Bundled connector that indexes Wikipedia articles so the engine can recall relevant passages from Wikipedia content in response to questions.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@passageway what do my connectors say about the Treaty of Versailles?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Retrieval for Claude over MCP. passageway indexes what your connectors report, finds the best short passages for a question with keyword plus embedding search, and serves them as one recall tool. It stays silent when nothing is relevant enough. It does no generation: the calling model reads the passages.
The core knows no source. A connector is any executable that lists items and returns their text as JSON Lines; anyone can write one. An eval harness (coming) measures retrieval quality on your own questions so you can publish the numbers.
Write a connector, the connector protocol and the Python SDK that does its plumbing
Bundled connectors: Wikipedia
For AI agents: skills and llms-full.txt; in Claude Code, /plugin marketplace add Marceltov/passageway gives you /create-passageway-connector
Documentation: the pages in docs/, will be published at https://passageway.marceltov.de.
Status: early. The engine started as the recall engine of trilium-recall and is being generalized. Licensed AGPL-3.0-or-later.
This server cannot be deployed
Search your knowledge bases from any AI assistant using hybrid RAG.
Search and retrieve permission-aware knowledge from connected sources through Remly.
Read-only search of your Sortio knowledge graph (files and entities) for Claude and ChatGPT.
Connect your team's living knowledge base — docs, data, issues, CRM — to Claude and ChatGPT.
