Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Portunus
MCP serversSecret broker for agents: reference secrets by name; values injected only at the execution boundary.
ghcr.io/mdostal/portunus:0.34.0 -
Draugr
MCP serversSecurity scanning for AI agents: SAST, SCA, secrets, IaC, DAST, ranked by real risk.
https://github.com/draugr-dev/draugr/releases/download/v0.179.0/draugr-0.179.0.mcpb@0.179.0 -
Keyblind
MCP serversEncrypted secrets vault for AI agents. 27 MCP tools resolve secrets at runtime, never leaking them.
keyblind@0.8.8 -
clerk-mcp
MCP serversQuery the Clerk Backend API (secret key; set CLERK_SECRET_KEY, Bearer): users, user details.
clerk-mcp@1.0.0 -
ncrypted
MCP serversOne-time, end-to-end encrypted secrets for agents. 0.005 USDC per secret via x402.
@seidl-family/ncrypted-mcp@0.2.2 -
TokenSafe
MCP serversReduce your AI bills by up to 99% locally: focused code, warm prompt caches & zero secret leaks.
tokensafe@4.1.3 -
DevProjex
MCP serversTurn any folder or Git repo into safe, token-efficient context for LLMs, AI chats, and coding agents like Claude Code, Codex, and Cursor — local-first GUI, TUI, CLI, and a read-only MCP server with Live Context, agent journal, Smart Ignore, secret/PII redaction, Git scopes, and code compression. Windows, macOS, Linux.
git clone https://github.com/Avazbek22/DevProjex.git -
OpenKeylet
MCP serversOpenKeylet — Local password and credential manager for AI agents via MCP. Use passwords, API keys, SSH, and TOTP while keeping hidden plaintext out of model context by default.
git clone https://github.com/omaekumiko2-create/OpenKeylet.git -
MCP-Bridge
MCP serversA middleware to provide an openAI compatible endpoint that can call MCP tools
git clone https://github.com/SecretiveShell/MCP-Bridge.git -
mcp-warden
MCP serversLocal credential broker: agents call APIs, SSH and DBs via scoped presets; secrets stay in keychain.
mcp-warden@0.6.1 -
GitGuardian
Public APIsScan files for secrets (API Keys, database credentials)
-
agent-security
Agents & frameworksLocal-first, open-source security gateway for AI coding agents. Enforce tool-call policies, detect secrets, and audit actions on-device.
git clone https://github.com/solongate/agent-security.git -
infisical-mcp
MCP serversInfisical API: manage secrets via universal auth.
infisical-mcp@1.0.0 -
KeySlip
MCP serversSend and read one-time encrypted secrets with local encryption.
https://github.com/dobrician/keyslip-distribution/releases/download/v1.3.0/keyslip-linux-x64.mcpb -
secure-vault
MCP serversEncrypted secrets and credential management for agents
secure-vault-mcp@0.1.1 -
Trestle
MCP serversDetects leaked secrets (API keys, tokens, private keys) in source code.
@trestlescan/mcp@1.4.1 -
VaultGuard
MCP serversSecret scanner preventing leaks of corporate keys and credentials.
-
Haldir
MCP serversGuardian layer for AI agents: identity, secrets, audit via MCP.
haldir@0.1.0 -
q-ring
MCP serversOS keychain secrets for AI coding agents, over MCP.
@i4ctime/q-ring@0.19.2 -
sops-mcp
MCP serversMCP server for creating and managing SOPS-encrypted secrets
sops-mcp@0.12.0 -
flowcheck
MCP serversLeast-privilege auditor for GitHub Actions workflows: permissions, triggers, secrets.
@reneturcios/flowcheck@0.1.2 -
aegis
MCP serversCredential isolation for AI agents. Inject secrets at the network boundary.
@getaegis/cli@1.0.5 -
Aegis
MCP serversCharter-bound defensive security copilot: secrets, obfuscation, deps, Dockerfile, IaC scans.
aegis-sec@0.1.1 -
MCP Security Sanitizer
MCP serversRedacts common secrets, email addresses, and phone numbers.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.