Pulse8 AI Cortex Knowledge Vault runs on your own machine — the client starts it, so there is no endpoint to ping. 71 installs a week from pypi. Last commit 27 Jul 2026.
Agent-native knowledge OS on Markdown: typed graph, hybrid search, and compiler over MCP.
We read the source, 19 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const child = spawn(QMD_BIN, args);
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add pulse8-ai-cortex-knowledge-vault -- uvx pulse8-ai-cortex-knowledge-vault
{
"mcpServers": {
"pulse8-ai-cortex-knowledge-vault": {
"args": [
"pulse8-ai-cortex-knowledge-vault"
],
"command": "uvx"
}
}
}
[mcp_servers.pulse8-ai-cortex-knowledge-vault]
command = "uvx"
args = ["pulse8-ai-cortex-knowledge-vault"]
{
"mcpServers": {
"pulse8-ai-cortex-knowledge-vault": {
"args": [
"pulse8-ai-cortex-knowledge-vault"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"pulse8-ai-cortex-knowledge-vault": {
"args": [
"pulse8-ai-cortex-knowledge-vault"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
CORTEX_VAULT_PATH (Absolute path to the Markdown vault directory the server reads and writes.), CORTEX_LLM_API_KEY (Optional OpenRouter (or compatible) API key. Only needed for LLM cross-referencing during compile; file conversion and search work without it.).
The author declared them in the registry entry; get the values from the project itself.
Local Markdown/Obsidian knowledge substrate for MCP agents with governed memory and hybrid search.
Semantic memory for AI agents with hybrid search, knowledge graph, and consolidation
Local-first memory for Claude Code and any MCP client: hybrid search + knowledge graph, $0/token.
Governed graph-native agent memory: knowledge extraction, fusion, hybrid RAG, scoped access tokens.
Read-only MCP over a vault's typed knowledge graph: concept search, contradictions, article fetch.
Persistent memory for AI agents: Markdown entries, hybrid search, typed graph links
Self-hosted knowledge backend for AI agents with hybrid search and MCP tools
Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
Answers built from our own checks of this server.