before rebuilding.
The version lock is the constraint that will bite first
The server's releases are matched to IDA versions, so check the current compatibility table before installing or upgrading. A newer server is not necessarily compatible with an older IDA installation. Distribution channels and available builds can change; use the release notes for the exact version and architecture rather than relying on a historical package-manager listing.
Getting it running: three commands and two environment variables
The README documents installation and MCP registration for macOS, Linux and Windows. The server needs IDA's runtime libraries; nonstandard locations may require `DYLD_LIBRARY_PATH` on macOS, `IDADIR` or `LD_LIBRARY_PATH` on Linux, or the IDA directory on Windows' `PATH`. Follow the instructions for the matching release and verify loading before configuring the client.
MCP gives the client access to analysis, database modification and IDAPython execution. Limit access to trusted clients and inputs, review tool permissions, and avoid exposing the server on an untrusted network without appropriate authentication and isolation.
What you are actually adopting, and the licence question
The project itself is MIT licensed, which covers the Rust server code. It does not and cannot cover IDA Pro or idalib. The README requires a compatible IDA installation with a valid license, and the runtime linking model means the binary is inert without IDA's shared libraries present. Decompilation requires the appropriate Hex-Rays capability and entitlement; check the terms of your specific IDA edition. So the effective cost of adoption is the IDA licence you already hold or must buy, plus the maintenance cost of keeping the ida-mcp release tag aligned with your IDA version on every upgrade. The release cadence shows three releases between mid-July and late August 2026, which suggests the tags move when IDA does. None of this is legal advice; if you redistribute the binary or bundle it into a product, the interaction between the MIT licence on the wrapper and Hex-Rays' terms on the linked library is a question for your own counsel, not for this README.
How this differs from running IDA's own scripting interface
The obvious alternative is IDAPython, or IDA's headless command-line mode, driven by a script you write yourself. That approach has no MCP layer, no tool schema, and no agent-facing protocol; you get IDA's full API and you own all the glue. ida-mcp-rs trades that flexibility for a fixed, discoverable tool surface that any MCP-capable agent can call without custom integration work. The server exposes a defined tool surface, and its documented `run_script` tool can also execute IDAPython in the open database. That flexibility expands the permission and security boundary. The README shows list_functions, disasm_by_name, strings, open_idb, analyze_funcs, task_status, decompile and tool_catalog, and it does not document the full set, so an analyst can inspect the current tool catalog or use IDAPython where appropriate. A second alternative, using a disassembler that is not IDA, removes the licence dependency entirely but also removes Hex-Rays output, which for many reverse engineering tasks is the reason to use IDA in the first place. The honest framing is that this project is a convenience layer over an existing paid tool, not a replacement for it.
Editorial conclusion
ida-mcp-rs exposes IDA's headless analysis and editing capabilities to MCP clients. Check the current release's compatibility with your IDA installation and license, and verify the required shared libraries and decompiler entitlement. The server can modify databases and run IDAPython, so restrict client access, inspect requested actions and work on backed-up copies of sensitive databases.
Frequently asked questions
Which IDA Pro version does ida-mcp-rs work with?
The project publishes releases matched to IDA versions, including a 9.5 line. Check the current release notes and README for the exact IDA version and platform supported by the build you install; a mismatch can cause IDA-backed tools to fail.
How do I install ida-mcp-rs on Windows?
With Scoop, which locates IDA and sets IDADIR, or by copying ida-mcp.exe next to ida.dll and idalib.dll inside the IDA directory and giving the agent that full path. Windows has to resolve those DLLs before the server starts, and a third documented route sets IDADIR and the user Path by hand before restarting the terminal.
Which coding agents can use ida-mcp-rs?
The README provides setup examples for Claude Code, Codex CLI, Gemini CLI and Cursor. MCP compatibility alone does not guarantee a client's configuration or permission behavior; check its current documentation and the matching IDA and server versions.
Can ida-mcp-rs write to the IDA database?
Yes. The documented tools include renaming, comments, patches and other database changes. `save_idb` checkpoints edits; keep a separate backup and verify tool results before relying on changes.
Why does building ida-mcp-rs depend on a branch?
The source build uses Git dependencies for idalib. Inspect the selected revision's Cargo manifest and lockfile: a branch can move, while a committed lockfile may record a specific Git revision. Verify the resolved source when producing a reproducible build.
Official sources
Add this badge to your README
If you maintain this project, the badge below links readers to this analysis and shows its maintenance status from the daily GitHub snapshot. Paste the markdown into your README; add ?metric=license or ?metric=stars to the image URL for a different field.
[](https://hysenlabs.com/projects/blacktop-ida-mcp-rs)Star history chart for your README
[](https://hysenlabs.com/projects/blacktop-ida-mcp-rs)Was this useful?