Andish MCP Server

by andish Your server? Claim it

local only

Andish runs on your own machine — the client starts it, so there is no endpoint to ping. 117 installs a week from pypi.

Knowledge-graph memory for your team's documents. Answers cite the source, not a summary.

Installs per day peak 29 · avg 13 · +15% w/w

a month agotoday

117

Installs / week

pypi · andish-mcp

—

Stars

on GitHub

—

Last commit

from GitHub

—

License

language unknown

Nothing serious here today

Today is the operative word: we check Andish every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

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 Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add andish-mcp -- uvx andish-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "andish-mcp": {
      "args": [
        "andish-mcp"
      ],
      "command": "uvx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.andish-mcp]
command = "uvx"
args = ["andish-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "andish-mcp": {
      "args": [
        "andish-mcp"
      ],
      "command": "uvx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "andish-mcp": {
      "args": [
        "andish-mcp"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: ANDISH_API_KEY (Andish API key. Create one in the dashboard at https://andish.ru), ANDISH_BASE_URL (API base URL. Defaults to the hosted service; set it only when pointing at your own deployment.). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Andish

same job, measured the same way

Postgram

by ivo-toby

Self-hosted memory for AI agents with hybrid search, knowledge graphs, tasks, and document sync.

local only

Liminary

by liminary-api

Your AI's memory for what you actually know: recall across your documents, notes, and meetings

answering

SuperLocalMemory

by qualixar

Local-first memory for AI agents: recall with sources, answer checks, documents, mesh, governance.

local only

Membase

by membase

Long-term memory for you and your AIs: search memories, read the profile, add facts and documents.

answering

ContextLayer

by dotnova

Intelligent context infrastructure for AI teams: knowledge graph, sessions, tasks, documents.

62 tools answering

ClearMakes Agents

by clearmakes

Search one ClearMakes agent's knowledge: your documents, website pages and Drive files.

answering

Chaos Cypher

by chaoscypherinc

Local-first knowledge graphs from your documents: build, search (GraphRAG) and edit on your machine.

218 installs/wk local only

Claim Done

by com-claimdone

Australian legal documents drafted from your answers for a flat fee. Not a law firm.

7 tools answering

Andish — questions

Answers built from our own checks of this server.

Why is there no uptime for Andish?

Andish runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package andish-mcp was installed 117 times last week.

How do I connect Andish?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls andish-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use Andish?

The pypi package andish-mcp was installed 117 times in the last week. Week over week that is +15%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.