Is io.github.theanshsonkar/emfirge safe to use?

io.github.theanshsonkar/emfirge has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.

How do I install io.github.theanshsonkar/emfirge?

io.github.theanshsonkar/emfirge can be installed by cloning its GitHub repository and following the setup instructions in the README.

What AI clients work with io.github.theanshsonkar/emfirge?

io.github.theanshsonkar/emfirge is compatible with claude-desktop, cursor, claude-code. It uses stdio transport.

io.github.theanshsonkar/emfirge

Privacy-first AWS security in your AI: attack paths & fix simulation, IDs never sent to the LLM.

GitHub

No known CVEs

No license

Maintenance unknown

No commit data

Works with most clients

Transport: stdio

0 tools

Token cost not measured

Edit this pageView history

Cloud

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "io-github-theanshsonkar-emfirge": {
      "command": "<see-readme>",
      "args": []
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/io-github-theanshsonkar-emfirge)](https://mcppedia.org/s/io-github-theanshsonkar-emfirge)

Read me

What io.github.theanshsonkar/emfirge does

Privacy-first AWS security in your AI: attack paths & fix simulation, IDs never sent to the LLM.

Test This Server

No automated test available for this server. Check the GitHub README for setup instructions.

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

0/100across 5 weighted dimensions

How we score →

0255075100

−100

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

No package registry to scan.

Help improve this page

This server is missing a description. Tools and install config are also missing.If you've used it, help the community.

Add information

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is io.github.theanshsonkar/emfirge safe to use?: io.github.theanshsonkar/emfirge has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.
How do I install io.github.theanshsonkar/emfirge?: io.github.theanshsonkar/emfirge can be installed by cloning its GitHub repository and following the setup instructions in the README.
What AI clients work with io.github.theanshsonkar/emfirge?: io.github.theanshsonkar/emfirge is compatible with claude-desktop, cursor, claude-code. It uses stdio transport.

Similar servers

Others in cloud

View all →

Observability Mcp94

MCP Server for GCP environment for interacting with various Observability APIs.

846 10

Sink93

⚡ A Simple / Speedy / Secure Link Shortener with Analytics, 100% run on Cloudflare.

6.9k 3

Iam Policy Autopilot90

IAM Policy Autopilot is an open source static code analysis tool that helps you quickly create baseline AWS IAM policies that you can refine as your application evolves. This tool is available as a command-line utility and MCP server for use within AI coding assistants for quickly building IAM policies.

376 1

com.apideck/mcp90

Apideck Unified API MCP — 229 tools across 200+ SaaS connectors (accounting, HRIS, file storage).

14 2

MCP Security Weekly

Get CVE alerts and security updates for io.github.theanshsonkar/emfirge and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

Edit this pageView history

Cloud

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "io-github-theanshsonkar-emfirge": {
      "command": "<see-readme>",
      "args": []
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/io-github-theanshsonkar-emfirge)](https://mcppedia.org/s/io-github-theanshsonkar-emfirge)

Read me

What io.github.theanshsonkar/emfirge does

Privacy-first AWS security in your AI: attack paths & fix simulation, IDs never sent to the LLM.

Test This Server

No automated test available for this server. Check the GitHub README for setup instructions.

README

🛡️ Emfirge

Privacy-first AWS security, inside your AI.

Trace attack paths from the internet to your sensitive data, calculate blast radius, and prove fixes before you apply them — without your resource IDs ever reaching the LLM.

[Website][website] · [Source][repo] · [MCP Registry][registry] · [Privacy][privacy] · [Report an issue][issues]

[][registry] [][license]

Your AI can read your code, but it can't see your cloud. Emfirge fixes that. It scans your live AWS account, builds a graph of every resource and how they connect, then lets your assistant walk attack paths, simulate breaches, and verify fixes — all from a conversation.

The AI never guesses. Emfirge clones your infrastructure graph, applies the change, and re-runs 58 deterministic rules. Your assistant reads back what the engine proved.


🕸️ Graph-based	Maps every AWS resource and relationship — not isolated resource linting like Checkov/tfsec.
🎯 Attack paths	Weighted-Dijkstra routes from the internet to your data, ranked by exploit difficulty, not hop count.
💥 Blast radius	See exactly what an attacker reaches once they land on a resource.
🔒 Privacy-first	Resource IDs are tokenized on your machine before anything reaches the LLM. The mapping never leaves.
✅ Proven fixes	Clone the graph → apply the change → re-run every rule → diff. A real simulation, not a hunch.
📋 Compliance	CIS AWS Foundations 1.5 + SOC 2, per-control pass/fail, mapped to MITRE ATT&CK.

Install (30 seconds)

npx @emfirge/mcp install

Auto-detects and wires up Claude Desktop, Cursor, Kiro, Cline, Continue, and Codex CLI, then asks you to pick a privacy mode. Restart your client and just ask:

"Scan my AWS account, role arn:aws:iam::123456789012:role/EmfirgeReadOnly, region us-east-1"

No role yet? Say "help me set up Emfirge" — your assistant hands you a one-click CloudFormation deploy link for a read-only IAM role.

Free. 5 scans/day per AWS account. No signup. No API keys.

Try it with zero setup

Use the demo ARN — fake infrastructure, the real engine:

arn:aws:iam::194722410583:role/EmfirgeReadOnly    region: us-east-1

"Scan with arn:aws:iam::194722410583:role/EmfirgeReadOnly in us-east-1"

Want a visual graph instead? [emfirge.cloud][website] — same engine, browser UI, free during beta.

What your AI gets

Tool	What it does
`emfirge_setup_help`	Returns a clickable CloudFormation deploy link (for first-time setup).
`emfirge_scan`	Scan an AWS account — returns risk score, finding counts, and an `analysis_id`.
`emfirge_get_findings`	Full findings list for a scan, filterable by severity.
`emfirge_attack_paths`	Attack paths from the internet to internal resources, plus chokepoints.
`emfirge_verify_fix`	Simulate a fix and see the real score delta — no changes to your AWS.
`emfirge_check_compliance`	CIS AWS Foundations / SOC 2 per-control status.
`emfirge_simulate_breach`	Full kill-chain walkthrough — attack stages, blast radius, follow-up moves.

All seven tools are deterministic on the backend — no LLM calls inside the MCP path. Your host LLM (Claude / Cursor / etc.) is the only AI in the loop, and in strict mode it only ever sees tokenized data.

Privacy by default

In strict mode (the default), every AWS identifier is tokenized locally before it reaches your LLM:

What the LLM sees:    "SG_001 has SSH open → reaches S3_001"
What's on your disk:  SG_001 = sg-0a1b2c3

... [View full README on GitHub](https://github.com/theanshsonkar/emfirge#readme)

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

0/100across 5 weighted dimensions

How we score →

0255075100

−100

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

No package registry to scan.

Help improve this page

This server is missing a description. Tools and install config are also missing.If you've used it, help the community.

Add information

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is io.github.theanshsonkar/emfirge safe to use?: io.github.theanshsonkar/emfirge has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.
How do I install io.github.theanshsonkar/emfirge?: io.github.theanshsonkar/emfirge can be installed by cloning its GitHub repository and following the setup instructions in the README.
What AI clients work with io.github.theanshsonkar/emfirge?: io.github.theanshsonkar/emfirge is compatible with claude-desktop, cursor, claude-code. It uses stdio transport.