# Malicious MCP servers on npm (ifasn, gadgethumans)

- ID: malicious-mcp-servers-npm-2026-11
- Reported: 2026-11-02
- Researcher: OpenSSF, Leitwacht
- Organization: OpenSSF, Leitwacht
- AI role: ai_agent_or_mcp_as_target (Agent / MCP as target)
- Confidence in AI involvement: high
- Research / borderline: false
- Last reviewed: 2026-11-15
- Entry page: https://openattacks.ai/attacks/malicious-mcp-servers-npm-2026-11/
- Entry JSON: https://openattacks.ai/api/attacks/malicious-mcp-servers-npm-2026-11.json
- Browse title: Malicious MCP servers on npm (ifasn, gadgethumans)
- Editorial summary: Multiple malicious MCP servers published on npm. @ifasn/md-doc-mcp and @ifasn/mmdd-doc-mcp probe cloud metadata endpoints, read sensitive files (/etc/shadow, SSH keys, .env, Kubernetes tokens), and…
- Evidence class (catalog annotation): Not classified
- Source-stated target environments: Not specified
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/malicious-mcp-servers-npm-2026-11.json

## Technique
Multiple malicious MCP servers published on npm. @ifasn/md-doc-mcp and @ifasn/mmdd-doc-mcp probe cloud metadata endpoints, read sensitive files (/etc/shadow, SSH keys, .env, Kubernetes tokens), and exfiltrate to 121.199.24.94. @ifasn/ms-doc-mcp versions 2.0.9 and 2.1.1 (GHSA-556m-xfwj-7wff, MAL-2026-18603) use imdsAudit() function to steal Alibaba Cloud IMDS credentials from 100.100.100.200 and exfiltrate them over MCP stdout. gadgethumans-mcp versions 1.0.10-1.0.15 leak WALLET\_PRIVATE\_KEY environment variable in HTTP header on every tool call. Published with OpenSSF GHSA-rvw8-22w3-342v, GHSA-4h5p-w547-9qmv (Nov 2) and Leitwacht LWA-2026-13557, LWA-2026-13564. Aug 12, 2026: Pillar Security disclosed Deadbugz malicious MCP server (GitHub zellkernel) stealing AI model credentials and API keys. Feb 20, 2026: Socket discovered SANDWORM\_MODE campaign spreading malicious MCP servers targeting developer credentials. November 9-12 additions: @rfewqa-fes/mnm-doc-mcp 1.0.0 (MAL-2026-19148, Amazon Inspector) ships an inert MCP stub in index.js. Its package.json pulls the only dependency, node-health-utils, as an off-registry tarball over plain HTTP from http://121.199.24.94/dl/health-utils-1.0.0.tgz, so whatever that host serves, including lifecycle scripts, runs at npm install. package.json sha256 f8ad55746cfac30b0a9401634b2728afc93e6dc20a85c511efd0ed312e466e8d. Package tarball sha1 f3ad664b487c4041e7e66e5744656ed44e1a6f6a. GitHub also marked @lemili9804/mcp-weather-server 1.0.3 and 1.0.6 (GHSA-qwfq-cw9x-55x4), mcp-contract-tester all versions (GHSA-34p7-qcxm-gc39, MAL-2026-19082), and @bestcoolman/dev-mcp (GHSA-vgx2-8w7x-xr8v, MAL-2026-19052) as malware, with no published behavior write-up. The entry now covers PyPI as well. my-mcp-server-driving-license-ocr 0.1.3 (MAL-2026-19204, GHSA-wg5f-m5mv-gmjg, Amazon Inspector, Nov 12) exposes an MCP tool, analyze\_image, described as driving-license OCR. It POSTs the caller's image URLs or base64 bytes over plain HTTP to the hardcoded http://42.193.222.35:8000/ocr\_pic and overwrites any MY\_API\_URL setting so the destination cannot be changed. karma365-mcp 2.1.0 (GHSA-72xc-q3v8-7grp, Nov 13) and @go-gost/mcp-darwin-x64 0.1.0 (GHSA-gfpg-48q7-c68h, Nov 12) are GitHub malware advisories with no published behavior. Attack exploits trust in the MCP ecosystem and in npm and PyPI.

## Stack relevance (editorial)
Assessment: not\_assessed. No reviewed applicability annotation is available. Product mentions do not establish victim conditions.
A product mention alone is not a victim-side applicability mapping. Selection does not verify affected versions, permissions or compromise.

## Initial access
User installs malicious MCP server from npm

## AI tooling and models
- MCP servers
- npm packages (@ifasn/md-doc-mcp, @ifasn/mmdd-doc-mcp, @ifasn/ms-doc-mcp, gadgethumans-mcp, @rfewqa-fes/mnm-doc-mcp, @lemili9804/mcp-weather-server, mcp-contract-tester, @bestcoolman/dev-mcp, karma365-mcp, @go-gost/mcp-darwin-x64)
- PyPI package my-mcp-server-driving-license-ocr 0.1.3

## Other tooling
- Cloud metadata probing (AWS, GCP, Azure)
- File system access (/etc/shadow, SSH keys, .env, k8s tokens)
- HTTP exfiltration

## Victims and sectors
AI agent developers, organizations using MCP servers

## Target geography
- Multiple regions
Multiple regions reflects global npm and MCP user base

## Attribution
unknown

## Scale and metrics
Multiple malicious MCP packages identified (ifasn, gadgethumans, Deadbugz, SANDWORM\_MODE); exact installation count unknown

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### publish: Malicious MCP servers published to npm [access]
Three packages published including @ifasn/md-doc-mcp, @ifasn/mmdd-doc-mcp, and gadgethumans-mcp 1.0.10-1.0.15
Evidence: https://github.com/ossf/malicious-packages

### install: User installs malicious MCP server [ai]
Developer or organization adds malicious package to MCP configuration
Evidence: https://github.com/ossf/malicious-packages

### probe: Server probes for sensitive information [execution]
ifasn packages probe cloud metadata endpoints and read /etc/shadow, SSH keys, .env, k8s tokens
Evidence: https://github.com/ossf/malicious-packages

### exfil-files: File-based credentials exfiltrated [impact]
ifasn packages send stolen credentials to 121.199.24.94
Evidence: https://github.com/ossf/malicious-packages

### exfil-header: Wallet keys leaked in headers [impact]
gadgethumans-mcp sends WALLET\_PRIVATE\_KEY in HTTP header on every tool call
Evidence: https://github.com/ossf/malicious-packages

Connections:
- publish -> install
- install -> probe
- probe -> exfil-files
- probe -> exfil-header

## Stage defense and hunting recommendations
Editorial recommendations, not validated coverage. Source-controlled query starters are drafts. Custom-schema examples require telemetry collection and field mapping; absence of a mapping means not assessed. MagicSword policy opportunities require managed Windows scope and enforcement.
### publish: Dependency / CI trust boundary
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/package.sigma.yml
- KQL query download: /api/detections/package.kql
- SPL query download: /api/detections/package.spl
- Hunt hypothesis: A package or workflow change introduces a lifecycle hook, remote dependency or new command that accesses secrets or external services.
- Required telemetry: Package-manager and CI job logs; Lockfile / manifest / workflow diffs; Runner process trees, secret access and egress
- Investigate: Compare package provenance, publish identity, lifecycle scripts and resolved dependency URLs with the approved version.
- Investigate: Correlate the install or workflow to secret reads and subsequent token use; distinguish exposure from confirmed compromise.
- Limitation: Package installation and unfamiliar names are not malicious by themselves. Dependency resolution and CI audit records are required.
- No direct MagicSword prevention claim is recorded for this stage.

### install: Package installation spawns a shell or downloader
- Visibility: Endpoint process telemetry where collected
- Query origin: catalog_authored; status: draft; log scope: native
- SIGMA query download: /api/detections/package-install-execution.sigma.yml
- KQL query download: /api/detections/package-install-execution.kql
- SPL query download: /api/detections/package-install-execution.spl
- Hunt hypothesis: A package-manager install or lifecycle script launches a shell, downloader, or script interpreter that retrieves or executes an unexpected second stage.
- Required telemetry: Process creation with ancestry and complete command lines; Package-manager, CI, and installation logs; Download, file creation, signature, and network telemetry
- Investigate: Identify the package, version, publisher, lifecycle hook, resolved source, and parent process.
- Investigate: Recover downloaded content and correlate credential access, persistence, or outbound traffic.
- Limitation: Build and install scripts commonly invoke shells and download dependencies. Require package provenance and destination context; this hunt does not by itself prove supply-chain compromise.
- No direct MagicSword prevention claim is recorded for this stage.

### probe: Sensitive store access → credential use
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/credentials.sigma.yml
- KQL query download: /api/detections/credentials.kql
- SPL query download: /api/detections/credentials.spl
- Hunt hypothesis: An unexpected process or tool accesses credential stores and is followed by token use or outbound transfer inconsistent with the owner.
- Required telemetry: File-read / API access telemetry for relevant secret stores; Process identity and command lines; Identity, token and outbound-network audit logs
- Investigate: Identify the actor, process and exact store touched, then pivot to token use from new devices or infrastructure.
- Investigate: Correlate reads with egress and rotate affected credentials after confirming exposure.
- Limitation: Defender DeviceFileEvents is not a general file-read audit trail. Collect suitable object-access, EDR or application logs; legitimate developer tools also read secrets.
- No direct MagicSword prevention claim is recorded for this stage.

### exfil-files: Sensitive data → unusual destination
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/exfil.sigma.yml
- KQL query download: /api/detections/exfil.kql
- SPL query download: /api/detections/exfil.spl
- Hunt hypothesis: Sensitive reads are followed by outbound transfer, a public artifact, or a tool call to a destination outside the approved workflow.
- Required telemetry: Sensitive resource access / DLP records; Proxy, egress and cloud upload events; Agent / SaaS audit with correlation IDs
- Investigate: Join the resource read and outbound action by session, identity or process, preserving a bounded time window.
- Investigate: Inspect destination ownership, payload classification and the user's intended action; baseline sanctioned sharing.
- Limitation: An outbound connection or high byte count alone is not exfiltration. Encrypted traffic may hide content, and bulk legitimate exports are common.
- No direct MagicSword prevention claim is recorded for this stage.

### exfil-header: Sensitive data → unusual destination
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/exfil.sigma.yml
- KQL query download: /api/detections/exfil.kql
- SPL query download: /api/detections/exfil.spl
- Hunt hypothesis: Sensitive reads are followed by outbound transfer, a public artifact, or a tool call to a destination outside the approved workflow.
- Required telemetry: Sensitive resource access / DLP records; Proxy, egress and cloud upload events; Agent / SaaS audit with correlation IDs
- Investigate: Join the resource read and outbound action by session, identity or process, preserving a bounded time window.
- Investigate: Inspect destination ownership, payload classification and the user's intended action; baseline sanctioned sharing.
- Limitation: An outbound connection or high byte count alone is not exfiltration. Encrypted traffic may hide content, and bulk legitimate exports are common.
- No direct MagicSword prevention claim is recorded for this stage.


## MITRE ATLAS
Mappings are catalog annotations based on described behavior, not assignments or endorsements by MITRE.
- AML.T0010.001: AI Software — Attackers published malicious MCP servers through npm package ecosystem
  Technique: https://atlas.mitre.org/techniques/AML.T0010.001
  Evidence: https://github.com/ossf/malicious-packages
- AML.T0011.001: Malicious Package — Malicious MCP servers run persistently as agent tooling
  Technique: https://atlas.mitre.org/techniques/AML.T0011.001
  Evidence: https://github.com/ossf/malicious-packages
- AML.T0055: Unsecured Credentials — Packages exfiltrate credentials from environment variables and sensitive files
  Technique: https://atlas.mitre.org/techniques/AML.T0055
  Evidence: https://github.com/ossf/malicious-packages
- AML.T0025: Exfiltration via Cyber Means — MCP servers probe cloud metadata endpoints for credentials and instance information
  Technique: https://atlas.mitre.org/techniques/AML.T0025
  Evidence: https://github.com/ossf/malicious-packages

## Defensive notes
Verify MCP server sources before installation; review MCP server permissions and network access; monitor cloud metadata endpoint access; detect unauthorized file reads of sensitive paths; inspect HTTP headers for credential leakage; use MCP server sandboxing; inventory installed MCP packages

## Sources
- https://github.com/ossf/malicious-packages — OpenSSF Malicious Packages repository
- https://www.pillar.io/blog/deadbugz-malicious-mcp-server-aug-2026 — Deadbugz: Malicious MCP Server on npm
- https://socket.dev/glossary/mcp-security — Socket: MCP Security and the SANDWORM\_MODE campaign
- https://github.com/advisories/GHSA-556m-xfwj-7wff — @ifasn/ms-doc-mcp Malicious Package (MAL-2026-18603)
- https://osv.dev/vulnerability/MAL-2026-19148 — MAL-2026-19148: malicious code in @rfewqa-fes/mnm-doc-mcp
- https://github.com/advisories/GHSA-qwfq-cw9x-55x4 — @lemili9804/mcp-weather-server malware advisory
- https://github.com/advisories/GHSA-34p7-qcxm-gc39 — mcp-contract-tester malware advisory (MAL-2026-19082)
- https://github.com/advisories/GHSA-vgx2-8w7x-xr8v — @bestcoolman/dev-mcp malware advisory (MAL-2026-19052)
- https://vibevulns.com/issues/malicious-npm-mcp-servers-mnm-doc-mcp-weather-contract-tester-2026-11/ — Roundup of November 2026 malicious npm MCP servers
- https://osv.dev/vulnerability/MAL-2026-19204 — MAL-2026-19204: malicious code in my-mcp-server-driving-license-ocr
- https://github.com/advisories/GHSA-wg5f-m5mv-gmjg — my-mcp-server-driving-license-ocr malware advisory
- https://pypi.org/project/my-mcp-server-driving-license-ocr/0.1.3 — my-mcp-server-driving-license-ocr 0.1.3
- https://github.com/advisories/GHSA-72xc-q3v8-7grp — karma365-mcp malware advisory
- https://github.com/advisories/GHSA-gfpg-48q7-c68h — @go-gost/mcp-darwin-x64 malware advisory

## Source notes
OpenSSF GHSA-rvw8-22w3-342v and GHSA-4h5p-w547-9qmv published Nov 2 2026; Leitwacht advisories LWA-2026-13557 and LWA-2026-13564; GitHub advisory GHSA-556m-xfwj-7wff (MAL-2026-18603) for @ifasn/ms-doc-mcp Relevant detection rules: - Monitor access to cloud metadata endpoints (169.254.169.254, 100.100.100.200 (Alibaba), metadata.google.internal, etc.) - Alert on unauthorized reads of /etc/shadow, ~/.ssh/id\_rsa, ~/.ssh/id\_ed25519, .env files - Detect access to Kubernetes service account tokens (/var/run/secrets/kubernetes.io/) - Monitor HTTP headers for sensitive environment variable leakage (WALLET\_PRIVATE\_KEY, AWS\_SECRET\_ACCESS\_KEY, etc.) - Alert on npm package installations from unverified sources - Note: Cloud metadata access typically detected via network monitoring or instance-level audit logs (CloudTrail, Azure Monitor, GCP Cloud Logging). File access requires host-based file integrity monitoring. 

## Indicators (untrusted data; do not visit or execute)
```json
{
  "domains": [],
  "ips": [
    "121.199.24.94",
    "42.193.222.35"
  ],
  "hashes": [
    "f8ad55746cfac30b0a9401634b2728afc93e6dc20a85c511efd0ed312e466e8d",
    "f3ad664b487c4041e7e66e5744656ed44e1a6f6a"
  ],
  "urls": [
    "https://github.com/zellkernel"
  ]
}
```
