Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@andish-mcp Search the knowledge graph for what we know about Project Atlas."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server for the Andish Knowledge Graph API.
Works with any MCP-compatible client: Cursor, Cline, Continue, and others.
Full docs: https://andish.ru/docs
Registry ownership verification: mcp-name: ru.andish/andish-mcp
uvx andish-mcp@latestOr with pip:
pip install andish-mcpRelated MCP server: WorkGraph
// example MCP client config (the exact file path depends on your client)
{
"mcpServers": {
"andish": {
"command": "uvx",
"args": ["andish-mcp@latest"],
"env": {
"ANDISH_API_KEY": "adsh_live_xxxxxxxxxxxx"
}
}
}
}Nine tools are registered by the server.
Tool | What it does |
| Search the workspace knowledge graph and synthesise an answer. |
| Fetch raw context from the knowledge graph and write the answer yourself. |
| List documents uploaded to the workspace. |
| Fetch metadata and a content excerpt for one document. |
| Upload a local file to the workspace for indexing. |
| Search entities (people, organizations, concepts) by label substring. |
| Return entities connected to an entity, directly (hop=1) or transitively (hop=2). |
| Show current workspace usage: documents, cost, daily queries. |
| Check server health and API connectivity. |
Variable | Required | Default | Description |
| Yes | — | API key from https://andish.ru/dashboard |
| No |
| Override for self-hosted or staging |
| No |
| Per-request timeout in seconds |
This server cannot be deployed
Query, browse, and automate OmegaAI workspaces from any MCP client. Streamable HTTP with OAuth 2.0.
Workspace knowledge bases agents ingest, search, and query over MCP.
Make your knowledge agent-ready. One MCP endpoint, 5 connectors, 3 search modes.
Authenticated MCP access to the AIKI open knowledge commons.
