"How to extract text from images" matching MCP servers:

Metis gives AI agents expert know-how that named reviewers have approved, and only where its recorded conditions match the situation. High-risk situations go to a person. When an agent sees practice depart from procedure, it can send the expert one short question. Every retrieval is recorded on a hash-linked evidence chain.

Connects to SlimSnap to provide recent screen captures as structured JSON data (text and annotations) for AI to read, avoiding screenshot limitations.

Self-improving, verifiable memory for AI coding agents. Learns how you work, stops repeating mistakes, models each project, recalls the right lesson at the right moment. Every memory is signed and tamper-evident. Local-first.

Semantic memory for AI builders: capture the tacit engineering know-how that never reaches your docs, recall it the moment it applies. Built in Rust on Postgres and pgvector.

A read-only MCP server that lets you search current and historical facts from a time-indexed knowledge graph derived from a folder of Markdown/text documents, with verification against original sources. It exposes tools for status, fact search, history search, and revision lookup while keeping document insertion and modification to the CLI.

Gives every AI agent working in a repository a shared, persistent knowledge graph stored in a plain JSONL file, with each entity, relation, and observation tagged with the date and agent that added it. Provides tools and prompts for searching, editing, renaming, merging, cleaning up, and exporting that memory, and keeps it locked to the repository that owns it.

Enables programmatic access to EndNote .enl libraries, allowing users to list, search, and extract full text from bibliographic references and their attached PDFs through MCP tools.

Semantic search over 4.6 million text chunks from 20,000+ classical philosophy and humanities works (pre-1928). Covers Aristotle, Plato, Kant, Hegel, Nietzsche and hundreds more. Multilingual: English, German, Latin, French, Italian, Greek, Russian.

Enables MCP clients to search, organize, and read preserved article text from a Linkwarden bookmark manager, supporting both read and write operations with safety confirmations.

Enables agents to check and retrieve concept-structured YouTube video summaries from the oratilo library via lookup and full-text search tools, avoiding redundant summarization work.

A lightweight knowledge base MCP server that enables full-text search and retrieval of markdown documents from indexed sites using Orama BM25.

Enables AI agents to build, populate, and search knowledge graphs by providing tools for entity extraction, relationship mapping, and graph traversal. It manages the underlying database infrastructure so users can create searchable knowledge bases from text through natural language commands.

An MCP server that allows AI assistants to search and retrieve human-curated content recommendations from Copus.

Provides read-only MCP tools to inspect imported history sources, list sessions, search literal text, and read paginated event history from a local SQLite index.

Provides local, scoped access to DEVONthink 3 on macOS, enabling search, reading cited text, following references, and previewing document organization from an AI assistant.

Analyzes GitLab group projects to extract purpose, I/O, dependencies, and database tables, serving this knowledge via MCP tools and a read-only HTML visualization.

A Model Context Protocol server that enables running Cypher queries and retrieving schema from Neo4j databases, supporting AI-driven graph exploration and text-to-Cypher workflows.

Enables AI agents to store, full-text search, and organize notes with tags.

Extract domain knowledge from codebases to reduce LLM token consumption by 20x and time in agentic search by 10x — gathers and makes concepts, naming conventions, and vocabulary queryable via MCP.

A codebase ontology and a cited wiki, both kept as Markdown in one folder on your disk. Typed graph answers — what a change affects, how two concepts connect, which wiki lines lack a citation — and every write lands as a Git diff a person reviews.