env-phantom
Provides the underlying infrastructure for security features like explain_exfil_attempt by serving language models on port 11434.
Protects cloud-based API endpoints by routing traffic through the phantom vault pattern when configured via HTTP_PROXY, ensuring real secrets are secured in a local edge proxy.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
env-phantom
One line: npx env-phantom mask .env --allow-write && npx env-phantom run -- node app.js
Child processes and coding agents see format-preserving phantom_* tokens in process.env. Real secrets are swapped in only inside the local edge HTTP proxy when the outbound Host matches your allowlist; everything else gets 403 Blocked by env-phantom. HTTPS_PROXY uses HTTP CONNECT (tunnel or local TLS MITM for rewrite hosts). The vault is encrypted at rest (AES-256-GCM); set ENV_PHANTOM_VAULT_KEY or use the machine-derived fallback. mask --allow-write backs up .env to .env.bak first.
Why not dotenvx / 1Password / Infisical?
Those tools decrypt secrets directly into the child process environment. Any dependency, coding agent, or postinstall script can read process.env and exfiltrate the real key. env-phantom never places the real secret value in the child environment.
Related MCP server: Janee
Install
bunx env-phantom mask .env --dry-run
npx env-phantom mask .env --dry-run
# or install in your project / globally
bun add -d env-phantom
npm i -D env-phantomJSR:
bunx jsr add @kanchingyg/env-phantom
npx jsr add @kanchingyg/env-phantomCLI
Command | Purpose |
| Print masked env ( |
| Run command with phantom env + local proxy |
| Print blocked exfiltration attempts |
| Start MCP server over stdio |
Ollama (optional)
For explain_exfil_attempt, run Ollama on port 11434. Cloud OpenAI-compatible endpoints used for embeddings can sit behind the same phantom vault pattern via HTTP_PROXY.
MCP Tools Reference
Tool | Mutates | Description |
|
| List phantom env keys and merged allowlisted hosts (no secret values). |
|
| Run |
|
| Summarize a blocked exfiltration log entry ( |
Masking .env is CLI-only (mask); use npx env-phantom audit for blocked outbound attempts.
Editor and Agent Integration
Cursor (.cursor/mcp.json)
{
"mcpServers": {
"env-phantom": {
"command": "npx",
"args": ["-y", "env-phantom", "--mcp"]
}
}
}Claude Code CLI
claude mcp add env-phantom -- npx -y env-phantom --mcpProgrammatic Usage (JSR / TypeScript)
import * as bridge from "jsr:@kanchingyg/env-phantom/bridge";Runtime Safety and Guardrails
Stdio frame isolation:
--mcpkeeps JSON-RPC onstdoutclean (logs go tostderr).Read-only default:
run_sandboxedneeds--allow-write;--dry-runblocks mutating tools.Loop breaker: Identical MCP tool calls halt after three repeats.
Path containment:
maskand MCPcwdmust stay under the process working directory.Edge proxy: Non-allowlisted hosts get
403when a request carries a phantom token.
License
This server cannot be deployed
Maintenance
Related MCP Connectors
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
Guarded MCP server for agent-readable business truth, provenance, readiness, and discovery.
Security & DLP proxy for MCP: tool-poisoning scans, PII redaction on tool args/results. Beta.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceMCP server that lets AI agents call APIs without ever seeing the credentials, using a local encrypted vault and per-secret allowlist policies for HTTP requests and subprocess environment variables.1AGPL 3.0
- AlicenseNot gradedqualityCmaintenanceSecrets management MCP server that injects credentials into API requests for AI agents, enforcing policies and logging all activity without exposing raw keys.60 npm30MIT
- AlicenseNot gradedqualityBmaintenanceA local-first MCP server that lets AI agents use gated APIs without holding keys, enforcing declarative policies, injecting secrets server-side, and auditing access without content.2Apache 2.0
- AlicenseNot gradedqualityCmaintenanceA tiny local MCP server and CLI that lets AI agents read only allowlisted environment variables, redacts known secrets from text, and logs every access.MIT