MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
connection-string-secret-auditno update data
—
smithery -
Zero-knowledge one-time secret sharing behind Erseni Vault, and vault-ask, the MCP server for AI agents
npm AGPL-3.0 -
Native local MCP secret entry for AI clients — built by Abomination81
MIT ★ 5 -
Secure, value-blind Model Context Protocol server for Bitwarden Secrets Manager using the official Python SDK.
MIT -
MCP server secrets in the iCloud keychain, synchronized across Macs
MIT ★ 1 -
macOS key-chain secret storage for API keys and creds from CLI and MCP
Apache-2.0 ★ 3 -
Self-hosted secrets control plane over Vaultwarden: versions, aliases, rotation, REST, MCP and credential proxy.
MIT ★ 1 -
MCP Server generated by mcp.ag2.ai
-
Mask secrets in a project with stable placeholders, encrypt the originals, and restore them byte-for-byte. Guards Claude Code, Codex, Gemini CLI, Cursor and Copilot, and blocks git commits that leak secrets. Powered by gitleaks.
MIT ★ 3 -
catarina-secretsactive
Find leaked API keys in your code and git history, and keep secrets in an encrypted vault your apps and AI agents use without seeing them.
npm MIT -
Detect hardcoded secrets in source and config, reporting masked previews and never the values themselves.
npm MIT -
MCP server and CLI that scan staged diffs, files, and text for secrets before they reach a commit - offline, with masked findings.
MIT ★ 1 -
claude-secretsgithub.com/BellaBe/claude-secretsupdated this year
GPG-encrypted credential manager for Claude Code MCP channels. Keeps API tokens out of .env files that Claude can read.
-
pi-secrets-guardgithub.com/vaibhav-patel/pi-secrets-guardupdated this year
Block secrets and PII before they land: regex + entropy scanning for files, diffs, and AI coding agents (CLI + MCP + skill + pi extension).
MIT -
MCP server that lets an agent request a secret from the user without the value entering the conversation.
MIT -
Self-hosted secrets broker for AI agents: Bitwarden-compatible vault + per-agent approvals, audit, MCP and OAuth 2.1
AGPL-3.0 -
hush — keep API keys out of AI agent chats. Vault + redacting runner + harness-agnostic MCP server.
npm MIT -
MCP server: scan text for leaked credentials before an agent commits it. Local-only, dependency-free.
mcpb MIT -
claude-secretsgithub.com/vaultry/claude-secretsupdated this year
Encrypted secrets store for Claude Code (MCP) + CLI + .env placeholder expansion. macOS Keychain backed.
npm NOASSERTION ★ 6 -
MCP server detecting leaked secrets/credentials (32+ provider rules). In the official MCP Registry: io.github.eltociear/secrets-audit-mcp. Pure stdlib, zero deps.
oci MIT ★ 1 -
Local-Secrets-MCPgithub.com/danielrosehill/Local-Secrets-MCPupdated this year
Notes / an idea for a local MCP handler for secrets that works in conjunction with a cloud API
★ 1 -
Local encrypted secrets for AI coding agents — MCP-native, macOS-first. One vault, every harness.
MIT ★ 1 -
Local MCP server + GUI that lets LLMs access your secrets - but only when you and your butler want them to
MIT -
experimental MCP - encrypted thoughts for LLMs
MIT ★ 2 -
Give the agent a handle, not the key. MCP server that keeps API keys out of AI agent conversations.
MIT-0 ★ 1 -
secrets-detection-mcpgithub.com/deja666/secrets-detection-mcpupdated this year
MCP server that detects accidentally committed secrets, API keys, tokens, and credentials using pattern matching and entropy analysis
npm MIT -
Centralized secrets manager for solo developers managing 100+ public repos. Generate .env files, rotate keys, sync to GitHub Actions.
smithery -
env-secret-exposure-analyzer-mcpgithub.com/vola-trebla/env-secret-exposure-analyzer-mcpupdated this year
MCP server that scans your project for secret exposure risks — leaked API keys, unprotected .env files, secrets in logs — before your AI agent accidentally exfiltrates them
npm MIT -
Deterministic no-LLM MCP server that scrubs secrets from text/logs before agent context. Redact/mask/hash, never leaks the value.
pypi MIT -
MCP server that scans code for exposed secrets - API keys, tokens, private keys and high-entropy strings - with placeholder-aware allowlisting and redacted reports
pypi MIT ★ 3 -
麦麦密桌 SecretTable:浏览器本地偏好评估 + 大模型 Agent 协商 + 麦当劳 MCP 官方核价
MIT ★ 2 -
A bilingual MCP server that analyzes GDWEB references independently and generates implementation-ready DESIGN_INDEX documents for LLM-driven frontend development.
npm MIT -
The secret manager for LLM agents: create, rotate, and use secrets they can never read. OS-native keyvault (macOS Keychain) + zero-dependency MCP server + Claude Code guard hook. No get verb, by design.
MIT -
secret-safe-envgithub.com/irrenwill/secret-safe-envupdated this year
MCP server that lets an AI agent put secrets into .env without ever seeing the value — native Windows masked dialog + PowerShell. Windows-only.
npm MIT -
Holds secrets and calls APIs for AI agents over remote MCP + OAuth 2.1, so agents never see a key. Cloudflare Workers POC.
MIT -
Let coding agents use your credentials without reading them
mcpb GPL-3.0 ★ 9 -
secret-vault-mcpgithub.com/n8nfelipe/secret-vault-mcpupdated this year
Local, encrypted password vault exposed as a Model Context Protocol (MCP) server. Secrets live on disk in AES-256-GCM ciphertext, unlocked by a master password derived via PBKDF2-HMAC-SHA256 (600,000 iterations). The master password is never written, never logged, and never transmitted.
MIT -
secrets-realestate-mcpgithub.com/rl-experiments/secrets-realestate-mcpupdated this year
MCP server for French property intelligence — sold prices, energy, risk, crime and schools for any address, each answer sourced.
MIT ★ 1 -
agent-secretsgithub.com/nyx-builds/agent-secretsupdated this year
Encrypted secrets management MCP server for AI agents — AES-128 Fernet vault, access policies, audit trails, key rotation.
MIT -
Agents never see your credentials. They ask; a window opens on your screen; you paste; the value lands in the macOS Keychain. MCP + CLI + loopback API, shared by Claude Code, Codex and Hermes. Public domain.
Unlicense -
Stop AI coding agents from leaking your API keys. Local proxy + MCP that swaps real secrets for phm_ tokens — works with Claude Code, Cursor, Windsurf, and Codex.
cargo MIT ★ 20 -
MCP.Secrets.Detectorgithub.com/davidCrejenovschi/MCP.Secrets.Detectorupdated this year
AI-powered inline secrets detector for GitHub Pull Requests. Uses multi-agent LLM scanning (Microsoft Agent Framework + GPT) to flag hardcoded API keys, tokens, passwords, and connection strings directly on code lines — then posts line-level review comments automatically.
-
@hyphen-network/devassetsgithub.com/0xryanlee/devassetsupdated this year
Local-first developer secrets manager — store encrypted env vars, manage API keys across projects, resolve provider identities, and inject secrets into commands. CLI + MCP server. No cloud, no account.
npm MIT -
vaultbridgegithub.com/Code-for-100k/vaultbridgeupdated this year
Secret management for AI coding agents. Your secrets never enter the LLM context window.
MIT ★ 1 -
Local MCP security reviewer for AI coding agents — catches NEXT_PUBLIC_ secret leaks, missing RLS, unauth server actions, and verbose error leaks
npm MIT -
MCP server for creating and managing SOPS-encrypted secrets
pypi Apache-2.0 -
MCP server for LinkPilot: short links and end-to-end encrypted one-time secret links, for AI assistants
npm MIT -
Zero-knowledge MCP secrets vault for AI agents — use API keys, passwords & SSH keys with plaintext never entering the model context. The Wundervault MCP server.
npm AGPL-3.0 ★ 2 -
MCP server that injects secrets into shell commands at exec time — plaintext never reaches the model context
oci MIT ★ 1 -
Encrypted secrets vault for developers, with memory and AI access without exposing values
Apache-2.0 -
jfsgithub.com/theone55/jfsactive
Secrets for AI agents that never see them — the CLI and MCP server of JFSecure
mcpb MIT ★ 1 -
envpactgithub.com/chirag127/envpactupdated this year
$0 serverless Git-backed secrets manager for solo devs: one private repo, shared keys, CLI + MCP + VS Code + GitHub Action.
MIT -
MCP-native secret scanner in one fast Rust binary: engine, CLI, and MCP server. Finds API keys and secrets, skips known-public fixtures, verifies live keys with a real provider call, and applies env-var rewrites. Privacy invariant: the raw secret never leaves disk.
cargo MIT ★ 4 -
Envelope-encrypted team secrets your AI agent can use but never read. Zero dependencies, zero servers — your git repo is the backend.
npm MIT ★ 6 -
A standalone, boundary-only secret broker — reference a secret by name, the value is injected only at the execution boundary, never inside an LLM or agent context. Free and open source.
oci MIT ★ 2 -
Zero-knowledge .env proxy: phantom tokens in process.env, real secrets only at TLS edge for allowlisted hosts
npm MIT -
Zero-knowledge .env proxy: phantom tokens in process.env, real secrets only at TLS edge for allowlisted hosts
npm MIT -
MCP server that lets AI agents scan code, staged diffs and text for secrets with gitleaks. Findings are always redacted.
MIT -
Per-project secrets in local KeePassXC vaults, injected into commands without ever printing them. Agent-safe: PreToolUse guard hook + read-only MCP server. Single Go binary.
oci MIT ★ 5 -
npx-able MCP server for seekrit (https://seekrit.dev), a zero-knowledge secrets manager and credential broker for AI agents — let Claude Code and other MCP clients provision, manage, and inject secrets.
npm