mlab.sh
Threat intelligence: enrich IOCs (IP, domain, URL, hash), search CVEs and actors, scan SBOMs.
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
claude mcp add --transport http mlab-sh 'https://mlab.sh/mcp' --header 'Authorization: <Bearer mcp_xxx static token. Leave empty if your client supports OAuth 2.1 (recommended): the server advertises its authorization server at /.well-known/oauth-authorization-server.>'{
"mcpServers": {
"mlab-sh": {
"type": "http",
"url": "https://mlab.sh/mcp",
"headers": {
"Authorization": "<Bearer mcp_xxx static token. Leave empty if your client supports OAuth 2.1 (recommended): the server advertises its authorization server at /.well-known/oauth-authorization-server.>"
}
}
}
}claude mcp add --transport sse mlab-sh 'https://mlab.sh/mcp'{
"mcpServers": {
"mlab-sh": {
"type": "sse",
"url": "https://mlab.sh/mcp"
}
}
}Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
Contents
mlab.sh MCP server
Public metadata and connection guide for the remote MCP server at https://mlab.sh/mcp, a threat intelligence server for SOC and DFIR work.
This repo is the registry listing and the documentation. It is not the server source: the server runs inside the mlab.sh backend and is closed source.
Connect
Endpoint: https://mlab.sh/mcp (Streamable HTTP via POST, SSE via GET).
Claude.ai
Settings > Connectors > Add custom connector, then paste the URL. OAuth runs in the browser, no token to copy.
https://mlab.sh/mcpClaude Desktop
claude_desktop_config.json:
{
"mcpServers": {
"mlab": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mlab.sh/mcp",
"--header",
"Authorization: Bearer mcp_xxx"
]
}
}
}Drop the --header pair to use OAuth instead of a static token.
Cursor
~/.cursor/mcp.json:
{
"mcpServers": {
"mlab": {
"url": "https://mlab.sh/mcp",
"headers": {
"Authorization": "Bearer mcp_xxx"
}
}
}
}VS Code
.vscode/mcp.json:
{
"servers": {
"mlab": {
"type": "http",
"url": "https://mlab.sh/mcp",
"headers": {
"Authorization": "Bearer mcp_xxx"
}
}
}
}curl
curl -sS -X POST https://mlab.sh/mcp \
-H "Authorization: Bearer mcp_xxx" \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"curl","version":"1.0.0"}}}'Ready to paste versions of these four configs live in examples/.
Officially supported clients are Claude.ai and Claude Desktop. Other MCP clients (Cursor, VS Code, Windsurf and friends) work but are best effort.
Tools
IOC enrichment
| Tool | Purpose |
|---|---|
detect_ioc | Auto detect the IOC type of a value and return relevant threat intel |
scan_ip | Threat intel for an IPv4 or IPv6 address |
scan_url | Static analysis of a URL without visiting it |
scan_hash | File hash lookup (MD5, SHA1, SHA256) in CIRCL hashlookup |
scan_crypto | Threat intel for a blockchain address: labels, sanctions, risk score, 18 chains |
scan_email | Offline style analysis of an email address |
scan_phone | Offline style analysis of a phone number |
scan_mac | Offline style analysis of a MAC address |
smishing_risk | Score an SMS for smishing |
Vulnerabilities and actors
| Tool | Purpose |
|---|---|
cve_search | Search CVEs |
cve_detail | Full CVE record |
actors_by_cve | Threat actors known to exploit a CVE |
search_actors | Search threat actors |
get_actor | Full threat actor profile |
Scanning
| Tool | Purpose |
|---|---|
start_domain_scan | Launch a domain scan: DNS, subdomains, SSL, security.txt, robots.txt |
get_domain_scan_results | Poll the results of a domain scan |
scan_bash | Static analysis of an inline shell script |
scan_sbom | Scan a dependency lockfile or SBOM for known CVEs |
Account
| Tool | Purpose |
|---|---|
get_scan_history | Past scans for the account |
get_scan_limits | Current quotas and remaining scans |
get_account_info | Account details |
add_bookmark | Bookmark an IOC |
remove_bookmark | Remove a bookmarked IOC |
get_bookmarks | List bookmarked IOCs |
hello_world | Connectivity check |
Authentication
OAuth 2.1 is the recommended path: authorization code with PKCE S256, dynamic client registration, CIMD supported. The server advertises its metadata at https://mlab.sh/.well-known/oauth-authorization-server, so a compliant client only needs the endpoint URL.
If your client does not speak OAuth, create a static token in Account > Settings > MCP Tokens and send it as Authorization: Bearer mcp_xxx.
Full details: https://doc.mlab.sh/docs/mlab.sh/integrations/mcp
Rate limits and quotas
Limits follow your mlab.sh account plan. Call get_scan_limits to read the quotas and remaining budget that apply to your account.
Registry
Published to the official MCP Registry as sh.mlab/mcp.
https://registry.modelcontextprotocol.io/v0.1/servers?search=sh.mlab
Other public servers
https://news.mlab.sh/mcp is a separate, unauthenticated, read only MCP server exposing a cyber news index. It is not published from this repo.
Security
Report vulnerabilities to security@mlab.sh. See https://mlab.sh/security.txt and SECURITY.md.
License
MIT, see LICENSE.
Frequently asked questions
What is mlab.sh?
Threat intelligence: enrich IOCs (IP, domain, URL, hash), search CVEs and actors, scan SBOMs.
How do I install mlab.sh?
It runs as a remote server. In Claude Code: claude mcp add --transport http mlab-sh 'https://mlab.sh/mcp' --header 'Authorization: <Bearer mcp_xxx static token. Leave empty if your client supports OAuth 2.1 (recommended): the server advertises its authorization server at /.well-known/oauth-authorization-server.>'. For other clients, paste the JSON configuration from this page into their MCP settings.
Does mlab.sh need an API key?
Yes. It expects Authorization, which you set in its configuration.
Is mlab.sh open source?
Yes. Its code is on GitHub under the MIT license.
Who maintains mlab.sh?
It is published by mlab-sh. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.