ShodanSAFE
MCP server for Shodan — host/network recon, CVE and exploit lookup, InternetDB, and persistent alerts (34 tools).
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol (MCP) server that provides access to Shodan API functionality and CVE database, allowing AI assistants to query information about internet-connected devices, services, and vulnerabilities.
Features
Network Intelligence
- Host Information: Get detailed information about specific IP addresses
- Search Capabilities: Search Shodan's database for devices and services
- Network Scanning: Scan network ranges (CIDR notation) for devices
- SSL Certificate Information: Get SSL certificate details for domains
- IoT Device Search: Find specific types of IoT devices
Vulnerability Intelligence
- CVE Lookup: Get detailed information about specific vulnerabilities
- Vulnerability Search: Search CVEs with advanced filters (product, KEV status, EPSS scores)
- CPE Information: Get Common Platform Enumeration data for products
- Latest Vulnerabilities: Access newest CVEs and Known Exploited Vulnerabilities
- Exploit Prediction: Get CVEs sorted by EPSS exploit prediction scores
- Exploit Search: Search Shodan's Exploits database for CVE-linked exploits
- InternetDB Lookup: Free, no-API-key host lookup (open ports, hostnames, CPEs, vulns, tags)
Network Monitoring
- Network Alerts: Create, list, inspect, and delete persistent alerts that monitor IPs/ranges for changes
- Notifiers: List available notifier providers and manage notifiers (Slack, email, webhook, etc.) that alerts can send events to
Installation
- Clone the repository:
git clone https://github.com/Cyreslab-AI/shodan-mcp-server.git cd shodan-mcp-server
- Install dependencies:
npm install
- Build the server:
npm run build
- Set up your Shodan API key:
export SHODAN_API_KEY="your-api-key-here"
- Start the server:
npm start
MCP Integration
This server can be inte
ba329813c5dfOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-shodan-server --env SHODAN_API_KEY=${SHODAN_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"mcp-shodan-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"SHODAN_API_KEY": "${SHODAN_API_KEY}"
}
}
}
}Exposed tools (34)
30 read · 2 write · 2 destructive. Blast radius: 2 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
count_exploits | read | Get the count of exploits matching a search query without returning the full exploit records |
create_alert | write | Create a persistent Shodan network alert that monitors one or more IPs/ranges and reports changes over time |
create_notifier | write | Create a new Shodan notifier (e.g. Slack, email, webhook) that network alerts can send events to |
delete_alert | destructive | Permanently delete a Shodan network alert by ID. This stops monitoring and cannot be undone. |
delete_notifier | destructive | Permanently delete a Shodan notifier by ID. This cannot be undone. |
dns_lookup | read | Resolve hostnames to IP addresses using DNS lookup |
get_account_profile | read | Get account profile information including membership status and credits |
get_alert | read | Get details about a specific Shodan network alert by ID |
get_api_info | read | Get information about your API plan including credits and limits |
get_cpes | read | Get Common Platform Enumeration (CPE) information for products |
get_cve_info | read | Get detailed information about a specific CVE |
get_cves_by_epss | read | Get CVEs sorted by EPSS score (Exploit Prediction Scoring System) |
get_domain_info | read | Get comprehensive domain information including subdomains and DNS records |
get_host_count | read | Get the count of hosts matching a search query without consuming query credits |
get_host_info | read | Get detailed information about a specific IP address |
get_internetdb_host | read | Get a free, lightweight lookup of an IP address using Shodan |
get_kev_cves | read | Get Known Exploited Vulnerabilities (KEV) from CISA |
get_my_ip | read | Get your current IP address as seen from the Internet |
get_newest_cves | read | Get the newest vulnerabilities from the CVE database |
get_ssl_info | read | Get SSL certificate information for a domain |
list_alerts | read | List all configured Shodan network alerts on the account |
list_notifier_providers | read | List available Shodan notifier providers (e.g. slack, email, webhook, telegram) and the arguments each one requires |
list_notifiers | read | List all configured Shodan notifiers on the account |
list_ports | read | List all ports that Shodan crawls on the Internet |
list_protocols | read | List all protocols that can be used when performing on-demand Internet scans |
list_search_facets | read | List all available search facets that can be used with Shodan queries |
list_search_filters | read | List all available search filters that can be used in Shodan queries |
parse_search_tokens | read | Parse a search query to understand which filters and parameters are being used |
reverse_dns_lookup | read | Get hostnames for IP addresses using reverse DNS lookup |
scan_network_range | read | Scan a network range (CIDR notation) for devices |
search_cves | read | Search for vulnerabilities with various filters |
search_exploits | read | Search Shodan |
search_iot_devices | read | Search for specific types of IoT devices |
search_shodan | read | Search Shodan |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (6 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
delete_alert, delete_notifier
@modelcontextprotocol/server, axios, zod, @types/node, typescript
Gates applied: no_behavioural_pass.
ba329813c5dffull audit observations/trust-audit/mcp-server/cyreslab-ai__shodan-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | ba329813c5df | SAFE | B | 89 | first audit |
Questions
What is the Shodan MCP server?
MCP server for Shodan — host/network recon, CVE and exploit lookup, InternetDB, and persistent alerts (34 tools).
What tools does Shodan expose?
34 in total: 30 read-only, 2 that write, and 2 that can delete or overwrite (delete_alert, delete_notifier). Every one is listed on this page with its risk.
Is Shodan safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 2 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Shodan need?
It reads SHODAN_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Shodan run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as mcp-shodan-server at 0.2.0.
How current is this page?
The grade is for one exact copy of the source (ba329813c5df), read on 2026-10-08. The repository is watched and re-audited when it changes.