AgentSec MCP
This connects Claude to x402's security intelligence platform on Base blockchain for threat research workflows. You get CVE vulnerability lookups, IP reputation checks, and secret scanning capabilities without leaving your chat context. Reach for this when you're investigating security issues and need to quickly pivot between checking vulnerability databases, validating whether an IP is sketchy, or scanning code snippets for leaked credentials. The streamable HTTP transport means it runs as a web service rather than a local process, so there's no installation beyond adding the endpoint to your MCP config.
- tools
- 3
- transport
- HTTP
- last updated
- Apr 21, 2026
Install
From registry metadata$ npx add-mcp https://agentsec-mcp.agentsec-mcp.workers.dev/mcp --name agentsec-mcpRun in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.
Review the command, arguments and environment values before installing. MCP servers run with your local permissions.
Other ways
Claude Code
$ claude mcp add --transport http agentsec-mcp https://agentsec-mcp.agentsec-mcp.workers.dev/mcpRun in your terminal. Add --scope user to make it available in every project.
Tools
Verified live · 3 toolsVerified live against the running server on Nov 6, 2026.
cve_lookupLook up known CVE vulnerabilities for an npm package+version or a specific CVE ID. Returns CVSS scores, descriptions, and fix versions from NVD and OSV. Results are cached for 10 minutes. Costs $0.01 USDC per call.
Look up known CVE vulnerabilities for an npm package+version or a specific CVE ID. Returns CVSS scores, descriptions, and fix versions from NVD and OSV. Results are cached for 10 minutes. Costs $0.01 USDC per call.
No parameters. Call it with no arguments.
reputation_checkCheck the reputation of an IP address or domain using AbuseIPDB and VirusTotal. Returns a security verdict (malicious/suspicious/unknown/clean) with confidence signals. Verdict is conservative: incomplete data returns 'unknown' never 'clean'. Results are cached for 10 minutes....
Check the reputation of an IP address or domain using AbuseIPDB and VirusTotal. Returns a security verdict (malicious/suspicious/unknown/clean) with confidence signals. Verdict is conservative: incomplete data returns 'unknown' never 'clean'. Results are cached for 10 minutes....
No parameters. Call it with no arguments.
secret_scanScan text content for hardcoded secrets, API keys, and credentials using 20 pre-compiled patterns. Privacy guarantee: Input text is NEVER logged, cached, stored, or forwarded. Only findings_count and finding offsets (not matched values) are returned. Detected pattern types inc...
Scan text content for hardcoded secrets, API keys, and credentials using 20 pre-compiled patterns. Privacy guarantee: Input text is NEVER logged, cached, stored, or forwarded. Only findings_count and finding offsets (not matched values) are returned. Detected pattern types inc...
No parameters. Call it with no arguments.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Category
- Security & Pentesting
- Transport
- HTTP
- Registry
- MCP registry, active
- Tools verified
- Nov 6, 2026
Related Security & Pentesting MCP servers
View all
Shadowgate Mcpjosephibra/shadowgate-mcpSecurity firewall for AI agents — scans MCP calls for injection, secrets, and risks.0stars
Mcp Servermiddlebrick/mcp-serverScan APIs for OWASP Top 10, LLM, and GraphQL security vulnerabilities.0stars
SecurityScansecurityscan-api/securityscan-apiScan GitHub-hosted AI skills for vulnerabilities: prompt injection, malware, OWASP LLM Top 10.0stars
mcpwallbehrensd/mcp-firewalliptables for MCP — blocks dangerous tool calls, scans for secrets, logs everything.0stars
PromptScancorporatelad/prompt-injection-firewallPrompt injection detection API for AI agents. Scan untrusted text before passing it to an LLM.0stars
Microsoft SQL Serverrichardhan/mssql_mcp_serverProvides MCP access to Microsoft SQL Server databases with multi-method authentication and SQL operations via Claude Desktop.345stars