MCP Kill-Chain Research — Stage 1 (Identity ≠ Behavior)
by dev.gtfo · security · mcp-server, official-registry
Security research: MCP registries verify identity, not tool behavior. See gtfo.dev.
Tags: mcp-server, official-registry
Source: mcp-registry
About security MCP servers and Claude skills
Security MCP servers let agents scan dependencies, audit logs, check for vulnerabilities, and enforce policy guardrails. Critical for any agent that touches production.
MCP Kill-Chain Research — Stage 1 (Identity ≠ Behavior) is one of hundreds of security entries indexed on Skiln. Browse the full security category or the complete directory of Claude skills, MCP servers, agents, commands, and hooks.
Related security MCPs and skills
- ZEN SecDB by cloud.nttzen.secdb
ZEN SecDB MCP server for CVE intelligence, CVSS/EPSS scoring, advisories, SSVC, and package audits.
- Website Auditor by io.github.SpikeyCoder
AI visibility + site audits: see if ChatGPT, Perplexity, Claude & Gemini recommend a website.
- ActionProof by io.github.Burakfenerci5
Tamper-proof audit trail for AI agents. Signed receipts, offline-verifiable, zero backend.
- io.github.0xthaner/reputa by io.github.0xthaner
Ethereum wallet risk and security analysis (Reputa), with optional x402 payment.
- Mailbuttons by com.mailbuttons
Governed email for AI agents: sandbox inboxes, server-side policy gate, tamper-evident audit.
- Solana Security Standard by io.github.Copenhagen0x
Scan Solana/Anchor code against the Solana Security Standard and serve the ruleset to MCP clients.
- io.github.CSOAI-ORG/as400-bridge-mcp by io.github.CSOAI-ORG
IBM i / RPG / DB2 bridge — parse, map, govern (IBM i security / SOX).
- io.github.Bishop81/domainintel-mcp by io.github.Bishop81
Domain intelligence for agents: WHOIS, DNS, SSL/TLS, security headers, reputation, subdomains.
Frequently asked questions
How do I install MCP Kill-Chain Research — Stage 1 (Identity ≠ Behavior)?
Add the install command above to your Claude Code, Cursor, or Windsurf MCP configuration. Most servers register via npx, a local command, or a Docker image. Refer to the upstream documentation for environment variables and credential requirements.
Which clients support MCP Kill-Chain Research — Stage 1 (Identity ≠ Behavior)?
Any MCP-compatible client works: Claude Desktop, Claude Code CLI, Cursor, Windsurf, Zed, and VS Code with the official MCP extension. OpenAI Codex and GitHub Copilot increasingly support MCP via adapter bridges.
Is MCP Kill-Chain Research — Stage 1 (Identity ≠ Behavior) free?
The server itself is typically open source. Any upstream service (API keys, paid tiers, hosted infrastructure) may have its own pricing. Check the source repository for details.