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. 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.
-
re-engine-mcpgithub.com/praydog/re-engine-mcpupdated this year
MCP server that gives AI agents live access to any running RE Engine game via REFramework
MIT ★ 46 -
Free web search for AI agents — multi-engine parallel, smart re-ranking, zero API keys. | 免费 AI 联网搜索 — 多引擎并行、语义重排、零 API Key
NOASSERTION ★ 28 -
Anti reverse engineering scanner for Electron, JS and game builds. See your app the way REA and other AI RE agents see it, then fix it. CLI + MCP server for Claude Code, Codex, OpenCode.
MIT -
Auto-reproduction & certification engine for the computational biomedical modeling literature — rebuild the model, re-run it, certify whether it reproduces its own results.
MIT -
Android reverse engineering for humans and AI agents: typed Java in milliseconds, xrefs, API and secret recon, APK diff, re-signing, a native viewer and an MCP server. One Rust executable, no JVM.
Apache-2.0 ★ 20 -
Tools to interact with the Camunda 7 Community Edition Engine using the Model Context Protocol (MCP). Whether you're automating workflows, querying process instances, or integrating with external systems, Camunda MCP Server is your agentic solution for seamless interaction with Camunda.
MIT ★ 14 -
@inferlane/mcp-servergithub.com/computegauge/inferlaneupdated this year
[DEPRECATED] Use @inferlane/mcp instead. This package re-exports a thin subset of tools; the canonical MCP surface (41+ tools, SQLite persistence, credibility engine, compute exchange) now lives in @inferlane/mcp.
npm MIT -
Um projeto feito com o Gemini 4 Argon que permita analistas de malware agilizarem a análise estática básica/avançada com uma ferramenta multi-mcp agêntica que se deriva principalmente de ferramentas open-source, tais como o Ghidra, FLOSS, CAPA, radare2 e o DiE.
-
Static, reverse-engineering-assisted vulnerability triage for AI agents -- CLI + MCP server, no Ghidra required. For files you own or are authorized to test.
MIT ★ 1 -
Virtual Assistant that enables AI-Powered Malware Research and Reverse Engineering activities, bringing Threat Intelligence Insights.
MIT ★ 2 -
Agentic code discovery: ask your codebase a question, get exact file + symbol + line span in milliseconds. No re-reading, no guessing, no index to build.
MIT -
MCP servers for Android and iOS reverse engineering: static APK/IPA analysis (npm) and dynamic analysis with adb, Frida and mitmproxy (pip)
MIT ★ 1 -
iflow-mcp_miscusi-peek-cheatengine-mcp-bridgegithub.com/miscusi-peek/cheatengine-mcp-bridgeupdated this year
Let multibillion $ AI datacenters analyze the program memory for you. Create mods, trainers, security audits, game bots, accelerate RE, or do anything else with any program and game in a fraction of a time.
pypi MIT -
context-bookgithub.com/aditya201551/context-bookupdated this year
Stop re-explaining yourself to Agents. Give it the right context, right when it needs it.
MIT ★ 5 -
[ALPHA] Binary + RE workstation (strings/entropy/DiE/CAPA/DKI). Implements the Storytold craft-app harness (CLI + MCP) - see storytold/artcraft.
Apache-2.0 -
MCP server for version-aware RE-UE4SS documentation and live introspection, control, and debugging of UE4SS-injected games.
MIT ★ 2 -
A local MCP server that serves your AI only the rules matching the file you're editing — just-in-time, per file.
MIT -
A gate that refuses to let an AI agent start on an underspecified request, and a committed record of what was missing. Reference implementation of RSGA (IEEE RE 2026).
Apache-2.0 -
Horizun Civil 3D MCP: Claude <-> Autodesk Civil 3D bridge with typed, dry-run, confirmed and re-verified writes (Horizun Group)
Apache-2.0 ★ 10 -
Verified memory for AI coding agents. Every memory carries evidence and is re-verified on every pull — stale beliefs get flagged, not retrieved. MCP + CLI.
MIT ★ 1 -
Keep Claude Code context clean. Open-source toolkit: drift detection, re-read dedup, integrity scoring, AST-aware reads, 15 MCP tools. 62.6% measured savings, reproducible.
MIT ★ 46 -
gfcgithub.com/jjjebli/gfcactive
git-for-context — LLM context dedup: unchanged file re-reads collapse to hash-verified stubs, changed files return diffs. OpenCode plugin + zero-dep MCP server. Measured −34% per-turn context.
MIT ★ 1 -
Sip your tokens, don't gulp them. Keep Claude Code's context clean: drift detection, re-read dedup, integrity scoring, AST-aware reads, and 16 MCP tools for Claude Desktop.
npm MIT -
costwise-mcpgithub.com/okyashgajjar/costwise-mcpupdated this year
Local MCP server that helps coding agents stop re-reading the same code every turn. Repository intelligence, cache-write optimization, and long-term session memory. 100% local. No API keys.
MIT ★ 22 -
Your agent should already know what you're looking at. A local context harness for the browser: it reads the page and how you got there, and hands it to Claude Code, Cursor or any MCP agent.
MIT ★ 1 -
Verified memory for coding agents: your rules, decisions and past defects, briefed before each task, proven by a check you choose, and re-opened when the code they cover changes. Prompts advise; the gate enforces. Claude Code hooks, MCP for any agent, one SQLite file in the repo.
pypi MIT ★ 4