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.
-
Rust library, CLI, and Dockerized MCP server for static disassembly of PE, ELF, and raw binaries using Miasm, with JSON output and control-flow graphs.
GPL-2.0 -
MCP server for controlling Google Flow (Veo, Nano Banana) with AI agents from your own browser.
MIT ★ 5 -
A controlled AI workflow for Blender: every copilot edit is a supervised tool call—proposed, approved, executed in sequence, cancellable after the current step and undoable by name—inside a visual studio with a built-in MCP server. · blender-ai-copilot-flow · blender · blender 3d · blender addon · blender plugin · blender extension
MIT ★ 427 -
nifipilotgithub.com/giojacke/mcp-nifipilotupdated this year
MCP server for Apache NiFi 2.2.0 — lets AI agents inspect and control NiFi flows
pypi -
Drive Google Flow from the command line: Veo video and Imagen images, scripted, batched and pipeline-ready. Ships an MCP server so coding agents can drive it too, giving you and your agents full programmatic control over generation. Unofficial, alpha, not affiliated with Google.
pypi MIT ★ 395 -
An MCP server that scales development into controllable agentic, recursive flows, and build a feature from bottom-up
MIT ★ 46 -
Benzi is code intelligence infrastructure for AI models. It compiles your codebase into a resolved, queryable map of calls, data flow, control flow and class hierarchy first; then it reads, explains, runs, edits and verifies your code using it. Every language runs its own tree-sitter grammar into the same query map.
NOASSERTION ★ 179 -
mcp-nifipilotgithub.com/Giojacke/mcp-nifipilotupdated this year
AI Copilot for Apache NiFi — MCP server with 17 tools to inspect, build and control NiFi flows via AI agents
★ 1 -
MCP server for SharpTrader trading software: connect Claude, ChatGPT and other AI agents for monitoring, strategy control, scheduled orders within limits, flow profile and 76 indicators.
-
A production-ready Model Context Protocol (MCP) server for Apache Kafka. Features Information Flow Control (IFC) sandboxing, granular namespace isolation, and strict bounded buffers to securely bridge autonomous AI agents with enterprise streaming infrastructure.
Apache-2.0 ★ 2 -
MCP server that indexes any codebase with tree-sitter into one local SQLite file — function inventory, call graph, call chains, module dependency graph, control-flow graph, impact analysis and dead-code detection for AI coding agents (Claude Code, Cursor,
npm MIT -
Local code index for AI agents. Scans a repo with tree-sitter into one SQLite file — function inventory, call graph, module deps, control flow, impact analysis — then serves 32 MCP tools to Claude Code, Cursor and VS Code. No LLM calls, no upload, no telemetry. npm i -g codindex
MIT ★ 3 -
MCP server that drives a deployed DeerFlow instance over its HTTP API: deep research and full thread/run/artifact control.
npm MIT -
A structural review layer for Python — baseline-aware, deterministic, built for CI and AI agents
pypi MPL-2.0 AND MIT