# Emfirge (npm · @emfirge/mcp)

Git branch for your cloud. Understand AWS risk, prove fixes, and ship safer changes.

- Trust score: 66/100 (medium)
- Change this week: +20
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@emfirge/mcp`: 66/100 (this document), [markdown](https://verifymcp.io/servers/theanshsonkar-emfirge/emfirge-mcp.md), [page](https://verifymcp.io/servers/theanshsonkar-emfirge/emfirge-mcp)

## Channel facts

- Registry: `npm`
- Package: `@emfirge/mcp`
- Version: `0.2.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: the license (BUSL-1.1) isn't a recognized OSI-approved license.
  - Actively maintained (last published 18 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 789 tokens (~112/item across 7 items; 7 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add theanshsonkar-emfirge -- npx -y @emfirge/mcp
```

### Codex

```bash
codex mcp add theanshsonkar-emfirge -- npx -y @emfirge/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "theanshsonkar-emfirge": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@emfirge/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add theanshsonkar-emfirge --command npx --arg -y --arg @emfirge/mcp
```

### Hermes

```yaml
mcp_servers:
  theanshsonkar-emfirge:
    command: "npx"
    args: ["-y", "@emfirge/mcp"]
```

### Other

```json
{
  "mcpServers": {
    "theanshsonkar-emfirge": {
      "command": "npx",
      "args": [
        "-y",
        "@emfirge/mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 66, +3)

- [functional improvement] Stability: unverified → 0.23

### 2026-08-02 (score 63, +27)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] License: unverified → fail
- [functional improvement] Schema quality: unverified → excellent
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional] Licence: BUSL-1.1

### 2026-08-01 (score 36, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-07-31 (score 21, −7)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 28, +4)

- [security regression] Malware scan: pass → unverified
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-28 (score 24, −22)

- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (7)

### `emfirge_setup_help` (~109 tokens)

Returns the AWS CloudFormation deploy URL for setting up the read-only IAM role. Call this when the user does not have a role ARN yet, or if emfirge_scan returns 403. CRITICAL: After calling this tool, paste the deploy URL verbatim in your reply to the user. Many MCP clients (Claude Code, Codex CLI, Kiro CLI) hide tool output by default, so saying 'click the link above' will leave the user with nothing to click.

### `emfirge_scan` (~198 tokens)

Scan an AWS account for security risks. Returns risk score (0-100), finding counts, and an analysis_id for the other tools. Resource IDs are tokenized by default.

Input parameters:

- `region` (string, required): AWS region to scan (e.g., us-east-1, ap-south-1, eu-west-1, eu-central-1, ap-southeast-2). REQUIRED — there is no default. Most AWS resources are region-specific, so scanning the wrong region returns…
- `role_arn` (string, required): AWS IAM role ARN to assume. Must trust Emfirge's account with ExternalId 'aws-risk-agent'. If the user doesn't have one, call emfirge_setup_help first.

### `emfirge_get_findings` (~87 tokens)

Get the full findings list for a previous scan, optionally filtered by severity (Critical/Moderate/Low). Each finding has rule_id, issue, recommendation, attack_path, blast_radius, MITRE mapping.

Input parameters:

- `analysis_id` (string, required): Analysis ID returned by emfirge_scan
- `severity` (string): Filter findings by severity. Omit to get all.

### `emfirge_attack_paths` (~58 tokens)

Get attack paths from the internet to internal resources. Shows pivot routes from public-facing resources to crown jewels. Also returns chokepoint and orphaned resources.

Input parameters:

- `analysis_id` (string, required): Analysis ID returned by emfirge_scan

### `emfirge_verify_fix` (~133 tokens)

Simulate fixing a finding without applying changes. Clones the infra, applies the rule's mutation, rebuilds the graph, re-runs all rules, returns score delta + which other findings get resolved.

Input parameters:

- `analysis_id` (string, required): Analysis ID returned by emfirge_scan
- `resource_id` (string, required): AWS resource ID (sg-..., i-..., arn:...) OR a token from a previous response (SG_001). Tokens are auto-expanded.
- `rule_id` (string, required): Rule ID like EMFIRGE-EC2-002 (or short form EC2-002)

### `emfirge_check_compliance` (~74 tokens)

Get CIS AWS Foundations 1.5 or SOC 2 compliance status. Returns per-control pass/fail with the findings that triggered each failure.

Input parameters:

- `analysis_id` (string, required): Analysis ID returned by emfirge_scan
- `framework` (string): Framework to filter by. Omit to get all.

### `emfirge_simulate_breach` (~130 tokens)

Walk a full kill chain end-to-end against the infrastructure graph. Given a natural-language scenario or 'what if' query, returns verdict + severity + every stage of the attack (entry → pivot → impact) + blast radius + follow-up moves. Read-only — no AWS changes.

Input parameters:

- `analysis_id` (string, required): Analysis ID returned by emfirge_scan
- `query` (string, required): Natural-language query about the infra. Examples: 'what gets exposed if SG_001 opens port 80', 'show the worst attack path'. Tokens like SG_001 are auto-expanded.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/theanshsonkar-emfirge/emfirge-mcp#diagnostics

## Score history

- 2026-08-03: 66
- 2026-08-02: 63
- 2026-08-01: 36
- 2026-07-31: 21
- 2026-07-30: 28
- 2026-07-28: 24
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/@emfirge/mcp
- Socket report: https://socket.dev/npm/package/@emfirge/mcp
- Repository: https://github.com/theanshsonkar/emfirge
- Website: https://emfirge.cloud/
- Changelog RSS feed: https://verifymcp.io/servers/theanshsonkar-emfirge/emfirge-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/theanshsonkar-emfirge/emfirge-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/theanshsonkar-emfirge/emfirge-mcp