"Semantic Web" matching MCP servers:

Enables any MCP client to query DeepSeek's web chat, including its built-in live web search, with no separate search API, provider account, or extra cost. Also supports continuing chat sessions, uploading local files as prompt attachments, and automatic token re-harvesting from a logged-in browser profile.

Enables agents to interact with a governed semantic layer for querying and authoring metrics, providing tools for discovery, planning, validation, and execution of analytics queries.

Enables agents to deduplicate semantic prompt caches by measuring Jaccard token overlap, preventing redundant LLM calls and reducing cost. It provides deterministic lookup-or-insert cache behavior through an MCP-compatible interface.

Enables estimating LLM hallucination and confabulation by clustering sampled responses into semantic equivalence classes and computing semantic entropy. It provides a plug-and-play validation filter for agent pipelines using the MCP protocol.

Enables detecting LLM hallucinations and confabulations by clustering sampled responses into semantic equivalence classes and computing semantic entropy.

Enables LLM agents to make fast semantic decisions by choosing one of 2–16 options with probabilities, via tools for single and batch classification.

Enables AI agents to store, search, and recall semantic memories with three memory types (semantic, episodic, procedural) and auto-consolidation, compounding intelligence over time.

Embedding space analysis toolkit that measures semantic drift, traces trajectory dynamics, and projects passages onto caller-defined semantic axes, exposed as MCP tools for agentic integration.

A local MCP/CLI tool that uses a Chrome profile with an active ChatGPT web session to submit image generation prompts and return saved images as MCP content.

Enables MCP clients and a terminal CLI to run web searches through a user's own SearXNG instance, saving every query as a reusable session and optionally generating AI-synthesized answers.

Enables AI agents to generate text, images, and videos via Grok's web UI using MCP tools (grok_chat, grok_generate_image, grok_generate_video) without an API key.

Enables agents to store LLM query-response pairs and retrieve them via fuzzy cosine similarity matching, reducing duplicate inference calls; it exposes tools for setting cache entries, semantic lookup, and hit-rate statistics.

Provides web and image search using the Doubao (Volcengine) API with configurable parameters.

Enables Codex to interact with Gemini Web through browser automation, allowing it to ask scoped questions and analyze public URLs or YouTube videos without a Gemini API key.

Enables agents to deduplicate semantic prompt cache entries by calculating Jaccard token overlap, reducing redundant LLM calls and cost.

Five-layer agent memory over MCP. zenbrain_store routes each memory: steps to a procedure, emotional weight to an episode, high confidence to a pinned core memory, the rest to a semantic fact. zenbrain_recall returns results with id and layer; zenbrain_forget deletes one plus what consolidation linked to it; zenbrain_consolidate runs one sleep-like pass. Local SQLite, no account, no network call.

Provides AI assistants with real-time web search, reasoning, and research capabilities through Perplexity's Agent API and Search API, enabling tools for search, conversational Q&A, deep research, and advanced reasoning.

Official MCP server for the Perplexity API Platform, enabling AI assistants to perform real-time web search, reasoning, and deep research using Sonar models.

Official MCP server for Perplexity API Platform, enabling AI assistants with real-time web search, reasoning, and research capabilities through Sonar models and the Search API.

Enables AI agents to hand high-level objectives to a decision-making core that autonomously reasons, plans, enforces deterministic policy, executes capabilities, evaluates outcomes, and persists semantic memory over stdio or Streamable HTTP.