Emfirge
NPM · @EMFIRGE/MCP · SCANNED SEP 20
Git branch for your cloud. Understand AWS risk, prove fixes, and ship safer changes.
Available components
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. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency35
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: the license (BUSL-1.1) isn't a recognized OSI-approved license. See how to fix → Fail
- Actively maintained (last published 1 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability82
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 789 tokens (~112/item across 7 items; 7 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management90
- Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the Emfirge MCP server?
Emfirge runs locally as an npm package, launched with npx -y @emfirge/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @emfirge/mcp
claude mcp add theanshsonkar-emfirge -- npx -y @emfirge/mcp
{
"mcpServers": {
"theanshsonkar-emfirge": {
"command": "npx",
"args": [
"-y",
"@emfirge/mcp"
]
}
}
} {
"servers": {
"theanshsonkar-emfirge": {
"command": "npx",
"args": [
"-y",
"@emfirge/mcp"
]
}
}
} codex mcp add theanshsonkar-emfirge -- npx -y @emfirge/mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"theanshsonkar-emfirge": {
"type": "local",
"command": [
"npx",
"-y",
"@emfirge/mcp"
],
"enabled": true
}
}
} openclaw mcp add theanshsonkar-emfirge --command npx --arg -y --arg @emfirge/mcp
mcp_servers:
theanshsonkar-emfirge:
command: "npx"
args: ["-y", "@emfirge/mcp"] {
"McpServers": {
"theanshsonkar-emfirge": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"@emfirge/mcp"
]
}
}
} assistant mcp add theanshsonkar-emfirge -t stdio -c npx -a -y @emfirge/mcp
{
"mcpServers": {
"theanshsonkar-emfirge": {
"command": "npx",
"args": [
"-y",
"@emfirge/mcp"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Sept 26 −3
- Stability: pass → 0.80 functional
- 16 Sept 26 0
- Stability: 0.97 → pass security
- 15 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 +1
- Security disclosure: unverified → pass ▲ functional
- 11 Sept 26 0
- Security disclosure: pass → unverified ▼ functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed npm/@emfirge/mcp@0.2.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 96 packages
| Packages resolved | 96 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
emfirge_attack_paths ~58
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.
| Name | Type | Req | Description |
|---|---|---|---|
| analysis_id | string | yes | Analysis ID returned by emfirge_scan |
No output schema declared.
No examples provided.
emfirge_check_compliance ~74
Get CIS AWS Foundations 1.5 or SOC 2 compliance status. Returns per-control pass/fail with the findings that triggered each failure.
| Name | Type | Req | Description |
|---|---|---|---|
| analysis_id | string | yes | Analysis ID returned by emfirge_scan |
| framework | string | – | Framework to filter by. Omit to get all. |
No output schema declared.
No examples provided.
emfirge_get_findings ~87
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.
| Name | Type | Req | Description |
|---|---|---|---|
| analysis_id | string | yes | Analysis ID returned by emfirge_scan |
| severity | string | – | Filter findings by severity. Omit to get all. |
No output schema declared.
No examples provided.
emfirge_scan ~198
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.
| Name | Type | Req | Description |
|---|---|---|---|
| region | string | yes | 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 | yes | 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. |
No output schema declared.
No examples provided.
emfirge_setup_help ~109
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
emfirge_simulate_breach ~130
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.
| Name | Type | Req | Description |
|---|---|---|---|
| analysis_id | string | yes | Analysis ID returned by emfirge_scan |
| query | string | yes | 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. |
No output schema declared.
No examples provided.
emfirge_verify_fix ~133
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.
| Name | Type | Req | Description |
|---|---|---|---|
| analysis_id | string | yes | Analysis ID returned by emfirge_scan |
| resource_id | string | yes | AWS resource ID (sg-..., i-..., arn:...) OR a token from a previous response (SG_001). Tokens are auto-expanded. |
| rule_id | string | yes | Rule ID like EMFIRGE-EC2-002 (or short form EC2-002) |
No output schema declared.
No examples provided.
What is the Emfirge MCP server?
Emfirge is an MCP server listed in the public MCP registry as io.github.theanshsonkar/emfirge. Git branch for your cloud. Understand AWS risk, prove fixes, and ship safer changes. This page covers its npm package (@emfirge/mcp).
Is the Emfirge MCP server safe to use?
Emfirge scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Emfirge MCP server expose?
Emfirge exposes 7 tools: emfirge_setup_help, emfirge_scan, emfirge_get_findings, emfirge_attack_paths, emfirge_verify_fix, and 2 more. Their descriptions and schemas cost roughly 789 tokens of context every time the server is loaded.
Is the Emfirge MCP server still maintained?
Emfirge is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Emfirge MCP server under?
Emfirge declares the BUSL-1.1 licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.