66 public tools: semantic search, queues, inboxes, webhooks, approvals, DNS, images, PDF and more.

Enables an assistant to search and read AtoM archival catalogue records, including their hierarchy, authority records, images and file text, and to propose improvements such as access points, relationships, descriptions, transcriptions and translations. Every proposal is queued for archivist review and nothing changes until approved.

Enables any MCP-compatible client to persist long-term memories for AI agents, with LLM-based fact extraction, semantic vector search, update/delete/list operations, and queue status checks across sessions.

Exposes tools that let an agent read a CV, search the Arbeitnow job board for Berlin AI/ML working student roles, score each vacancy against the CV, draft cover letters whose every claim cites CV facts, and queue them for human approval. The same tools can be driven from other MCP clients such as Claude Desktop, with scoring done deterministically in code and limits enforced outside the prompt.