unseenkey
Use Unseenkey’s local broker to discover and call provider APIs with stored secrets without ever seeing the raw keys.
List available secrets/handles with their provider and applicable policy; values are never returned.
Call provider APIs by secret name, method, path, optional headers/body/upstream; the broker injects the real credential, enforces policy, logs the call, and scrubs the response.
Request owner approval for policy-gated requests or to allow a new upstream host.
Explain in plain English what a secret’s policy allows you to do.
Operate under per-handle controls such as expiry, request caps, approvals, host locking, canaries, and tamper-evident audit logging.
Stores Google OAuth refresh tokens or service-account JSON in the vault and proxies Google API calls through the broker, keeping access tokens fresh and credentials hidden; supports scoped service-account access such as Search Console.
Moves OpenAI API keys out of .env files into the vault and replaces them with handles, so applications and agents can call OpenAI through the broker without seeing the real key, with policy enforcement and response scrubbing.
Creates policy-scoped handles for Stripe, such as payment-only presets, and brokers Stripe API calls with per-handle restrictions, expiry, request caps, approvals, and logging.
Stores Twilio credentials, including two-part credentials, in the vault and issues handles for brokered Twilio API calls with policy enforcement and audit logging.
Every SDK, .env file and AI agent asks for the raw key, and once it exists in plaintext it gets pasted into a chat, committed to git, printed in a log, or handed to a contractor you'll never see again. Unseenkey keeps the key in an encrypted vault on your machine and hands out a handle instead. The handle looks like a key to whatever receives it, but it only works through the local broker, which swaps it for the real key at the last moment, checks a policy, scrubs the key out of the response, and writes every call to a tamper-evident log.
A leaked handle costs you nothing. A leaked key costs you until you notice.
Status: v0.1, alpha. Works and is tested on Windows, macOS and Linux. Not yet externally audited: use it with keys you can rotate. Delegating keys to other people through a hosted broker is designed, not built.
How it works
Related MCP server: keyward
Two minutes with Claude Code
usk init # pick a password; write down the 24 recovery words
usk add anthropic # paste the key at a hidden prompt; provider detected, host-locked
usk env anthropic --policy chat # prints ANTHROPIC_BASE_URL + ANTHROPIC_API_KEY=usk_h_…
claude -p "hello" # Claude Code now calls Anthropic through the broker
usk log # every call, hash-chained--shell powershell|cmd|dotenv prints the variables for your shell or .env. The daemon starts itself on first use, listens on loopback only, and locks after 15 minutes without a request or when the screen locks or the machine sleeps.
Or give your AI tools the tools, in one command:
usk mcp installIt finds Claude Code, Claude Desktop, Cursor and Windsurf on your computer and connects them, makes the vault first if you don't have one, offers to add your first key, and checks that the connection answers. Run it again whenever you like; it changes nothing that already works. Then restart the tool and ask it what API keys it can use. It calls APIs through Unseenkey and never sees a key.
Claude Code also has a plugin, if you'd rather install it that way. Use the plugin or usk mcp install, not both, or Claude Code gets the tools twice. The plugin needs Unseenkey 0.1.7 or later.
claude plugin marketplace add Bhagyesh97/unseenkey
claude plugin install unseenkey@unseenkeyWhat a handle can do
Policy per handle | Presets for each provider ( |
Hard caps |
|
Canaries |
|
Incident responses | A burst of refused requests throttles, pauses, asks you, or locks the vault — your choice per handle. |
Approvals | Live prompts in the desktop app or |
Camouflage | Handles shaped like the provider's own keys ( |
AWS and OAuth2 | boto3, the AWS CLI and the JS SDK sign with a placeholder; the broker re-signs with the real key. OAuth2 refresh tokens stay in the vault; the broker keeps the access token fresh. |
MCP server |
|
Projects | Group keys by the app that uses them. |
|
|
Desktop app | Projects with a status panel, keys, agent access, approvals, activity with chain verification, one-click MCP setup, Windows Hello, signed auto-updates. |
More of the same:
usk handle create stripe --policy payments --expires-days 7 --cap 500/day # for a contractor: gone next week
usk handle create stripe --canary # a tripwire for .env.example
usk add aws-dev && usk env aws-dev # boto3 and the AWS CLI through the broker
usk add google-oauth # paste a refresh token or gcloud's ADC file
usk add gsc --file key.json --scope webmasters.readonly # a Google service account; the file stays in the vault
usk add twilio # keys in two parts: asks for each, or paste first:second
usk run --with DATABASE_URL=prod-db -- ./app # for what cannot be proxied (audited, scrubbed)Why not just…
A | A secrets manager (Doppler, Infisical, 1Password CLI, Vault) | Your own proxy | Unseenkey | |
Your AI tool never sees the real key | No | No, it is injected into the process | Yes | Yes |
Works offline, no account | Yes | Usually needs an account or a server | Yes | Yes |
Rules per call: host, path, method | No | No | If you build them | Presets for 73 providers |
Asks you before risky calls | No | At most for reading a secret, not per call | If you build it | Yes, confirmed with Windows Hello or your password |
Removes the key from responses | No | No | If you build it | Yes, streamed and compressed too |
Request limits, to stop a runaway bill | No | No | If you build them | Per handle and per project |
Tamper-evident log of every call | No | Logs secret reads, not API calls | If you build it | Yes |
AWS signing and OAuth refresh | The key sits in the file | The key reaches the SDK | If you build them | Done inside the broker |
Already use a vault? Keep it. A vault stores keys; Unseenkey stops them reaching the agent. Importers for 1Password, Bitwarden and the OS keychain are on the roadmap (#4).
Built your own proxy? So have others: Infisical Agent Vault, fnox and OneCLI share the core idea. Unseenkey focuses on the person who owns the key: a desktop app with approvals, AWS re-signing, OAuth refresh, canary keys, a log that catches deleted entries, and next, lending a key to someone you hire.
Install
scoop bucket add unseenkey https://github.com/Bhagyesh97/scoop-unseenkey && scoop install usk # Windows
brew install Bhagyesh97/unseenkey/usk # macOS, Linux
winget install Unseenkey.Unseenkey # desktop app, Windows
cargo install --locked --git https://github.com/Bhagyesh97/unseenkey usk # from source, Rust 1.85+Archives and installers for every platform are on the Releases page: CLI for Windows x64, macOS arm64/x64 and Linux x64/arm64; NSIS/MSI, DMG, deb/rpm/AppImage for the desktop app. Every archive has a Sigstore signature, every installer a minisign signature, and each release ships an SBOM. The installers are not yet code-signed, so Windows SmartScreen and macOS Gatekeeper warn on first launch.
Verify a download
From 0.1.10, SHA256SUMS on a release lists every archive, bundle and installer on it, and is signed by the release workflow itself through Sigstore: there is no key of ours to steal, and the signature names the workflow and the tag it ran for. With cosign installed, download SHA256SUMS, SHA256SUMS.sig and SHA256SUMS.pem beside your file, then (with the version you downloaded in place of 0.1.10):
cosign verify-blob SHA256SUMS \
--signature SHA256SUMS.sig --certificate SHA256SUMS.pem \
--certificate-identity https://github.com/Bhagyesh97/unseenkey/.github/workflows/release.yml@refs/tags/v0.1.10 \
--certificate-oidc-issuer https://token.actions.githubusercontent.com
sha256sum --check --ignore-missing SHA256SUMS # Linux, Git Bash
shasum -a 256 --check --ignore-missing SHA256SUMS # macOSIn PowerShell, on one line, cosign takes the same arguments; then compare (Get-FileHash <file>).Hash with the file's line in SHA256SUMS. Verified OK from cosign says the list was made by this repository's release workflow for that tag; the second command says your file is the one on the list. Each CLI archive also has its own .sig and .pem, checked the same way. Up to 0.1.9, SHA256SUMS covers the CLI archives and the MCP bundle only. Scoop, Homebrew and winget check the hash in their manifest for you.
Providers
Provider | Presets | Provider | Presets | |
Anthropic, OpenAI | chat, no-admin, full | GitHub | read-only, contribute, full | |
Groq, Mistral, OpenRouter | chat, no-admin, full | Stripe | read-only, payments, full | |
Google AI | generate, full | Slack, Notion, Cloudflare, Vercel | read-only, write, full | |
AWS | s3-read-only, s3, full | SendGrid, Resend | read-only, write, full | |
Supabase | read-only, data, full | Twilio | read-only, messaging, full |
Plus 55 more with a safe default or read-only, and full: xAI, Together, Fireworks, Deepgram, ElevenLabs, AssemblyAI, Cohere, DeepSeek, Replicate, Perplexity, Cerebras; Paddle, Polar, Paystack, Mollie, Mercado Pago, Lemon Squeezy, Square; DigitalOcean, Linode, Vultr, Hetzner, Netlify, Render, Heroku, Neon, Supabase management, Hostinger; Postmark, Brevo, Mailgun, Loops, beehiiv, Vapi, Telnyx, Plivo, Vonage, Discord bots; Razorpay, Google service accounts, Cloudinary, Jira and Confluence, DataForSEO; Figma, Airtable, ClickUp, Coda, Calendly, Tally, HubSpot, Clerk, CircleCI, Mapbox, YouTube, OpenWeatherMap and Alpha Vantage.
Paste a key and the provider, its allowed websites and a safe default fill in, from the key's shape or, failing that, its name; then one read-only request checks the key works. generic covers any other host, Google service account key files sign in by themselves, OAuth2 refresh-token clients cover Google and anything RFC 6749, and usk presets lists everything with plain-English explanations. The provider research covers 247 services and is where new presets come from.
Security
Nothing goes through us. Unseenkey has no server in the path, no account and no telemetry. Your keys go only to the provider you're calling, and the desktop app checks GitHub for updates. SECURITY.md lists everything that leaves your machine, and the known open issues.
Vault: Argon2id → XChaCha20-Poly1305, one SQLite file, keys locked in memory and zeroised on lock, 24-word recovery phrase, optional Windows Hello.
Fail closed: each secret is locked to its provider's hosts; unmatched requests, browser-origin requests and anything the broker cannot classify are refused.
Audit: hash-chained log with a keyed head, so
usk log verifycatches edits, gaps, a log cut short and a deleted head; the entry is committed before the response reaches the caller.Scrubbing: the real key, its encodings and OAuth access tokens are removed from responses, logs and error messages. The broker negotiates compression itself and unpacks replies before scrubbing; a reply it cannot unpack is refused.
Owner confirmation: revealing a value, approving a request, enrolling a device unlock, loosening a setting and handing out or changing a policy need an owner token that only an unlock or a fresh password or Windows Hello check gives out. It lives in the CLI's or the app's memory, never on disk. The session token in
daemon.token, which any program running as you can read, is not enough for them.Nothing old stays behind: a replaced or deleted value, policy or handle state is erased from the file, not merely superseded.
What it does not do. It stops accidental leaks (chats, git, logs, screenshots, SDK telemetry) and bounds what a dishonest holder of a handle can do. A process running as you with arbitrary code execution can still use an unlocked vault within the care level, add keys, and make care-level handles, and a transparent proxy for tools like gh and git is not built yet. For a hostile agent you also want an OS sandbox. Read the threat model before trusting it with anything; report vulnerabilities privately per SECURITY.md.
Documentation and roadmap
docs/00-README.md indexes the design: vision, decision records, product spec, threat model, architecture, cryptography, broker and policy, data model, API/CLI/MCP reference, implementation plan with as-built notes, testing, operations, UX.
Next is delegation: grant a developer or agency the use of a key with a policy, an expiry, a signed log and a broker they do not control; revoke in one click. Then importers (1Password, Bitwarden, OS keychains), agent-framework plugins, a transparent proxy mode for CLIs, macOS Touch ID, and an attested hosted broker. Order and status in docs/11.
Building and contributing
cargo test --workspace # core, daemon, CLI
cargo install --path crates/usk # puts `usk` and `uskd` on your PATH from this checkout
cd apps/desktop && npm install && npm run tauri devSee CONTRIBUTING.md. Apache-2.0 for the core, CLI, daemon and desktop app; cloud services, when added, will be AGPL-3.0.
Unseenkey is built by one maintainer. Sponsoring it pays for a first external security audit, code-signed installers and the time to keep fixing security issues quickly.
Available Tools
4 toolscall_apiA
Call a provider API using a stored secret by name. The broker injects the real credential; you only see the (scrubbed) response. Paths are relative to the provider, e.g. secret="stripe-live", method="GET", path="/v1/customers?limit=3". For generic secrets and providers that span many hosts (AWS: upstream="https://s3.eu-west-1.amazonaws.com") pass upstream="https://host".
Inputs: path (required), method (required), secret (required), body, +2 more.
explain_policyC
Plain-English description of what you may do with a secret.
Inputs: secret (required).
list_secretsA
List the secrets you may use, with their provider and the policy that applies to you. Never returns values.
Inputs: filter.
request_accessA
Ask the owner to approve a request that policy gates behind approval (for example POST /v1/refunds), or to allow a host the secret is not yet locked to (pass upstream). Waits briefly for a decision. If the policy denies the path outright, the owner must change the policy; this tool will say so.
Inputs: reason (required), secret (required), scope, upstream.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct role: discovery, credential-backed API calls, access escalation, and policy explanation. list_secrets and explain_policy both touch policy, but one enumerates usable secrets while the other explains constraints, so they are not easily confused.
All tools use consistent snake_case and follow a predictable verb_noun pattern: list_secrets, call_api, request_access, explain_policy. The naming is uniform and easy to scan.
Four tools is well-scoped for a secret broker: discover secrets, use them, request additional access, and understand policy. Each tool earns its place without redundant operations.
The agent-facing lifecycle is well covered: listing secrets, calling APIs, escalating access, and explaining policy. Minor gaps exist around secret administration or revocation, but those may intentionally be owner-managed rather than agent-facing.
Maintenance
Related MCP Connectors
Credential broker for AI agents: scoped, revocable API access with policy enforcement and audit.
Supervised API-write gateway for AI agents with policy, human approval and execution receipts.
A secret store for AI agents: the agent never sees the plaintext.
Password vault for AI agents with scoped, user-approved access
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceLocal encrypted vault for API keys. LLMs never see your real keys — the server injects them transparently into HTTP requests.-
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to securely use API keys by storing them in an encrypted vault and injecting them on demand with user approval, without exposing the key values to the model.3MIT
- AlicenseNot gradedqualityBmaintenanceLets AI agents make authenticated API and OAuth calls using stored credentials they never see, with per-credential Touch ID approval, proxy execution, and a local audit log of every use.1Apache 2.0
- AlicenseAqualityBmaintenanceEnables AI agents to stage API keys into non-exposing handles and make API calls where the real key is injected locally, so secrets stay out of prompts, transcripts, tool arguments, and logs. Also allows listing handles, revoking secrets, and inspecting vault info without ever returning raw secret values.51MIT No Attribution