FRENES

Memory and knowledge · MCP server

Kybase: MCP server, setup and security

Kybase is an open-source MCP server published on GitHub that lets an AI agent browse and edit Markdown notes serving as persistent agent memory. Its repository has 5 stars and its last commit is from October 22, 2026 and it is licensed under AGPL-3.0.

Actively maintainedNeeds secrets

What Kybase does

According to its repository: “Self-hosted Markdown knowledge base that doubles as persistent memory for AI agents: a notes app you browse and edit (wikilinks, backlinks, graph), 18 MCP tools over Streamable HTTP with OAuth (works as a claude.ai connector) or stdio. Hybrid search (Postgres full-text + pgvector, RRF, optional rera”

The Model Context Protocol (MCP) is a standard plug between an AI agent and an outside service: once the server is connected, its tools show up in the agent, which decides when to call them. Kybase is listed under Memory and knowledge, a category of 250 servers in the directory, where it ranks #229 by stars.

Topics declared by the repository: agent-memory, claude, claude-code, knowledge-base, nextjs, ollama.

Installing and connecting Kybase

Distribution modes declared in the official MCP registry:

  • npm package (Node.js, usually started with npx)

It works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, VS Code, Codex and most recent agents). You add one entry to the client's MCP configuration: server name, start command or URL, environment variables. Project language: TypeScript. Listed systems: macOS, Windows, Linux.

The registry lists 3 secret variables to provide (API key, access token). Keep them in the client's environment variables, never in a shared file or a repository.

Security: what to check

Connecting an MCP server means installing software that talks straight to your agent: it runs with your rights and the model trusts its tool descriptions. The risk therefore depends on what it can touch and how far its code can be trusted.

Points found for Kybase:

  • Secrets: the server acts with your credentials. Create a dedicated key with minimum rights and an expiry date.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on July 11, 2026, the Kyrzin/kybase repository has 5 stars and 0 forks, with 0 open issues. It has more stars than 13% of the servers in the directory. It received changes this month. Version published in the registry: 0.2.3 (October 22, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

Context7Context7 : 63.6K63.6KHindsightHindsight : 53.4K53.4KCogneeCognee : 32.7K32.7KSkill SeekersSkill Seekers : 15.2K15.2KHonchoHoncho : 7.8K7.8KBasic memoryBasic memory : 4.3K4.3KNoteDiscoveryNoteDiscovery : 2.8K2.8KMemantoMemanto : 2.3K2.3KKybaseKybase : 55
GitHub stars of the most followed servers in the category (log scale); Kybase in orange. Checked October 25, 2026.

Verdict

Kybase is a reasonable choice; check the points below before connecting it.

Strengths

  • Active project: recent commit
  • Listed in the official MCP registry

Limitations

  • Requires an API key or token
  • Few visible users

Avoid if…

  • You do not want to give credentials to an agent

Frequently asked questions

How do I install Kybase?

Kybase is distributed as npm package (Node.js, usually started with npx). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of Kyrzin/kybase.

Is Kybase free?

The code is published under the AGPL-3.0 licence and can be used free of charge. It needs an API key: the service it connects to may be paid.

Is Kybase safe?

Points to watch: secrets. Give it minimum rights and approve sensitive actions.

Is it an official server?

Nothing says so: it is a project published by Kyrzin on GitHub. Check who maintains it before giving it access.

What are the alternatives to Kybase?

In the same category: Context7, Basic memory, Hindsight, and Cognee. Context7 and Basic memory score higher on our grid.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score