secure-api MCP server
Commit 12 Nov 2026Menyuntikkan secret ke dalam command dan API call saat runtime sekaligus melakukan sanitasi pada output untuk mencegah paparan data sensitif ke AI client.
Juga dikenal sebagai than/secure-api-mcp
- Stars
- 5
- Tools
- 5
- Unduhan, 30 hari
- —
- Versi terbaru
- —
- Commit terakhir
- 12 Nov 2026
- Lisensi
- —
Apa itu secure-api MCP?
Menyuntikkan secret ke dalam command dan API call saat runtime sekaligus melakukan sanitasi pada output untuk mencegah paparan data sensitif ke AI client. Server ini menyediakan 5 tool, seperti get_env_keys, run_with_env, api_call.
Ringkasan dibuat dari README proyek
Tentang secure-api MCP server
Server ini memungkinkan Anda melindungi kredensial sensitif agar tidak tersimpan di cache atau dibaca oleh AI client seperti Claude Code. Developer dapat memberikan kemampuan kepada AI agent untuk menggunakan environment variables dan file konfigurasi tanpa pernah mengekspos nilai secret yang sebenarnya di dalam context percakapan. Dengan menyuntikkan secret ke dalam command dan HTTP request saat runtime lalu menyensor output yang dihasilkan, server ini menjaga lapisan keamanan antara private key Anda dan LLM.
User dapat mengelola secret melalui tool spesifik seperti api_call untuk HTTP request terstruktur dan run_with_env untuk mengeksekusi shell command. Server ini juga menangani kredensial MySQL melalui read_mycnf dan membantu pemeliharaan dokumentasi menggunakan sync_env_example. Untuk memastikan keamanan, tool api_call menyertakan proteksi SSRF dan mendukung host allowlist melalui environment variable SECURE_API_ALLOWED_HOSTS. Setup ini ditujukan untuk lingkungan pengembangan lokal di mana developer ingin menggunakan Claude Code sambil mencegah penyimpanan secret dalam bentuk plaintext secara tidak sengaja di dalam history file.
Apa yang bisa Anda lakukan dengannya
- 1Eksekusi shell command dengan secretMenjalankan command terminal yang membutuhkan environment variables tanpa membiarkan AI melihat nilai tersebut di dalam output.
- 2Melakukan API request yang amanMelakukan HTTP call yang menyertakan Bearer token atau custom headers sambil memastikan tujuan request sudah terotorisasi.
Ditulis berdasarkan README proyek. Setiap use case diperiksa terhadap kutipan dari README tersebut.
Tool secure-api MCP 5
Terdeteksi dari READMEget_env_keysrun_with_envapi_callread_mycnfsync_env_example
| get_env_keys | — | |
| run_with_env | — | |
| api_call | — | |
| read_mycnf | — | |
| sync_env_example | — |
Konfigurasi
SECURE_API_ALLOWED_HOSTS
| Nama | Deskripsi | Tipe |
|---|---|---|
| SECURE_API_ALLOWED_HOSTS | — |
Pengecekan otomatis
Berjalan 14 Nov 2026Laporan lengkap →Belum diverifikasi. Sebuah server memerlukan skor 80, tidak ada temuan serius, dan data yang cukup untuk kami periksa. Cara kerja checks · Yang perlu diperbaiki untuk menambah poin
- Source repository terhubung dan dapat dijangkauthan/secure-api-mcp is public and reachablegithub.com/than/secure-api-mcp ↗Lolos
- Nama paket mencantumkan repositori ini sebagai sumbernyaTidak diperiksa
- Provenance build (atestasi Sigstore)Tidak diperiksa
- Lisensi open source (OSI)No licenseTemuan
- Ada commit atau release dalam satu tahun terakhirLast commit or release 2026-11-12github.com/than/secure-api-mcp ↗Lolos
- OpenSSF ScorecardTidak diperiksa
- Nama package tidak mirip dengan package populerTidak diperiksa
- Tidak ada advisory kritis pada paket atau dependensinyaTidak diperiksa
- Tidak ada instruksi tersembunyi untuk model5 tool descriptions and the README read; no override phrases, credential paths or hidden charactersLolos
- Tools yang bersifat destruktif telah diberi labelNo tool named like delete, drop or execLolos
- Endpoint remote merespons handshake MCPTidak diperiksa
README
Lihat di GitHubsecure-api-mcp
MCP server that lets Claude Code use secrets without seeing them.
Claude Code silently reads .env files and caches them in plaintext in ~/.claude/file-history/. This server injects secrets into commands and API calls at runtime, then sanitizes output to strip secret values before they reach Claude's context.
Threat model — read this. The strength of the guard differs by tool:
api_callhas the smallest attack surface: no shell, structured output, SSRF protection, and an optional destination allowlist (see below). Sanitization reliably covers its responses.run_with_envruns an arbitrary shell command. Output sanitization is best-effort, not a hard boundary — a command can re-encode, reverse, chunk, or otherwise transform a secret into a form the sanitizer won't recognize before printing it. Treat it as defense-in-depth.
A secret can only be protected if you control where it goes. Both tools can send a secret to an external destination by design; restrict that with deny rules, the api_call allowlist, and review of run_with_env commands.
Tools
get_env_keys(project_dir)— Returns key names from.env. No values exposed.run_with_env(project_dir, command, env_keys?, timeout_ms?, include_mycnf?)— Runs a shell command with.envvars injected. Output is sanitized — secret values replaced with[REDACTED:KEY_NAME]. Setinclude_mycnfto also sanitize MySQL credentials from.my.cnfin command output.api_call(project_dir, url, method?, headers?, body?, auth_env_key?, timeout_ms?)— HTTP request with secret injection.auth_env_keyadds a Bearer token. Headers support{{KEY_NAME}}template syntax. When a secret is injected, the destination host is checked againstSECURE_API_ALLOWED_HOSTS(see below). Redirects are followed manually, up to 5 hops, with the SSRF guard and the allowlist re-applied to every hop. Times out aftertimeout_ms(default 30s).read_mycnf(project_dir, section?)— Reads MySQL.my.cnfconfiguration. Returns section names and safe fields (port,database,socket) with credentials (user,password,host) redacted as[REDACTED:section.field]. Checks~/.my.cnfand project-local.my.cnf.sync_env_example(project_dir)— Generates/updates.env.examplefrom.env. Preserves comments and structure, strips values, uses smart placeholders.
Setup
npm install && npm run build
Register in Claude Code:
claude mcp add secure-api -- node /path/to/secure-api-mcp/dist/index.js
Pair with deny rules in ~/.claude/settings.json to block direct .env reads:
"deny": [
"Read(.env)", "Read(**/.env)",
"Read(.env.local)", "Read(**/.env.local)",
"Edit(.env)", "Edit(**/.env)"
]
Keeping .env.example in sync
Run sync_env_example to generate or update .env.example from your .env. It:
- Preserves comments and blank lines from
.env - Strips secret values, replacing them with smart placeholders (URLs stay URL-shaped, booleans stay as-is, numbers stay as-is, everything else blanked)
- Merges with any existing
.env.example— custom placeholders you've added won't be overwritten - Lets Claude read
.env.examplefreely (since deny rules only block.env) so it knows what config exists without seeing values
Pair this with get_env_keys and Claude has full awareness of your project's config without any secret exposure.
Restricting where api_call can send secrets
By default api_call will attach a secret to a request bound for any public host (internal/private IPs are always blocked for SSRF). To restrict this, set SECURE_API_ALLOWED_HOSTS to a comma-separated list of permitted hosts:
export SECURE_API_ALLOWED_HOSTS="api.stripe.com,api.github.com,*.internal.example.com"
- Set — a request that injects a secret is blocked unless its host matches.
*.example.commatches any subdomain and the apexexample.com. Matching is case-insensitive. - Unset — secrets are still sent (so existing setups keep working), but the response includes a
warningsentry naming the destination host.
Requests that inject no secret are never gated.
MySQL .my.cnf support
Claude can work with MySQL configs without seeing your credentials. read_mycnf exposes structural fields (port, database, socket) while redacting user, password, and host. When running MySQL commands via run_with_env, set include_mycnf: true to sanitize any credential values that appear in command output — the mysql CLI reads ~/.my.cnf natively, so no env var injection is needed.
Resolution order matches MySQL's own: ~/.my.cnf (global), then <project_dir>/.my.cnf (project-local overrides global per-field). !include and !includedir directives are followed. Includes in the project-local chain are contained to the project directory (resolved through symlinks) so a crafted project .my.cnf can't disclose files elsewhere on disk; the trusted global ~/.my.cnf chain is unrestricted.
How sanitization works
Secret values of 4 or more characters are replaced in all output, sorted longest-first to prevent partial matches. A value like sk-abc123xyz becomes [REDACTED:API_KEY]. The literal value, its base64 form, and its URL-encoded form are all matched, followed by a pattern pass for common token shapes (AWS, GitHub, Stripe, Slack, JWTs, private keys). Values transformed in other ways (hex, reversed, split across lines) are not caught — this is why run_with_env output is best-effort, not a guarantee.
License
MIT
Pertanyaan tentang secure-api MCP
Tool apa yang disediakan secure-api MCP?
Server ini menyediakan 5 tool, termasuk get_env_keys, run_with_env, api_call, read_mycnf, sync_env_example.
Bagaimana server ini melindungi secret saya agar tidak terlihat oleh Claude?
Server akan menyuntikkan secret ke dalam command dan API call saat runtime, lalu melakukan sanitasi pada output untuk menghapus nilai secret sebelum data tersebut mencapai context AI.
Apakah sanitasi pada output shell command dijamin sepenuhnya?
Tidak, sanitasi untuk shell command bersifat best-effort. Sebuah command berpotensi melakukan re-encode atau transformasi pada secret sehingga sanitizer tidak mengenalinya.
Bisakah saya membatasi host mana saja yang boleh menerima secret melalui tool api_call?
Ya, Anda dapat mengatur environment variable SECURE_API_ALLOWED_HOSTS dengan daftar host yang diizinkan (dipisahkan dengan koma) untuk membatasi request yang menyuntikkan secret.