"Connecting to Gemini Flash Experimental" matching MCP servers:

An MCP server that sends plain-text Gmail messages only to a predefined allowlist, using generated recipient IDs instead of email addresses to enforce security.

Enables local inspection of AI model deployment artifacts without executing model code, returning SHA-256, structure, defect analysis, and evidence-gap findings in Gemini CLI conversations.

Enables checking a verified email for breach exposure and querying SHA-1 password hash prefixes through read-only tools that return concise evidence summaries.

Enables AI agents to access only task-relevant data with secrets hidden and personal details pseudonymized, while enforcing destination policies to prevent data leakage even under prompt injection.

Enables ADK agents and Gemini Enterprise connectors to use Google SecOps OneMCP tools by stripping oversized input/output schemas from tools/list responses so Vertex AI accepts the function declarations. It forwards JSON-RPC 2.0 calls to OneMCP, preserves all 71 tool names and descriptions, and enforces Cloud Run IAM with OIDC while passing through the caller's OAuth token.

A neutral, public danger grade for MCP servers that AI agents rely on, providing A-F grades and transparency signals to vet servers before connecting.

MCP server for connecting to SQL Server in readonly mode. Allows any MCP client to explore the schema and run SELECT queries against a SQL Server database.

Automates Android app analysis using Frida via AI commands, connecting a rooted Android phone to a computer and running dynamic analysis scripts without manual command execution.

Enables AI assistants to manage software licenses through natural language commands by connecting to the ExisOne licensing platform.

MCP server for checking supply-chain trust before connecting to AI agents, frameworks, or MCP servers.

Encrypts local Claude Code and Google Antigravity sessions out of their history and locks chosen ChatGPT, Claude.ai and Gemini web chats behind Touch ID or a passphrase. Any MCP client can hide, list, unlock, read and restore those hidden sessions through its tools.

Local MCP server for macOS that scans AI coding tool history (Claude Code, Cursor, Copilot, Cline, Codex, Gemini CLI) for leaked secrets. Finds API keys in chat transcripts, redacts with sieve:// placeholders, and runs commands with Keychain-injected secrets - no plaintext values ever returned.

Open-source guardrails between AI agents and FHIR clinical data — PHI redaction, immutable audit, step-up auth, tenant isolation. MCP server + OpenAI/Gemini adapters. A healthclaw.io project.

Enables natural language querying of Tanium assets, vulnerabilities, patches, and deployment information through the Tanium Gateway GraphQL API, integrating with MCP hosts like Claude Desktop, Cursor, VS Code, and Gemini CLI.

A high-performance MCP server for Ubiquiti UniFi Dream Machine (UDM Pro/SE) and UniFi OS Cloud Gateways, connecting directly to the local REST API using native API keys to provide 40 tools for managing Wi-Fi, VLANs, firewall rules, port forwarding, switch ports, guest vouchers, QoS, clients, and devices—all with 2FA bypass and ultra-low latency.

Enables detection of AI-generated content from ChatGPT, GPT-4, and Gemini models through the BACH AI Content Detector API.

Enables AI-assisted vulnerability management by connecting Claude Desktop to local Nessus and Tenable Vulnerability Management, allowing natural-language queries for scan management, threat intelligence enrichment, and prioritized remediation planning.

Connect AI agents like Claude, Cursor, and Gemini to historical Windows performance and privacy data gathered by the AppControl Windows app. This server enables natural language queries into CPU, GPU, and temperature history alongside system security events for deep local auditing.

Enables connecting Postgres databases to MCP clients with built-in query and inspection tools, custom parametrized SQL tools, scoped API keys, group permissions, and audit logging.

Enables AI agents to propose structured payment intents, apply deterministic policy, require human approval, and record tamper-evident audit trails without connecting to live payment rails.