Home › Knowledge & Memory › LINZA
LINZA
Local-first MCP sidecar for Markdown artifacts, review intents, and supervised knowledge growth.
Topics: Knowledge & Memory
Connect
Review any command before running it. Package names and URLs come from the server's own registry entry.
Package (pypi 0.2.2)
uvx linza-mcp
Or add to your MCP client config:
{
"mcpServers": {
"linza-mcp": {
"command": "uvx",
"args": [
"linza-mcp"
],
"env": {
"LINZA_EMBED_KEY": "<YOUR_VALUE>"
}
}
}
}
LINZA_VAULT— Absolute path to the Markdown workspace or vault LINZA may index. Defaults to ./vault.LINZA_EMBED_PROVIDER— Embedding provider. Allowed values: lmstudio, openai, ollama. Default: lmstudio.LINZA_EMBED_URL— Embedding API base URL when LINZA_EMBED_PROVIDER is lmstudio, openai, or ollama.LINZA_EMBED_MODEL— Embedding model name.LINZA_EMBED_KEYsecret — Optional embedding API key.LINZA_BRIDGE_THRESHOLD— Semantic bridge threshold as a floating-point string. Default: 0.55.LINZA_MAX_BRIDGE_PAIRS— Maximum note pairs for semantic bridge rebuilds. Default: 1000000. Use 0 to disable the guard.LINZA_DEFAULT_PROFILE— Default search profile name. Defaults to general.LINZA_LANGUAGE— User-facing guide language. Allowed values: auto, en, ru. Default: auto.
Related servers
modelcontextprotocol/servers
Direct local file system access.
Context7
Up-to-date docs for AI agents
hindsight
Hindsight: long-term memory for AI agents modeled on human memory.
cognee
Memory manager for AI apps and agents using graph and vector stores, with ingestion from many data sources.
Skill_Seekers
Turn docs, GitHub repos, PDFs, videos, Confluence, Notion and Slack/Discord into AI skills and RAG knowledge, exportable to vector…
basic-memory
Local-first knowledge management with bi-directional LLM sync via Markdown files.
Listed in punkpeye/awesome-mcp-servers (MIT)
Data from the Official MCP Registry