43,019 servers you connect by URL over streamable HTTP. Nothing to install or keep running on your machine.
A remote MCP server runs on someone else's infrastructure and your client connects to it by URL over streamable HTTP (older servers use SSE). Sign-in usually happens through OAuth in the browser instead of an API key in a config file.
Local servers run as a process on your machine and can reach your files and private network. Remote servers need no runtime and update themselves, but your data goes to the provider. Pick remote for SaaS products, local for files, databases on your network and anything offline.
In Claude Code run claude mcp add --transport http <name> <url>. In Cursor and Gemini CLI add the URL under mcpServers; in VS Code add it under servers with "type": "http". Each server page has the exact config.
Scans and investigates AI supply chains by mapping agents, MCP servers, packages, and their potential reach to identify vulnerabilities.
$claude mcp add agent-bom -- uvx agent-bom
Enables AI clients to securely access metadata management capabilities including search, lineage, data quality, and governance through OAuth 2.0.
$claude mcp add --transport http openmetadata-mcp https://{openmetadata_host}/mcp
Puts authorization in front of AI agent HTTP actions, forwarding only requests approved by the Decionis authority and holding or blocking the rest.
$claude mcp add agent-safe-pipeline -- npx -y @decionis/mcp
Scans domains for DNS, email security, and deliverability issues, checks SPF/DKIM/DMARC/DNSSEC, and generates fix records.
$claude mcp add intodns-mcp-server -- npx -y intodns-mcp
Evaluates AI agent proposals against thirteen constitutional floors to provide governed verdicts and auditable receipts before execution.
$claude mcp add arifos-mcp -- uvx arifos
Gives AI agents evidence-backed crypto data on prices, wallets, DeFi, token security, DEX flows, and NFTs through one hosted connection.
$claude mcp add hive-sdk -- npx -y hive-intelligence
Checks and signs every AI agent tool call before it runs, holds risky calls for human approval, and exports tamper-evident records anyone can verify offline.
$claude mcp add --transport http tracekit https://{tracekit_gateway}/mcp
Gives AI clients persistent memory across sessions, enforces saved rules before actions, and reviews finished work against intent.
$claude mcp add cogmemai-mcp -- npx -y cogmemai-mcp
Lets an AI agent recall and calibrate policy-compliant tool-call arguments to prevent unauthorized or incorrect tool execution.
$claude mcp add achromat-mcp-server -- npx -y @achromat-ai/mcp-server
Lets AI clients securely access and manage FHIR healthcare data stored in Medplum.
$claude mcp add --transport http medplum https://api.medplum.com/mcp/stream
Runs 30+ domain security checks from an AI client, covering phishing links, exposed admin pages, DNS, SSL, email auth and infrastructure history.
$claude mcp add dechonet-mcp -- npx -y dechonet-mcp
Performs real-time token risk assessments by simulating trades on blockchain forks to detect honeypots and malicious contract functions.
$claude mcp add chaink9-mcp -- npx -y chaink9-mcp
Provides AI agents with a tamper-evident, publicly logged record of actions and events with verifiable offline proofs.
$claude mcp add fabric-verify-mcp -- npx -y @augmentev/fabric-verify-mcp
Detect malicious or vulnerable npm packages through registry searches, OSV.dev lookups, and GitHub advisory checks.
$claude mcp add --transport http npmscan-mcp-plugin https://npmscan.com/api/mcp
Enables AI clients to perform CVE, KEV, EPSS, and SBOM lookups with internet-exposure footprints derived from Shodan data.
$claude mcp add echelongraph-mcp -- npx -y echelongraph-mcp
Enforces guardrails for LLM outputs by providing safety and quality verdicts, recommended actions, and transaction simulation.
$claude mcp add overwing-mcp -- npx -y overwing-mcp
Helio acts as an MCP proxy that enforces governance policies, spend limits, and approval workflows for AI agents without changing their code.
$claude mcp add helio -- npx -y @gethelio/proxy
Allows AI agents to fetch TOTP codes for shared 2FA accounts to complete sign-in processes automatically.
$claude mcp add mcp-server -- npx -y @authn8/mcp-server
Gives AI agents their own email inbox to send, receive, reply to, and route messages for human approval.
$claude mcp add --transport http mcp-server https://api.e2a.dev/mcp
Provides AI agents with email addresses, encrypted credential storage, and behavioral trust scoring via MCP tools.
$claude mcp add agentlair -- npx -y @agentlair/mcp