MCP servers for Windsurf (legacy)

Python code intelligence for coding agents: call paths, control flow, and change impact.

Visual code workflow explorer for coding agents. Builds deterministic, source-grounded Mermaid flowcharts via MCP, local-first, with no API

Embeds your codebase and makes it available for quick LLM lookups via MCP.

MCP server for comprehensive GitHub repository analysis using Gemini AI

Graph-intelligent, token-efficient code navigation for AI assistants. Surgical reading, execution flows, risk scoring, and micro-metadata

Your codebase's memory. Persistent organizational memory for AI coding agents.

An MCP server for the codetoprompt library, enabling integration with LLM agents.

MCP server providing AI-powered access to Google CodeWiki for open-source repositories

Local stdio MCP delegation server that routes Claude-orchestrated tasks through codex exec

Policy-as-code enforcement for AI agents with MCP, CEL, Git hooks, SARIF, and static-analysis guardrails.

Self-hosted agent continuity server with bounded, recoverable memory and restart orientation.

A CoinEx MCP (Model Context Protocol) server that enables AI agents to interact with the CoinEx cryptocurrency exchange

MCP server for cold-chain sensor data analysis: threshold breaches, anomalies, journey segmentation. All processing local.

AI co-pilot for VFX artists using ComfyUI: 134 MCP tools across 6 swappable LLM providers (incl. any OpenAI-compatible endpoint), zero-LLM

Local-first MCP server that drafts, organizes, validates, and runs ComfyUI workflows - saved as clean, labeled, annotated UI-format graphs

Standalone MCP server + client for generating Anima-style images via a remote/local ComfyUI Server API.

HTML comparison Command Line Tool

A Model Context Protocol server for cognitive complexity analysis using complexipy

An MCP server that provides tools to author OSCAL security compliance documentation

Model Context Protocol Server via Cross-Platform (Mac & Windows) Split Screen Functions

A drop-in confidence gate for LLM agents: turn token logprobs into an accept / verify / ask-a-human routing decision, with honest per-model