MCP servers · over the network
Remote MCP servers
2,120 MCP servers list a remote transport, streamable HTTP or SSE. A remote server needs no install, but what you send it leaves your machine. Our audit reads the source in the repository; it cannot see what a hosted deployment runs.
Cite
Cite this page
ModelsAtlas. “Remote MCP servers”. Retrieved 29 Oct 2026. https://modelsatlas.com/mcp/remote/page/86
Verdicts · 2,120 servers
Transports
- stdio, runs locally1,435
- Streamable HTTP, remote1,960
- SSE, legacy remote423
A server can list more than one transport.
Tool risk
563
servers expose at least one destructive tool: delete, overwrite or run. The median server with a readable tool list exposes 12 tools.
Servers with no destructive tools →2,120 servers
2,041–2,064 of 2,120 · ranked by trust score, then stars
Faxbot
DMontgomery40/Faxbot
Self-hosted, open source, fax-sending API. HIPAA compliant. This fax API includes MCP (Model Context Protocol) support for AI assistant integration.
Better Auth
better-auth/better-auth
The most comprehensive authentication framework
TouchDesigner
8beeeaaat/touchdesigner-mcp
MCP server for TouchDesigner
MemClaw
caura-ai/caura-memclaw
Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
Open Computer Use
yambr/open-computer-use
ARCHIVED — superseded by Wide Moat
Travel Planner
gongrzhe/travel-planner-mcp-server
HealthClaw Guardrails
aks129/healthclawguardrails
Open-source guardrails between AI agents and FHIR clinical data — PHI redaction, immutable audit, step-up auth, tenant isolation. MCP server + OpenAI/Gemini adapters. A healthclaw.io project.
MCP Any
mcpany/core
artifact-site
lexmount/artifact-site
A self-hosted home for your team’s AI-generated pages and documents. Publish HTML, build folders, ZIPs and PDFs as sandboxed, versioned links. CLI + remote MCP for AI agents.
who2be
luetzey/who2be
Self-hosted hub for AI agent configuration: versioned personas, playbooks and knowledge with a mandatory review step, served to agents over MCP. Agent configuration you review — not behavior you hope for.
Genkit
genkit-ai/genkit
Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google
SoloMD
zhitongblog/solomd
A markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.
caura
caura-ai/caura
Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
One MCP
1mcp-app/agent
A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.
Thoughtbox
kastalien-research/thoughtbox
Thoughtbox is an intention ledger for agents. Evaluate AI's decisions against its decision-making.
jazz-ai
lvndry/jazz
One agent. Every surface. Your rules.
unitares
cirwel/unitares
Accountability infrastructure for long-running AI agents. Self-hosted MCP server: identity, claims and evidence, review, outcomes, and reconstruction across agent runtimes.
token-enhancer
Footshaped-friction742/token-enhancer
Reduce web pages to clean text before they reach your AI agent’s context window, saving tokens and cutting noise
N8n
czlonkowski/n8n-mcp
A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you
Databuddy
databuddy-analytics/Databuddy
Open-source product analytics for startups: track visitors, events, funnels, and goals without cookies, and ask Databunny, the built-in AI analyst. Uptime, feature flags, and short links in the same dashboard.
AgenticMail
agenticmail/agenticmail
Email, SMS & phone-call infrastructure for AI agents — send and receive real email and text messages, and place agent-driven outbound voice calls, all programmatically
jev-judge-mcp
PyModel/jev-judge-mcp
Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate.
Digital Twins
pome-sh/digital-twins
Test mode for your integrations, built for the way agents build
agent-bounties
NSPG13/agent-bounties
Open-source bounty network where AI agents post, fund, claim, solve, verify, and get paid for digital work.
Other risk hubs
By job
Questions
What counts as a remote MCP server?
Do remote servers also run locally?
Are remote servers safe?
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What counts as a remote MCP server?
- Do remote servers also run locally?
- Are remote servers safe?