shodan-mcp

shodan-mcp is an MCP (Model Context Protocol) server that exposes Shodan capabilities as 20 callable tools for AI agents. It supports passive reconnaissance and vulnerability intelligence (CVE/CPE) and provides 4 tools that work without a Shodan API key.

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ Security mcp shodan osint cybersecurity vulnerability-intelligence reconnaissance cve cpe vscode claude
⚙ Agent Friendliness
66
/ 100
Can an agent use this?
🔒 Security
64
/ 100
Is it safe for agents?
⚡ Reliability
28
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
85
Documentation
85
Error Messages
0
Auth Simplicity
90
Rate Limits
40

🔒 Security

TLS Enforcement
70
Auth Strength
70
Scope Granularity
30
Dep. Hygiene
60
Secret Handling
90

Security controls are described at a high level: input validation, injection prevention (blocking forbidden characters), no shell execution (httpx), and API key protection (keys not exposed in error messages/logs). TLS enforcement and dependency vulnerability posture are not verifiable from the provided text; scope granularity is not described (likely all-access for the API key).

⚡ Reliability

Uptime/SLA
0
Version Stability
40
Breaking Changes
20
Error Recovery
50
AF Security Reliability

Best When

You need IDE/agent-integrated passive intelligence from Shodan (especially CVE/CPE and pre-indexed device search) with validated inputs and structured outputs.

Avoid When

You cannot obtain/secure appropriate Shodan API credentials, or you lack authorization/compliance for OSINT research on targets.

Use Cases

  • Passive OSINT for internet-facing services and exposed devices
  • CVE/CPE lookup and CVE search enriched with vulnerability-related metadata
  • DNS resolution and reverse DNS for observed hosts/domains
  • Device search using Shodan query language for reconnaissance workflows
  • Honeypot likelihood scoring to prioritize targets for further investigation

Not For

  • Automated targeting or exploitation of systems (the tool is passive but can facilitate recon that could be misused)
  • Scanning networks you do not have authorization to investigate
  • Replacing a full vulnerability management workflow (this is research/intelligence)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: SHODAN_API_KEY (environment variable)
OAuth: No Scopes: No

README indicates authorization is required for the majority of tools; 4 tools work without an API key. No OAuth or fine-grained scopes are described.

Pricing

Free tier: Yes
Requires CC: No

Pricing depends on Shodan API plan/credits; specific plan costs and rate/credit units are not provided in the package docs.

Agent Metadata

Pagination
none
Idempotent
True
Retry Guidance
Not documented

Known Gotchas

  • Some tools require a Shodan API key; agents should handle failures when a key is missing.
  • API-credit consumption may occur for key-required tools (search/recon), even though operations are passive.
  • Results depend on Shodan’s indexing freshness; CVE/CPE mappings may be incomplete for newly disclosed products.
  • In MCP usage via Docker, passing environment variables correctly (SHODAN_API_KEY) is required for key-based tools.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for shodan-mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered