mcp — independent software & tools
-
patient-zero
Supply-chain attack scanner for the agent era. Triage in 30s with `npx patient-zero`, block malicious installs before postinstall runs, or drop into CI as a GitHub Action. Covers npm + Python + MCP agent configs. Free, MIT, no signup, no telemetry.
-
cast
Minimal terminal coding agent with OpenAI-compatible routing. Works with any provider — OpenRouter, Ollama, vLLM, LiteLLM, or your own.
-
veilbrowser
Stealth browser for AI agents — real Chrome over raw CDP, no Playwright/Puppeteer. TypeScript + MCP-native. Passes sannysoft 57/57, bypasses Cloudflare.
-
hspace
Ship to one, not to all. Targeted sharing for AI-built HTML/Markdown: one link + password, view receipts, instant revoke, per-recipient passwords, versioned. Open source, edge-native.
-
toksave
A zero-config CLI that securely installs and wires token-saving tools into AI coding agents.
-
Obsidian-vault-api
Obsidian plugin that exposes your vault as a local MCP server for Claude Desktop app
-
grounded-reasoning
Zero-token, precision-guaranteed relation-algebra verifier for LLM/agent multi-hop reasoning
-
AlfredOS
An open-source, self-hostable, multi-user, multi-persona, security-hardened agentic OS.
-
aegis
The meta-harness that brings real agentic collaboration as a first-class citizen
-
revops-skills
Automate Salesforce RevOps tasks with Claude agent skills designed for pipeline hygiene, forecast reconciliation, and deal pressure testing.
-
exomem
Self-hosted MCP server that makes your Obsidian/markdown vault searchable — text, PDFs, Office docs, images, audio — from any MCP client. Hybrid retrieval over a typed, governed corpus, sub-second at 50k notes; your files stay plain markdown.
-
epicurus
Self-hosted, modular, local-first personal-assistant platform — an AI agent plus pluggable integration modules.
-
akashic-aurora
Memory for AI agents that learns what actually helped: lessons injected at the moment of action, credited by outcome, challenged by counter-evidence. Local-first, multi-agent, test-gated.
-
VecMem
Manage LLM agent memory with a resource-aware dual-tier system that uses HNSW indexing to balance short-term context and long-term knowledge retention.
-
bike4mind
The open-core AI workbench — notebooks, agents, RAG, voice, and images across any model: OpenAI, Anthropic, Google, xAI, or local via Ollama/vLLM. BSL 1.1, auto-converting to Apache-2.0 on a two-year clock. Your AI keeps running when theirs doesn't.
-
trusty-tools
Unified Rust workspace for the trusty-* AI developer-tooling ecosystem: hybrid code search, memory palace, code analysis, PR review, and the MPM multi-agent platform — MCP servers, daemons & CLIs.
-
gnosis
Gnosis is a Greek noun meaning "knowledge" or "awareness"
-
busabase
⚡ The approval-first, open-source database & knowledge base for AI agents — review & approve every change before it's trusted. Local-first, self-hostable Airtable/Notion alternative.
-
omadia
Self-hostable agentic OS. Build, run & audit multi-agent AI teams from signed plugins. Bring your own LLM key, own all your data, EU/GDPR-ready.
-
kalshi-mcp-server
Self-hosted MCP server for Kalshi prediction markets. Native RSA-PSS auth, token-bucket rate limiting, demo/prod safety controls. Designed to be forked and deployed.
-
Synaptic
Auditable code intelligence for AI agents - map dependencies, predict change impact, select the right tests, and verify refactors before they ship.
-
cyborg
Open-source collaborative AI agent platform. Humans and AI agents on different machines work together in shared workspaces — agents run locally on your own daemon, self-hosted, no cloud execution of your code.
-
fireflyiii-mcp
Connect any MCP client to Firefly III — 140 tools via stdio (PAT) or HTTP (OAuth
-
symaira-ingest
Document ingestion + OCR core for the Symaira ecosystem.
-
sportsdata-agents
Free, open-source agentic sports-data workbench — an agent team over live odds + stats: arbitrage & value detection, backtesting with CLV, monitors, racing, fantasy. BYO model key.
-
opencode-browser-automator
Autonomous Web Agent Toolkit 2026 - AI Browser Automation for Testing & Scraping
-
peacock
Stateless Rust renderer and MCP-App host for agent-authored, agent-consumed data reports — turns an escurel report skill into an A2UI + Vega-Lite artifact for MCP hosts, chat, and agents, with view state synced to the conversation.
-
godot-game-studio-agent
Automate game production in Godot, Unity, and Unreal with a studio-style agent that manages workflows, project documentation, and engine-specific quality checks.
-
atomic-agents-stack
AI agents that live in your folder, not someone else's database. Vault-native, MIT-licensed. 21 spec docs + Python reference implementation.
-
onyx-mcp
Proof of Agent Execution — the neutral trust layer issuing portable, signed execution credentials for AI agents (x402 · MCP · ERC-8004).
-
albu-mcp
MCP server for AlbumentationsX image augmentation workflows
-
distil
Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior across 7 domains. Works with any SDK.
-
android-agent
Control Android devices through ADB with this Python automation framework for task execution and phone farm scaling.
-
marketnow
Trust layer for agent commerce. 8,560 MCP skills, Sentinel L1.5 security audits, AP2 mandates, x402 payments. Open source MIT.
-
gachi-data-api
Deep, obscure Japanese data you won't find anywhere else — stations, accessibility, vacancy, hazards. Hand-verified, English-first, built for AI agents.
-
tiro
The open-source reading OS that keeps everything you read as markdown files on your machine — with a frontier-model research assistant, and your own agents, on top.
-
agent-config
Universal AI Agent OS — audited skills, governance rules, replayable state. One contract, every host agent.
-
atlas-context-router-rs
Graph-aware code context for CLI and MCP workflows
-
kimi-K2.6
Build full-stack applications with an autonomous IDE using an agent swarm architecture powered by the Kimi 2.6 model.
-
gaia-skill-tree
Gaia is a living, open registry of every AI agent skill in existence — structured as a leveling skill graph. Basic skills combine into Extras, Extra Skills evolve into Ultimates. Fork it, extend it, PR a fusion. The complete skill frontier of AI agents, mapped and growing.
-
agent-rules-kit
Diagnose AI agent instruction files like AGENTS.md, CLAUDE.md, and Cursor rules using this local read-only Python CLI.
-
unity-kiss-mcp
MCP server for controlling Unity Editor from Claude Code. TCP bridge, 98 tools, plugin system, token-optimized, in-editor chat.
-
pi-shazam
A native codebase awareness extension for the Pi coding agent — 7 structural analysis tools (overview, lookup, impact, verify, changes, format, rename) powered by tree-sitter & LSP. Also available as MCP server for any AI agent.
-
clawseccheck
🦞 Free, local, read-only security self-audit for your own OpenClaw AI-agent setup. Scores it A–F, surfaces the urgent holes, emits copy-paste fixes. Zero deps, no network, no API key — your data never leaves your machine.
-
glyph
Glyph is a workbench for composing the forms intelligence takes today — and discovering the language it will speak tomorrow.
-
shotik
Beautiful open-source screenshot tool for Windows with a built-in MCP server - let Claude see your screen
-
roboclaw-reports
AI Robotics Demos 2026 - VLM Policies, MCP Skills & HTML Reports
-
ai-engineering-production
AI Engineering Roadmap 2026 🚀 | Build & Deploy AI Apps from Scratch
-
indexa
The local context engine for AI. Summarizes every file, rolls folders up into whole-project context, and serves any AI tool (Claude Code, Cursor, local models) a ranked slice over CLI, web & MCP. Local-first, Apache-2.0.
-
index
Map one unfamiliar repo into a self-contained, verified wiki, or a whole workspace into a two-layer atlas of repos, docs, and dependency graphs. Built from file:line evidence, not guesses. Offline, deterministic, zero runtime dependencies, with a native MCP bridge.
-
open-mind
Understand any unfamiliar codebase in an afternoon — a local, deterministic, source-traceable knowledge index (glossary · graphs · code search) that never invents what isn't there.
-
thesmos-governance
AI governance CLI, GitHub Action, VS Code extension & MCP server — 1,075 rules for Claude, Cursor, Copilot, Gemini, Codex.
-
hopbox
A compute-box substrate: one daemon turns a host into a fleet of isolated Firecracker microVMs reached over plain SSH — for humans and AIs. Your SSH key is your identity; the username is the box spec.
-
polygate
An MCP server that lets any LLM research and trade Polymarket. Point Claude, Cursor, or VS Code at it and your agent can read markets, prices, and your account — and place real trades. Optional REST gateway for algorithmic bots.
-
memory-seed
Portable local memory system and MCP search tooling for file-reading AI coding agents.
-
open-cowork
Open Cowork is a desktop, cloud and gateway workspace for OpenCode.
-
firebat
firebat
-
metagraphed
Operational metadata, health, schemas, and public interface discovery for Bittensor subnets.
-
skills
Automate literature reviews with research skills for fetching arXiv papers, extracting technical details, and tracking citations for agent workflows.
-
wigolo
The go-to web for your agent!