pulsemcp verified Safe content atomic mcp-remote

AI Infrastructure Agent (AWS)

AI Infrastructure Agent by VersusControl that provides autonomous AWS infrastructure management through natural language processing and state-aware decision making. Built with Go using the AWS SDK v2, langchaingo for multi-LLM support (OpenAI, Google AI, Anthropic), and mark3labs/mcp-go for Model Context Protocol integration, the implementation combines AI-driven infrastructure planning with real-time AWS resource discovery, conflict detection, and dependency graph analysis. The agent maintains persistent infrastructure state, correlates managed resources with discovered AWS resources, and executes step-by-step deployment plans through granular MCP tools covering EC2, VPC, Auto Scaling, Load Balancers, RDS, and security groups. Designed for DevOps teams and infrastructure engineers who need conversational infrastructure management with built-in safety through dry-run modes, conflict resolution, and comprehensive state tracking across complex AWS environments.

Cognium trust score

80%

Tier

Verified

Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.

Scan details: Circle-IR · 2026-09-19 · Appeal

View full trust & usage report →

Metadata

Version: 1.0.0
Skill type: atomic
Execution layer: mcp-remote
Category: cloud-infra
Source: PulseMCP
Repository: github.com/versuscontrol/ai-infrastructure-agent
Author type: human
Last scanned: 2026-09-19
Updated: 2026-09-19

View source Find related skills

MCP

Resolve AI Infrastructure Agent (AWS) from your agent

Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.

One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.

claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp

Swap --scope user for --scope project to commit it to .mcp.json.

Your client Same endpoint everywhere; only the config key differs. The full list is in the descriptor.

Claude Desktop · Settings → Connectors → Add custom connector

https://api.skillsregistry.net/mcp

Paste the URL as the connector endpoint. No authentication.

ChatGPT · Settings → Connectors → Create (developer mode) → MCP server URL

https://api.skillsregistry.net/mcp

Authentication: none. Works in chat and deep research — the server exposes the connector search and fetch tools.

Codex CLI · ~/.codex/config.toml

[mcp_servers.skillsregistry]
url = "https://api.skillsregistry.net/mcp"