"Information about enclave-gateway" matching MCP servers:

Governed MCP server (stdio & HTTP) and CLI orchestrator for isolated network enclaves: routes commands, 4 MiB delta file transfers, and TCP tunnels through a QEMU Windows VPN Appliance and an RDP Bastion (\tsclient) to multi-hop SSH target nodes, with policy-controlled routing, command guard, secret scrubbing, and hash-linked audit logs.

Enables AI agents to request passwords, API keys, passkeys, and other secrets from a person through one-time links encrypted in the browser, then store them in a local vault the agent can use without ever seeing them. Secrets can be referenced in commands and outputs are redacted, so agents can sign in or call APIs without exposing credentials in chat.

Static scanner for MCP/agent-gateway readiness anti-patterns, providing a 7-dimension R/Y/G score by scanning code and config for common failure modes.

Exposes Jira task management (list, create with two-step confirmation, start) to AI agents while keeping credentials hidden, and deliberately does not handle git operations.

Enables AI agents to discover and query enterprise knowledge documents and business metrics through standardized MCP tools, supporting retrieval, structured sales/order analysis, anomaly scanning, and data lineage lookups.

A Windows-native MCP gateway that lets any MCP-capable host orchestrate local coding-agent CLIs as external workers.

This server enables AI-assisted APK reverse-engineering entirely on-device, orchestrating jadx, apktool, adb, frida, and APKiD through a job/workflow engine, and exposing those agents as native MCP tools for Claude without any cloud dependency.

Unified MCP and skill management gateway for AI agents, enabling tool discovery, installation, and sharing with 99% context token savings.

AI gateway to unify authentication and expose internal APIs as MCP tools. Supports SSO, JWT, and basic auth with auto-refresh.

A single local MCP gateway for Neo4j that exposes both proxied generic Neo4j tools (schema, Cypher, GDS) and custom YAML-defined use-case tools behind one stdio endpoint.

Enables LLM agents to control Bambu Lab 3D printers via the bambu-gateway HTTP API, supporting printer listing, filament management, print session creation, and safe print initiation with user confirmation.

Enables AI agents to run local, deadline-aware format and PII checks before acting, with an optional safety classifier that runs only when suspicious text can be checked in time. It provides allow/redact/block verdicts plus status and load-simulation tools for MCP clients such as Claude Code and Cursor.

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.

Enables AI agents to place spot market orders on a paper or ccxt exchange account only when the trade fits a pre-registered mandate, sealing a hash of the agent's rationale into a tamper-evident trace and reconciling the authorized intent against the actual fill. It also exposes the mandate, quotes, balances, and trade trace/journal records as tools, failing closed whenever policy checks are unreachable.

Recordist writes notes from your calls on your laptop, with no bot in the call. Its open-source MCP server lets Claude, Cursor and other assistants search every call, open a meeting's notes and transcript, list the action items and draft the follow-up from what was said. What it returns goes to the assistant you connect. Get Recordist: https://recordist.app/download. MIT licence.

A local MCP gateway that aggregates multiple downstream MCP servers behind a single connection, with hot-reload via HTTP admin API or file-watcher and support for large payloads.

Global MCP router and gateway for Cocos Creator, connecting Codex, Claude Code, and other stdio MCP clients to project extensions for offline Prefab querying and project snapshots.

Serves as a lazy-loading proxy for multiple MCP servers to prevent tool schema bloat and reduce context token usage. Exposes 4 lightweight gateway tools that start backend servers on demand rather than loading all schemas at startup.

A local MCP gateway that allows AI clients to manage and interact with multiple MCP servers through a single connection, providing token-efficient access to tools and resources.

A FastAPI + FastMCP shared-memory gateway in front of Honcho v3 that provides a single shared brain for multiple AI agents to read from and write to, enabling context recall and change logging through bearer-authenticated endpoints.

Enables users to run shell commands with compressed output, extract information from large files, drive local opencode and Codex agents, perform browser-automation tasks, and monitor runs via a live dashboard.

Enables secure interoperability between LLM agents and MCP tool servers by sanitizing requests and responses, masking sensitive tokens, detecting PII, and performing server reputation scans.

Exposes an OpenAI- and Anthropic-compatible HTTP, SSE, and stdio gateway that wraps multiple subscription CLIs, adding prompt-injection defense, PII redaction, cost-aware routing, and reasoning-trace capture for MCP-compatible clients like Claude Desktop and Cursor.

A stdio or localhost/Tailscale HTTP MCP server that lets outside coding agents list and message your signed-in Desktop bots, read and wait on replies, check status, and reach a Tailscale-connected Linux VM over SSH using scoped, expiring gateway tokens.

A lightweight MCP gateway that aggregates multiple MCP services into a unified stdio interface, automatically prefixing tool names with the service name to avoid conflicts.

Exposes MCP tools that give desktop agents durable two-tier memory with recall and graph traversal, project code intelligence (symbol lookup, impact walking, notes search), and web search with page-to-Markdown conversion. It also runs a local model gateway that routes Anthropic- and OpenAI-shaped traffic across providers with usage accounting.

Enables secure, auditable access to Home Assistant through MCP, with a read-only observer profile and an operator profile for controlled mutations.

Acts as an intermediary between LLMs and other MCP servers, centralizing management, sanitizing sensitive information, and providing a unified interface for discovering and interacting with proxied MCPs.

MCP server that enables AI agents to simulate EVM bytecode and probe capabilities, serving as a gateway to an Ethereum execution engine.

Enables AI clients to connect through a single multiplexed SSE/HTTP endpoint to multiple local and remote MCP servers, with token authentication, per-tool approval policies, tool namespacing, and live telemetry.