"MCP servers with SSE endpoints" matching MCP servers:

Enables AI agents to perform dynamic and reflective problem-solving through a chain of thoughts, allowing them to break down complex problems, revise past thoughts, and explore logic branches before reaching a conclusion.

MCP server for the CortexCloud API, enabling pay-per-call AI generation, web search, market data, and blockchain RPC endpoints via the x402 protocol, billed in USDC on Base without API keys or subscriptions.

Search 60,000+ AI agent skills from ClawHub, LobeHub, Dify, and GitHub via MCP SSE or REST API. Free, no API key required.

Enables image analysis, OCR, and text-to-image generation through OpenAI-compatible APIs. Supports local paths, URLs, or base64 images with configurable models and backup endpoints.

Provides access to Agno framework documentation for AI agents, enabling search and retrieval of SDK references, API endpoints, code examples, and integration guides through MCP-compatible tools.

An MCP server that automates importing products from AliExpress, Alibaba, and Accio into DSers and pushing them to Shopify or Wix stores, with features like bulk import, pricing rules, and title cleanup.

Provides a sequentialthinking tool for dynamic, reflective problem-solving via chain-of-thought reasoning. Supports local Stdio and remote SSE deployment on Google Cloud Run.

A FastMCP server that exposes mem0 long-term memory to MCP clients over SSE, enabling AI agents to store and recall facts persistently.

Probe LLM API endpoints and report health metrics including time to first token, latency, and throughput.

Provides access to 9 AI executives offering board-ready business intelligence, competitor analysis, trend monitoring, and more via agent-payable endpoints.

Long-term and multimodal memory for AI agents. Store facts and conversations with add_memory, recall them with search_memories — 8 tools over stdio/SSE/HTTP. Per-character memory isolation, LLM-based semantic deduplication, FAISS + JSON storage, and a fully local option (Ollama, no API key). Drop-in compatible with Mem0.

An MCP server providing vision understanding tools (image QA, OCR, video and document understanding) via OpenAI-compatible endpoints, defaulting to Zhipu GLM vision models.

Enables AI agents to make decisions by calling the Kev pointer-head model's evaluate, permute, separate, and model-listing endpoints through four stdio-based tools.

Enables image generation and editing as MCP tools, abstracting tai-openapi's endpoints and returning images directly without relying on local URLs.

MCP server that adds vision capabilities to text-only AI models by sending images (local files, URLs, clipboard, screenshots) to a vision model and returning text descriptions.

Lets Claude Desktop, Claude Code, Cursor, and other MCP clients send messages to any external AI bot over an HTTP webhook and fetch the bot's answer back into the chat. Replies can arrive in the webhook response body, by polling a reply URL, over an SSE stream, or by posting to a local inbox, with tools for sending, reading, and waiting on threaded replies.

Enables chat completions, embeddings, and model listing through an OpenAI-compatible interface. Supports configurable public or custom Uplink endpoints, per-bot API keys, and MoE/fallback policies.

Lets AI clients call paid x402ai endpoints — embeddings, summaries, and short answers — paying per call in USDC on Base via the x402 protocol, with per-payment and per-session spend caps plus a free inspector for decoding any x402 endpoint's payment challenge. Runs locally over stdio, needs no hosted account, and can operate in quote-only dry-run mode.

Enables agents to query live artificialanalysis.ai data — leaderboards, model digests, benchmarks, pricing, cost-per-task, speed, provider endpoints, and image/video/speech/music arenas — through token-efficient table tools that need no API key. It works from the site's public RSC payloads by default, with an optional JSON-API backend (and automatic fallback) for capability and coding/agentic indexes.

Enables coding agents to ask what a window shows and receive a concise JSON answer from a local Ollama model instead of ingesting the full accessibility tree, reducing token usage. It is read-only and supports optional session context, health checks, and model release.

Enables storage, versioning, and retrieval of prompts with rich metadata via MCP tools, supporting stdio and SSE transports.

A local MCP bridge that registers multiple AI API endpoints, enabling agents to automatically discover and route to models based on capabilities like chat, vision, reasoning, embedding, image generation, TTS, STT, and rerank.

Enables MCP clients to call the platform's full API as individual tools—covering evals, criteria, gates, logs, datasets, aliases, label sets, audit/proving, dedicated endpoints, and training—with validated inputs and raw API responses.

Enables deterministic, read-only construction of Seedance-oriented video prompts, planning of multimodal reference-aware sequences, prompt diagnosis, and discovery of canonical See Dance 2 resources.

Provides fast static embedding, similarity, and search capabilities via MCP tools and an OpenAI-compatible HTTP API using a tiny 16M-parameter English embedding model.

MCP server that lets AI assistants interact with ChatGPT Web via browser automation, enabling chat, web search, file/image attachments, and model selection.

Lets any MCP host or OpenAI-compatible client chat with Meta's Muse (muse.ai Hatch) agent by driving your own logged-in Chrome, exposing tools for status, login, new chat, prompting, and reading replies. It also serves an OpenAI-compatible HTTP endpoint with real SSE streaming and prompt-injected tool calling, plus a small CLI for one-shot generation.

An MCP server that exposes governance, trust-scoring, compliance, guardrail, cost, drift, and supply-chain scanning tools and resources to any MCP client over stdio, Streamable HTTP, or legacy HTTP+SSE. It lets agents route every tool call through a deterministic five-way decision (allow, redact, require approval, deny, or quarantine) with hash-chained evidence, human approval workflows, and in-agent trust gates for LangChain, LangGraph, and Google ADK.

Production Model Context Protocol (MCP) server for business — replaces stale generic descriptions with concrete 2026 technical intelligence and data agents. Exposes dynamic KPI analytics, forecasting, anomaly detection, and schema resources across 10 enterprise domains via FastMCP over stdio and SSE transports.

A TypeScript-based MCP server that integrates with Swagger/OpenAPI specifications to expose API endpoints as tools for Large Language Models (LLMs), enabling natural language interaction with any OpenAPI-compliant API.