"browser use" matching MCP servers:

Gives every AI agent you use one shared, versioned memory in a local SQLite file, so a fact saved from one app is found by all the others. Runs fully offline with no API key, records which agent wrote each change, and keeps every prior version so nothing is silently overwritten.

Serves UltraRAG memory to agents over stdio MCP, providing project-local and per-user global memory. It lets agents read and append standing memory and daily dialogue rounds in UltraRAG's format, with an optional browser view.

Turns a tools.yaml contract into typed, tenant-guarded vector database tools that agents can use via Python imports or MCP.

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.

A focused local-paper RAG MCP server that imports PDFs, indexes them into SQLite and ChromaDB, and retrieves section-aware paper chunks for use with Claude Code, Codex, or any MCP client.

Enables Claude to index and retrieve context from codebases using self-hosted Milvus for semantic search, with hardened reliability and security for production use.

Enables indexing a folder of documents or uploaded files into a Qdrant vector store and retrieving relevant chunks with cosine similarity, metadata filters, and heuristic reranking. Exposes rag_stats, rag_search, and rag_index tools over HTTP and Streamable HTTP MCP so clients can fetch ready-to-use context blocks without any built-in chat model.

An archived, unsafe MCP server with critical security vulnerabilities, classified as a pump and dump operation. Do not use in production.

Enables MCP clients to discover and use an AI-KIDO knowledge base via literal, regex, and local semantic search, document/resource access, embedding generation, and index management. It also provides scoped file and Git operations for a separate writable project/fork while keeping the standard base protected.

Enables venues to discover taste-matched acts and artists or agents to find fitting rooms and cities through Qloo's taste graph. It exposes booking-focused tools for agent use over a remote MCP endpoint.

Exposes a layered long-term memory store — persistent self blocks, four-tier scoped retrieval, knowledge graph, and signed knowledge capsules — over stdio so any MCP-capable client can use the same 15 memory tools and shared ACL. It lets Claude Desktop, IDE agents, and custom orchestrators mount that store without depending on the DeepSeek Harness runtime.

Enables MCP clients to discover, list, and call browser-demo tools for SQL-like queries, vector and hybrid search, agent memory, and evidence-ledger operations over a stateless HTTP endpoint.

Enables MCP clients to index code repositories and run AST-aware semantic and hybrid keyword search across files, commits and branches, returning relevant code snippets with expanded file context. It handles incremental re-indexing with local embeddings and Qdrant storage, and can serve either over stdio or as a bearer-token-protected HTTP endpoint for remote or containerized use.

Pay-per-use semantic memory for AI agents with cryptographic attestation. Vector embeddings with SHA256 commitment, secp256k1 signature, and Lightning invoice.

Kollektiv

Enables semantic search across browser bookmarks from Chrome, Firefox, Edge, Opera, and other browsers using natural language queries. Extracts and indexes bookmark content and metadata into a vector database for intelligent retrieval.

Enables AI agents to use a neuro-symbolic memory fabric with bi-temporal knowledge graph and holographic VSA, providing tools for adding, searching, temporal queries, auditing, and proving memories with cryptographic provenance and zero-LLM ingest.

Enables Claude Code to use a self-hosted persistent memory layer backed by Qdrant, Neo4j, and Ollama, with Anthropic or Ollama as the main LLM. It provides MCP tools to add, search, update, delete, and graph memories across sessions.

Enables Claude Code to persistently remember and retrieve project context across sessions, manage stored memories and entity relationships, and use vector and graph storage with a local or API-backed LLM.

Enables LLM-based agents to perform full CRUD operations on FHIR resources, process clinical documents, and use semantic search through MCP-compatible clients using natural-language prompts.