"LinkedIn company profile pages" matching MCP servers:

Semantic search over Nordic economic data — market announcements, quarterly reports (162 companies), macro data (NO/SE/DK/FI), commodity prices, and press releases. 180,000+ vectors.

Persistent AI memory server with 3-layer hybrid search (vector + FTS5 + keyword), confidence scoring via Reciprocal Rank Fusion, episodic/profile memory, and 16 tools. Zero LLM dependency. Works standalone with Claude Desktop and Claude Code. MIT licensed.

Enables an LLM to maintain and query durable layered context across sessions, retrieving standing rules, current state, open loops, compiled pages, historical facts, and hard records with explicit conflict handling and abstention when nothing matches.

Persistent AI memory server with 3-layer hybrid search (vector + FTS5 + keyword), confidence scoring via Reciprocal Rank Fusion, episodic/profile memory, and 16 tools. Zero LLM dependency. Works standalone with Claude Desktop and Claude Code. MIT licensed.

Upload Word, Excel, PDF, or PowerPoint documents to a vector RAG store with vision-model extraction, then search semantically and retrieve chunks with page numbers for precise citations.

Enables AI assistants to search and retrieve information from Teleport documentation using a vector database. It provides a tool for semantic vector search over pre-populated embeddings of Teleport pages and examples to assist with technical queries.

Exposes a markdown knowledge base to MCP clients so they can search pages, fetch individual documents, and ask grounded questions that come back with numbered citations or a refusal. Retrieval is graded before answering, with a single query rewrite before giving up when nothing relevant is found.

A visual Retrieval-Augmented Generation MCP server that renders web pages, PDFs, and design screenshots into visual tiles and enables natural language querying over them via multimodal vision embeddings.

Enables RAG-based querying of local stock company data using a local LLM and vector database, providing tools to ask questions, search raw chunks, and list documents.

Enables AI assistants to interact with HubSpot CRM data, creating contacts and companies with duplicate prevention, retrieving company activity, active contacts and companies, and recent conversation threads. Built-in FAISS vector storage, thread-level indexing, and embedding caching provide semantic search over previously retrieved data to overcome HubSpot API limits and improve response times.

Enables AI assistants to interact directly with HubSpot CRM data, creating contacts and companies, retrieving company activity, active contacts/companies, and recent conversation threads, and running semantic searches over previously retrieved data. Built-in vector storage and caching overcome HubSpot API limitations while improving response times.

Enables semantic search and ingestion of investor content using Upstash Vector and Vercel Blob storage, with optional filtering by author, company, and date.