A database your agent can actually use

What an MCP database is

Model Context Protocol (MCP) is a standard for connecting AI agents to external tools and data sources. An MCP server exposes typed operations (read a schema, query records, add a row) that an agent calls directly instead of parsing text or scraping a UI.

An MCP database is a structured data store that an agent accesses through this protocol. Instead of dumping facts into loose markdown files where keys drift, formats break, and nothing sorts, the agent works with typed fields, validated records, and relational links.

Dosirak embeds an MCP server inside the desktop application. The agent reads the same schema and works with the same records the operator sees in the forms and lists.

One kernel, two ways in

The desktop app and the MCP server run the same command layer. When you add a record in the form, it goes through the kernel. When the agent adds a record over MCP, it goes through the same kernel.

This means the agent cannot do anything the app cannot show you. Every record the agent creates appears in your lists and forms. Every field the agent updates shows in the activity log.

The transport runs locally: stdio for headless operation, or HTTP on localhost when the desktop app is running. It does not go through a cloud relay, and there are no API keys or rate limits.

What the agent can do

The MCP server exposes tools that mirror the kernel's commands.

Schema tools (read the project structure):

• list_tables returns every table with its field definitions.
• get_schema returns the full schema for one table, including field types, constraints, and layout.

Record tools (work with data):

• query_records reads records with filters, sorting, and pagination.
• add_record creates a new record with typed field values.
• update_record changes fields on an existing record.
• search runs full-text search across all tables.

Coordination tools (involve the operator):

• ask_human files a todo card linked to a specific record, with action buttons or a text prompt.
• list_todos checks which requests are pending or resolved.

Every tool call is logged in the activity feed. You can review what the agent read, what it changed, and what it asked.

Review and approve

When an agent needs a decision (send the invoice? add this record? update the status?), it calls ask_human with a question, a link to the relevant record, and a set of structured actions.

The card appears in the todo tray in the desktop app. It shows the agent's name, the question, and the record it refers to. You tap Approve, and the agent continues. Or you reply, and the agent adjusts.

Nothing goes out without your sign-off.

Connecting an agent

Dosirak works with any MCP client. The dosirak-mcp binary ships with the desktop app.

Claude Desktop, add to claude_desktop_config.json:

{
  "mcpServers": {
    "dosirak": {
      "command": "dosirak-mcp",
      "args": ["--project", "/path/to/your.dosirak"]
    }
  }
}

Claude Code, add to your project's .mcp.json:

{
  "mcpServers": {
    "dosirak": {
      "command": "dosirak-mcp",
      "args": ["--project", "/path/to/your.dosirak"]
    }
  }
}

Any MCP client, the generic stdio invocation:

dosirak-mcp --project /path/to/your.dosirak

Questions