BeVigil MCP Server

Map a company's mobile attack surface from your AI assistant.

BeVigil has scanned millions of Android apps and extracted the infrastructure hiding inside them — backend hosts, staging subdomains, S3 buckets, API paths, and query parameters that never appear in DNS or search engines. This server puts that data behind seven MCP tools, so you can ask for it in plain language instead of stitching together curl calls.

Built for bug bounty hunters, pentesters, red teamers, and appsec engineers doing recon.

Tested with Claude Code, Claude Desktop, Codex, Cursor, and VS Code.

Quick start (2 minutes)

1. Get a free API key

Sign up at bevigil.com/osint-api. Free accounts get 25 credits, or 200 if you register with a work email. One lookup = one credit.

2. Add the server

No clone, no build — npx fetches and runs it.

claude mcp add bevigil -e BEVIGIL_API_KEY=your_key_here -- npx -y bevigil-mcp-server

Check it registered with claude mcp list.

Edit claude_desktop_config.json (Settings → Developer → Edit Config):

{
  "mcpServers": {
    "bevigil": {
      "command": "npx",
      "args": ["-y", "bevigil-mcp-server"],
      "env": { "BEVIGIL_API_KEY": "your_key_here" }
    }
  }
}

Restart Claude Desktop.

codex mcp add bevigil --env BEVIGIL_API_KEY=your_key_here -- npx -y bevigil-mcp-server

Check it registered with codex mcp list.

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project):

{
  "mcpServers": {
    "bevigil": {
      "command": "npx",
      "args": ["-y", "bevigil-mcp-server"],
      "env": { "BEVIGIL_API_KEY": "your_key_here" }
    }
  }
}

Add to your VS Code MCP settings:

{
  "mcp": {
    "servers": {
      "bevigil": {
        "command": "npx",
        "args": ["-y", "bevigil-mcp-server"],
        "env": { "BEVIGIL_API_KEY": "your_key_here" }
      }
    }
  }
}

3. Ask your first question

Investigate com.whatsapp with BeVigil and summarise the infrastructure it exposes.

You should get back something like this — real hostnames pulled out of the app's code:

# Investigation Report: com.whatsapp
Source: BeVigil OSINT API

## Hosts / Domains (155 found)
• osaka.nyc3.cdn.digitaloceanspaces.com
• s3.getstickerpack.com
• logger.instagram.com
• dev503.prn2.facebook.com
...

That's it — you're doing OSINT from the chat window.

What you can ask

Recon a company's mobile footprint

Which Android apps talk to api.acme.com? Then pull the hosts out of each one.

Find staging and internal endpoints

Get subdomains for acme.com from BeVigil and flag anything that looks like dev, staging, or internal.

Hunt for exposed storage

What S3 buckets does com.acme.mobile reference?

Build a target-specific fuzzing wordlist

Pull the BeVigil wordlist for com.acme.mobile and save the API paths to paths.txt.

Pivot from a single domain

Find apps referencing acme.com, then investigate the three most interesting ones and tell me which backends they share.

The last one is where an agent earns its keep — that's a dozen API calls and a correlation pass that you'd otherwise do by hand.

Tools

| Tool | Input | Returns | |---|---|---| | bevigil_get_hosts | package ID | Hostnames found in an app's code | | bevigil_get_subdomains | domain | Subdomains seen across indexed apps | | bevigil_get_urls | domain | Full URLs referenced by apps | | bevigil_get_s3_buckets | package ID | S3 buckets referenced in an app | | bevigil_get_app_packages | hostname | Reverse lookup — apps using that host | | bevigil_get_wordlist | package ID | Paths, endpoints, and params for fuzzing | | bevigil_investigate_app | package ID | Hosts + S3 + params + wordlist in one report |

Pagination

Every list-returning tool takes optional limit and offset (default 100, max 500). When results are truncated the response says so and gives the exact offset to continue from:

Hosts for com.whatsapp (155 found)
Source: BeVigil OSINT (package: com.whatsapp)
Showing 1-100 of 155.
For the next page, call this tool again with offset=100.

Credits

Responses are not cached. Every tool call — including each extra page — is one API request and one credit. bevigil_investigate_app makes four calls per run, so it costs four. When credits run out you get a clear message rather than a silent empty result.

Apps that aren't indexed yet

BeVigil only answers for apps it has already scanned. If a package isn't in the index, the tools tell you how to fix that:

"com.acme.mobile" is not in BeVigil's index, so there is no data to return.

To add it, upload the APK at https://bevigil.com/scanApp. BeVigil scans the app
and indexes the assets it finds, after which this tool will return them.

This is deliberately distinguished from "app is indexed but has no S3 buckets" — only the first case is something you can act on.

Configuration reference

API key

Preferred: set it in your MCP client config (as shown in the quick start), which passes it to the server as an environment variable. For shell use:

export BEVIGIL_API_KEY=your_api_key_here

A .env file in the package root also works. Note that it's resolved relative to the installed package rather than your working directory, since MCP clients launch servers from arbitrary places. Real environment variables always win over .env, and .env is gitignored — never commit it.

Running from source

For local development, or to pin a specific commit:

git clone https://github.com/santhosh-005/bevigil-mcp-server.git
cd bevigil-mcp-server
npm install
npm run build

Then point your client at the built entry point instead of npx:

claude mcp add bevigil -e BEVIGIL_API_KEY=your_key_here -- node /absolute/path/to/bevigil-mcp-server/build/index.js

Requirements: Node.js 20.12+, a BeVigil API key, and an MCP-compatible client.

How it works

MCP Client  →  BeVigil MCP Server  →  osint.bevigil.com
              · Zod input validation
              · pagination + truncation
              · error normalisation

The server is a thin, well-defended layer: it validates inputs, keeps responses inside a sensible context budget, and turns the API's several different ways of saying "nothing here" into one consistent, actionable message.

Design decisions worth knowing about:

• Seven task-shaped tools, not raw endpoint wrappers — each maps to something a researcher actually wants.
• Paginated results with next-offset hints, so large result sets stay reachable without flooding the context window.
• Concurrent lookups in the investigation workflow.
• Partial failure handling — a broken lookup doesn't sink the whole report.
• Findings are labelled observed data, never asserted as vulnerabilities. A bucket name is a lead, not a finding.

Limitations

• Mobile app data only — this reflects what's embedded in Android app code, not DNS enumeration or internet-wide scanning. Use it alongside your usual tooling, not instead of it.
• Index-only coverage — only apps BeVigil has scanned. Unindexed apps can be submitted at bevigil.com/scanApp.
• No app search — you need a package ID or domain up front; there's no endpoint to discover apps by name.
• Limited app metadata — reverse hostname lookups return app name and version; otherwise you get security-relevant assets only.
• Data freshness — results reflect BeVigil's most recent scan of each app, which may not be current.
• Credit-based — see Credits above.

Security

• API keys are read from the environment (or a package-root .env) — never hardcoded, never logged
• Error messages never expose credentials, and a test asserts this
• The server only talks to known BeVigil endpoints — no arbitrary URL fetching
• Path parameters are URL-encoded, so a crafted package ID can't escape the intended endpoint
• All tool inputs are validated with Zod schemas
• Request timeouts prevent hanging connections
• Page sizes are bounded (max 500) to prevent context overflow
• A pre-commit hook and a CI job both check that no credential reaches the repo
• Every tool is annotated read-only and non-destructive — nothing this server exposes can modify data
• No telemetry, no analytics, no stored queries — see PRIVACY.md

Use responsibly. This tool queries a public OSINT database. What you do with the results is your responsibility — only test systems you're authorised to test.

Development

npm install
npm test        # typecheck + full suite
npm run lint    # typecheck only
npm run build

Tests use Node's built-in runner with mocked API responses — no live calls, no credits spent. Coverage spans the API client (auth headers, every HTTP error path, timeouts, malformed and enveloped responses, and a check that errors never leak the key) and all seven tool handlers, including the investigation workflow's partial-failure behaviour. A registration contract test also asserts that every tool declares an input schema and all four MCP behaviour hints.

To enable the pre-commit hook that blocks committing credentials:

git config core.hooksPath .githooks

It refuses any commit that stages a .env file or puts a non-placeholder value in .env.example, and runs gitleaks on staged changes when installed.

├── src/
│   ├── index.ts              # MCP server entry point
│   ├── bevigil-client.ts     # API client (auth, errors, timeouts, envelopes)
│   ├── types.ts              # Shared types, pagination, output helpers
│   └── tools/                # One file per MCP tool
├── tests/
│   ├── bevigil-client.test.ts
│   ├── tools.test.ts
│   └── fixtures/responses.ts
├── .github/workflows/ci.yml  # Typecheck, build, test, secret scan
├── .githooks/pre-commit      # Blocks committing credentials
└── server.json               # MCP Registry metadata

Contributing

Issues and PRs welcome — bug reports, new BeVigil endpoints, and client configurations for MCP hosts not listed above are all useful.

License

MIT — see LICENSE. Privacy policy: PRIVACY.md.

Not affiliated with or endorsed by CloudSEK. BeVigil is a CloudSEK product; this is an independent open-source client for their public OSINT API.