MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Decompile binaries directly in Claude, Cursor & LLMs using Ghidra, Hex-Rays & Binary Ninja via Dogbolt.
MIT ★ 1 -
Native C++ MCP server plugin for IDA Pro 9.x: 249 tools for AI agents covering disassembly, Hex-Rays decompiling, microcode, types, xrefs, patching, debugging and IDAPython
MIT ★ 13 -
ida-codex-mcpgithub.com/Iamgublin/ida-codex-mcpupdated this year
IDA Codex MCP bridges IDA Pro 9.2 with the MCP ecosystem. It provides an IDA plugin and a stdio MCP server that expose function lists, call graphs, Hex‑Rays pseudocode, disassembly, imports/exports, xrefs, strings, and memory reads to MCP clients.
★ 31 -
A Model Context Protocol (MCP) server for IDA Pro: decompiler, disassembler, and analysis tools for MCP clients like Claude.
pypi MIT ★ 12 -
Secure local REST, CLI, MCP, and agent bridge for IDA Pro 9.x
MIT ★ 7 -
ida-pilotgithub.com/wklwkl115/ida-pilotupdated this year
Headless IDA Pro analysis server that exposes the decompiler and disassembler as MCP tools for AI agents — tiered tool loading, multi-layer caching, batch ops, and compact payloads to cut token cost. Go orchestrator + Python idalib workers.
MIT ★ 1