Home › Knowledge & Memory › Cathedral — Persistent Memory for AI Agents
Cathedral — Persistent Memory for AI Agents
Persistent memory and drift detection for AI agents across session restarts.
Connect
Review any command before running it. Package names and URLs come from the server's own registry entry.
Remote (streamable-http)
https://cathedral-ai.com/mcp Requires auth (checked 2026-09-24)
Claude Code:
claude mcp add --transport http cathedral https://cathedral-ai.com/mcp --header "Authorization: <YOUR_VALUE>"
Or add to your MCP client config:
{
"mcpServers": {
"cathedral": {
"url": "https://cathedral-ai.com/mcp",
"headers": {
"Authorization": "<YOUR_VALUE>"
}
}
}
}
Authorizationsecret
Package (pypi 1.1.0)
uvx cathedral-mcp
Or add to your MCP client config:
{
"mcpServers": {
"cathedral": {
"command": "uvx",
"args": [
"cathedral-mcp"
],
"env": {
"CATHEDRAL_API_KEY": "<YOUR_VALUE>",
"CATHEDRAL_BASE_URL": "<YOUR_VALUE>",
"CATHEDRAL_SANITISE": "<YOUR_VALUE>"
}
}
}
}
CATHEDRAL_API_KEYrequired secret — Your Cathedral API key from cathedral-ai.comCATHEDRAL_BASE_URL— Cathedral API base URL (for self-hosted instances)CATHEDRAL_SANITISE— Set to 1 to enable prompt injection filtering on memory content
Related servers
Context7
Up-to-date code docs for any prompt
cognee
Memory manager for AI apps and Agents using various graph and vector stores and allowing ingestion from 30+ data sources
hindsight
Hindsight: Agent Memory That Works Like Human Memory - Built for AI Agents to manage Long Term Memory
Skill_Seekers
Transform 17 source types (docs, GitHub repos, PDFs, videos, Jupyter, Confluence, Notion, Slack/Discord) into AI-ready skills and RAG…
basic-memory
Local-first knowledge management with bi-directional LLM sync via Markdown files.
NoteDiscovery
Self-hosted plain-markdown knowledge base with a built-in MCP server. Lets Claude Desktop, Cursor, and any MCP client search, read,…
Data from the Official MCP Registry