memors-mcp
memors-mcp is a local Model Context Protocol server providing a measurable, explainable knowledge base for AI agents. It uses hybrid search with provenance over a single SQLite file, supporting tools for ingesting documents, searching passages, recording atomic facts, and exploring knowledge graphs without cloud dependencies.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Ingest documents as markdown with provenance
- Search passages using words, identifiers, and meaning
- Record atomic facts with evidence and validity dates
- Explore knowledge graph connections between entities
Source and maintenance
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
https://github.com/kKEo/memors/releases/download/v1.6.5/memors-mcp_1.6.5_linux_amd64.tar.gz 1.6.5
{
"version": "1.6.5",
"transport": "stdio",
"fileSha256": "63744f5fa320df4c78e60a50b7b4c0c4a7abd33debf1a9e659cb4b992151991d",
"identifier": "https://github.com/kKEo/memors/releases/download/v1.6.5/memors-mcp_1.6.5_linux_amd64.tar.gz",
"registryType": "mcpb",
"environmentVariables": [
{
"name": "MEMORS_KB",
"format": "string",
"default": "default",
"description": "Name of the knowledge base to open; one SQLite file per name under $MEMORS_HOME/kb/."
},
{
"name": "MEMORS_HOME",
"format": "string",
"description": "Base directory for knowledge bases and settings (default ~/.memors-mcp)."
},
{
"name": "MEMORS_MODEL",
"format": "string",
"description": "Embedding model id from `memors-mcp model ls` (default granite-small-r2)."
}
]
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Let your agent find its tools
Find servers like memors-mcp from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.