"A tool for reading and recognizing image content using MCP" matching MCP servers:

A custom MCP tool that integrates Perplexity AI's API with Claude Desktop, allowing Claude to perform web-based research and provide answers with citations.

Provides content agents with structured search over editorial guidelines, visual templates, and past post outcomes, enabling auditable proposals that cite rule IDs.

Read-only MCP server for Ghost sites that enables AI assistants to search, summarize, and read content via hybrid lexical and semantic ranking.

A universal MCP tool gateway that manages multiple remote tool processes, enabling LLMs to dynamically invoke web scraping, summarization, and knowledge retrieval through standardized Function Calling.

An MCP proxy that embeds tool definitions and returns only the top-k semantically relevant tools per query, reducing context usage and routing calls to upstream MCP servers.

Graph-based tool retrieval for LLM agents. Builds a tool graph from OpenAPI/MCP specs and retrieves multi-step workflows via hybrid search (BM25 + graph traversal + embedding), recovering accuracy from 12% to 82% with 79% fewer tokens. Also works as an MCP Proxy to aggregate multiple servers behind 3 meta-tools.

A Model Context Protocol server that provides Claude with a dedicated space for structured thinking during complex problem-solving tasks, helping improve its reasoning capabilities.

Enables local Vietnamese ecommerce copy preparation, source-grounded RAG retrieval, offline voice previews, correction-memory feedback, hook review, and fine-tuning dataset preparation without publishing posts or approving audio.

Enables agents to send only the handful of tool definitions relevant to each question, ranking a large catalog by keywords and optional embeddings to cut context cost and wrong-tool picks. It can also run in front of any mcpServers config as a proxy that exposes just search_tools and call_tool instead of the whole catalog.

Enables agents to search across the pooled tools of many connected MCP servers and invoke them through a single endpoint, returning only the handful of tools relevant to each request. Filters by the caller's permissions before ranking, so agents never see or plan around tools their user is not allowed to use.

MCP server that enables persistent, hybrid, local memory for LLM agents, with vector + BM25 search, knowledge graph, and policy-driven retention, providing token-budgeted context injection for AI assistants.

An MCP (Model Context Protocol) server that chains calls to other MCP tools, reducing token usage by allowing sequential tool execution with result passing

Enables dynamic tool discovery and loading for Claude using BM25, regex, and semantic search algorithms. It supports managing a catalog of over 10,000 tools with minimal context overhead and provides a REST API for tool management.

Enables any MCP-compatible AI assistant to search, filter, and retrieve information from a local document collection using a hybrid search pipeline with vector, BM25, reranking, and LLM enrichment.

Provides an intelligent, graph-based memory system for LLM agents using the Zettelkasten principle, enabling automatic note construction, semantic linking, memory evolution, and autonomous graph maintenance with background optimization processes.

Enables MCP-compatible clients to perform retrieval-grounded Q&A over FordA dataset notes and safe arithmetic calculations through callable tools.

Exposes search over internal documents and company lookup via authenticated API, enabling LLMs to access firm files and data.

Read-only MCP server for a content contract layer: protocol, modules, pipelines, assets, library. 一句话 / One-liner（ZH）：给任何 AI agent 一个可校验的内容规范与资产底座——先查契约，再落笔。 描述 / Description：只读 MCP 服务器：把长内容的验收标准（协议 / 模块 / 管线 / 资产 / 馆藏）变成 agent 可调用的检索与取件工具面。10 个只读工具 + 1 个 prompt（assemble_guide）；支持 modern 2026-07-28 与 legacy 2025-11-25 双协议；零第三方依赖（Python 标准库）；无写路径。 仓库 / Repo：https://github.com/Monyeah777/NinFenz 站点

A server that leverages Cloudflare Browser Rendering to extract and process web content for use as context in LLMs, offering tools for fetching pages, searching documentation, extracting structured content, and summarizing content.

MCP for Azure DevOps Boards is a MCP server that lets your favourite AI browse, query and update Azure DevOps work items as if it were a project manager. Written in Rust and optimized for tokens usagem, It runs via stdio or HTTP mode and uses standard Azure authentication with az login.

Stores Organizations content

A proof of concept MCP server for Apache OFBiz

Builds searchable SQLite databases from PDFs, preserving inline image locations for AI agents to discover and caption visual content. Supports full-text search over text, image placeholders, and saved captions.

A Python-based MCP server that enables document-based question answering by processing PDF, TXT, and Markdown files through OpenAI's API. It provides hallucination-free responses based strictly on document content using semantic search and includes a web interface for management.

Production-ready MCP server providing RAG, hierarchical memory, and 8+ tools for AI agents via the Model Context Protocol.

Enables asking questions and performing semantic searches against an Inkeep knowledge base. Deployable to Vercel with Next.js.

Turns any static website into an MCP-searchable knowledge base by deploying a Cloudflare Worker that provides full-text search tools, enabling AI assistants to search and retrieve content from your site.

Transforms prompts into Chain of Draft (CoD) or Chain of Thought (CoT) format to enhance LLM reasoning quality while reducing token usage by up to 92.4%, supporting multiple LLM providers including Claude, GPT, Ollama, and local models.

Enables local data discovery by indexing metadata from SQLite, CSV, and Markdown sources, providing hybrid keyword and TF-IDF semantic search via MCP tools (listSources, indexSource, search, getSchema) and a REST API.

Provides a Google search tool via the Serper API, returning structured results and a summary answer for LLMs like Claude.