"Finding MCP servers that support SSE or Streamable HTTP, excluding stdio transport" matching MCP servers:

Local stdio proxy for Uno MCP Gateway that enables MCP clients without OAuth support to securely connect to authenticated remote servers.

Enables authenticated users and service accounts to discover and invoke tools from a wrapped third-party stdio MCP server behind a secure gateway, using per-profile credentials, role/default routing, and managed child instances.

Enables LLMs to make HTTP requests with OAuth2, session cookies, retry logic, and cURL command generation, while providing security features like SSRF protection and TLS enforcement.

Enables users to analyze HTTP response headers of any URL for security and configuration, returning a 0-100 security score, HSTS/CSP and header checks, server detection, caching details, and recommendations. Supports pay-per-call access via x402 micropayments.

An MCP server over Streamable HTTP that exposes two SAP help-desk operations to an AI agent: sap_reset_password and sap_unlock_users.

Enables support engineers to analyze tickets against a help center with cited retrieval, role-gated and human-confirmed actions, and safety-gated evaluation.

Enables read-only lookup of support tickets and ticket lists through two tools, returning only bounded fields like ID, status, title and note. Tenant filtering and argument validation confine every read to the configured organization, with denied access and upstream failures surfaced as explicit results.

Implements a Model Context Protocol server using Server-Sent Events for real-time communication with OAuth 2.1 integration via Ory Network, enabling secure AI model communication with authentication and client management.

Analyze and score HTTP security headers (CSP, HSTS, CORS, cookies) with actionable fix recommendations for web applications.

Enables authenticated MCP clients to list, read, prepare, and create support tickets through the existing HTTP API, with OAuth verification, company isolation, and safe write retries.

Protects AI support tools with Descope JWT authentication and scope-based authorization, enabling secure customer support operations like refunds with granular access control.

Bridges stdio-based LLM harnesses to OAuth-protected remote MCP servers via Streamable HTTP, handling PKCE browser login and token refresh automatically.

Enables customer support agents to answer order-related queries with minimal data exposure, returning only necessary fields and sanitizing logs.

Enables a role-aware customer support chat for an online course platform, letting learners, support agents, and admins perform scoped actions such as viewing courses and payments, managing tickets, extending access, issuing certificates, and viewing stats.

Enables network security scanning using Nmap through MCP protocol. Supports quick port scans, full port scans with service detection, and custom Nmap commands with async task management.

Enables secure execution of penetration testing commands on Kali Linux through Server-Sent Events with intelligent command validation, real-time monitoring, and comprehensive audit logging. Designed for authorized security research and penetration testing workflows.

This server gives AI assistants controlled read and write access to a Firefly III personal finance instance over MCP, exposing 139 operations across 24 entities with optional read-only mode and support for both stdio and authenticated HTTP transport.

Interact with Descope's Management APIs to manage users, audit, and more.

Enables Nest applications to expose decorated provider methods as MCP tools, resources, and prompts over Streamable HTTP or stdio, with Nest guards, interceptors, pipes, filters, OAuth 2.1 resource-server support, and an in-memory test client.

Enables deploying a secure MCP gateway that proxies, sandboxes, and policy-governs third-party MCP servers, with credential vaulting and audited tool access across stdio, SSE, and Streamable HTTP.

Enables authorized penetration testers to run reconnaissance, scanning, brute-force, exploitation, traffic capture, wordlist generation, and client-report workflows through MCP clients, with stdio/HTTP/SSE transport and OIDC bearer authentication.

Enables content moderation by checking user input against OpenAI's moderation API via Google ADK, with dual SSE/STDIO transport support and integration with local LLMs.

Aggregates multiple backend MCP servers (Stdio, SSE, and Streamable HTTP) into a single hub, exposing their combined tools and resources through unified SSE or Streamable HTTP endpoints, or as a Stdio server, while routing requests to the correct backend. Adds API-key/bearer-token endpoint security, per-tool enable/disable and renaming, and an optional web admin UI with live config reload, install monitoring, and a web terminal.

Enables MCP clients to expose selected JumpServer 3.10.15 REST API operations as tools over Streamable HTTP or SSE, with configurable read-only filtering and separate inbound/upstream authentication.

Next.js-based MCP server with OAuth 2.1 authentication, deployable on Vercel, supporting SSE and Streamable HTTP transports for various clients.

Enables building MCP servers with Mosaic sign-in, streamable HTTP transport, OAuth discovery, token authentication, and per-call logging.

Enables professional penetration testers to run authorized reconnaissance, scanning, exploitation, and reporting workflows through MCP tools such as nmap, ffuf, nuclei, hashcat, and report generation, with STDIO/HTTP/SSE transport and bearer/OIDC auth support.

Enables AI agents to inspect, reverse engineer, decompile, and operate on binaries through IDA Pro, including headless and GUI sessions, over stdio or Streamable HTTP.

Minimal demo of Entra ID authentication with MCP and HTTP+SSE transport, using session mapping with JWT-like tokens.

A fail-closed policy boundary that translates local stdio MCP clients to authenticated Streamable HTTP servers, enforcing allowlists or read-only modes and redacting credentials from audit trails.