"FIRST" matching MCP servers:

Enables querying Microsoft Entra first-party application scope metadata, including searching applications by name, ID, scope, and FOCI/public-client status.

Provides Microsoft Entra ID / Graph permissions data to AI agents, enabling search and retrieval of application and delegated permissions as well as Microsoft first-party app details.

Local-first encrypted key-value vault for securely storing and retrieving secrets like API keys using AES-GCM 256-bit encryption and a PIN.

A local-first MCP policy gateway that provides a four-step workflow (plan, approve, execute, read) for a single Apify fixture Actor, enforcing a fixed policy and sanitizing results. It does not call Apify and is designed as a policy control plane.

Enables policy-first defensive security operations for MCP, providing repository and web-security analysis with controlled authorization, scoped execution, and auditability.

A local-first secrets vault for MCP clients that lets AI assistants use secrets by injecting them into child processes, without the plaintext ever entering the model's context.

Local-first Gmail MCP server using PKCE + loopback OAuth flow that stores refresh tokens in the OS keychain, enabling secure read/write Gmail access via MCP tools without tokens leaving the device.

Local-first MCP server for per-agent key management, generating and using signing keys without external KMS.

Enables local-first governance preflight for MCP production, including plugin discovery, fail-closed policy evaluation, message validation, budget previews, and payload-free audit receipts without executing or proxying plugins.

Safety-first local MCP tool gate with control plane, runtime security, and observability for managing MCP backends.

Security-first MCP gateway for Odoo 17/18/19 — 27 tools, YAML-driven security

Privacy-first, tamper-evident receipts for MCP tool calls. It hashes and signs arguments/results so you can verify what ran, when, without storing raw payloads.

The official WhoisXML API MCP server: 32 first-party tools for WHOIS, DNS, IP geolocation, threat intel, typosquatting, email verification, and native bulk — in Claude, Cursor, VS Code, or any MCP client.

Local-first MCP audit and cleanup tool that scans MCP configs to find stale servers, abandoned packages, duplicates, context-heavy tools, risky permissions, and major upgrades, generating reversible patch plans.

Secure, local-first collaboration layer for AI agent teams, enabling authenticated agent-to-agent communication, shared memory with provenance, and scoped service execution through MCP.

Local-first CLI and MCP server for redacting sensitive text before sharing logs, configs, and errors with AI tools.

Enables developers to build production-grade MCP servers with secure defaults, validated inputs, and CI security audits from the first commit.

A security wrapper for MCP servers that provides trust-on-first-use pinning, guardrail scanning, and protection against prompt injection attacks. It acts as an intermediary layer to ensure universal compatibility and secure enforcement of server configurations across various MCP host applications.

An open-source MCP server that provides AI agents with secure access to read, search, and manage emails via Microsoft 365 and Gmail. It features security-first defaults like recipient allowlists and markdown content conversion to facilitate safe agent interaction with mailboxes.

A local-first memory vault MCP server for Windows that exposes an encrypted user memory store to agents via a permission-brokered protocol, ensuring user ownership and control over browsing data.