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

A simple MCP server implementation that demonstrates streaming capabilities with tools for greetings and notifications, accessible through an interactive command-line client.

Enables remote server control via SSH through Claude, supporting command execution, file transfers, and multi-server management with both standard and streamable HTTP protocols.

A starter MCP server using StdioServerTransport, providing example tools to check which app runs on a port (macOS) and add two numbers.

A read-only MCP server exposing SLURM, GPFS, Prometheus (node exporter + DCGM GPU metrics) and generic Elasticsearch exploration as diagnostic tools for LLM-based HPC support assistants.

Exposes any OpenAPI spec endpoints as AI agent tools via stdio, requiring no code generation or maintenance.

A simple MCP Server with shell execution capabilities that can be run locally with Ngrok tunneling or hosted in an Ubuntu 24 Docker container.

A server that provides MySQL database operations through SSE (Server-Sent Events) based on the MCP (Model-Controller-Provider) framework, enabling real-time data transmission from MySQL databases.

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.

A Python MCP server implemented from scratch, providing tool execution capabilities like system time and file hashing via stdio or HTTP transport.

Enables MCP clients to observe and, when explicitly enabled, send constrained input to whitelisted tmux sessions, with support for local STDIO and loopback-only HTTP transport behind an authenticated tunnel.

A Model Context Protocol (MCP) server that can be deployed locally via stdio or remotely via SSE/HTTP endpoints, supporting multiple MCP clients including VS Code, Cursor, Windsurf, and Claude Desktop.

External MCP server for controlling Orca worktrees, agent sessions, and multi-agent orchestration from any MCP client via stdio or Streamable HTTP.

A universal SQLite database management tool that enables SQL query execution through MCP protocol. Supports SELECT/INSERT/UPDATE/DELETE/CREATE operations with built-in SQL injection protection across stdio, SSE, and streamable-http communication modes.

Enables authorized penetration testers to run reconnaissance, web fuzzing, vulnerability scanning, brute-force/password cracking, traffic capture, privilege-escalation audits, wordlist generation, and client-report workflows over stdio, HTTP, or SSE with optional bearer/OIDC authentication.

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 building lightweight MCP servers where Rust handles transport, routing, and schema validation while Python defines tool behavior using type hints, with support for stdio and HTTP transports.

Enables authorized penetration testers to run reconnaissance, enumeration, vulnerability scanning, brute-force checks, traffic capture, and exploitation workflows via MCP tools, with STDIO/HTTP/SSE transport support. It also manages engagement records and generates client reports.

Enables professional penetration testers to run reconnaissance, exploitation, brute-force, traffic capture, and reporting workflows through stdio, HTTP, and SSE transports with auth and engagement record management.

Enables professional penetration testers to drive recon and exploitation tooling — including nmap, gobuster, nikto, John the Ripper, hashcat, subfinder, ffuf, nuclei, hydra, and sqlmap — over stdio, Streamable HTTP, or SSE transports with bearer/OIDC auth. Also supports wordlist generation, engagement record capture, and automated client report creation with scope-of-work handling.

Enables professional penetration testers to run reconnaissance, scanning, brute-force, exploitation, traffic capture, and reporting workflows through a unified MCP interface with STDIO, Streamable HTTP, and deprecated SSE transports plus bearer/OIDC authentication. Supports tools including nmap, gobuster, nikto, JtR, hashcat, subfinder, httpx, ffuf, nuclei, hydra, sqlmap, and wordlist generation.

Enables professional penetration testers to run reconnaissance, vulnerability scanning, brute-force checks, traffic capture, and client-report generation with stdio, HTTP, or SSE transports and optional bearer/OIDC authentication.

MCP server that executes caller-supplied Python code in a network-isolated, locked-down sandbox and returns stdout/stderr/exit code. Supports stdio, HTTP, and SSE transports with optional auth.

Exposes all CLI commands as MCP tools over stdio or HTTP transport.

Enables professional penetration testers to run reconnaissance and exploitation tooling—nmap, gobuster, nikto, John the Ripper, hashcat, subfinder, httpx, ffuf, nuclei, hydra, and SQLi extraction sweeps—alongside wordlist generation, engagement-record capture, and client report creation. Supports stdio, Streamable HTTP, and legacy SSE transports with bearer-token/OIDC authentication.

Enables authorized penetration testers to orchestrate reconnaissance, scanning, brute-force, traffic capture, wordlist generation, and reporting workflows via stdio, HTTP, or SSE with optional bearer/OIDC auth and structured engagement records.

Enables professional penetration testers to execute reconnaissance, scanning, brute-force, traffic capture, and reporting workflows through integrated tools with STDIO/HTTP/SSE transports and optional bearer/OIDC authentication.

Enables MCP-compatible clients such as Claude Desktop to interact with Juniper Junos network devices, exposing tools for running operational commands, applying and committing configuration changes with guardrails, and managing device connections over stdio or streamable-http transports. Supports password and SSH key authentication, connection pooling, and token-based access control for the HTTP transport.

Enables professional penetration testers to run and coordinate reconnaissance, scanning, brute-force, exploitation, traffic capture, and reporting tools through MCP, with stdio/HTTP/SSE transports and bearer/OIDC authentication.

Enables professional penetration testers to run reconnaissance, scanning, brute-force, exploitation, traffic capture, and reporting workflows through stdio, Streamable HTTP, or legacy SSE with bearer/OIDC auth.

Enables professional penetration testers to drive recon and exploitation tooling — nmap, gobuster, nikto, John the Ripper, hashcat, subfinder, httpx, ffuf, nuclei, hydra, sqlmap, and tcpdump — plus wordlist building and traffic capture from an MCP client. It also stores structured engagement records and generates client reports with scope-of-work handling, over stdio or authenticated Streamable HTTP (SSE deprecated).