Skip to main content
Glama
bezata

kObsidian MCP

Parse Kanban Board

kanban.parse
Read-onlyIdempotent

Extract the full structure of a Kanban board from its Markdown file: column names, card titles, and completion status. Works with Obsidian's Kanban plugin format. Use for retrieving complete board content.

Instructions

Parse a markdown Kanban board file into its column/card structure. Use this when you need the full board content — each column's name and its cards with their completion state. Works with the obsidian-kanban plugin's markdown format. Read-only. For completion counts and ratios instead of the full card list, use kanban.stats.

Operates on the session-active vault (see vault.current — selectable via vault.select) unless an explicit vaultPath argument is passed, which always wins.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
filePathYesPath of the Kanban board note (`.md`).
vaultPathNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
filePathYes
columnsYes

Implementation Reference

  • Core handler function for kanban.parse. Reads a markdown Kanban board file from the vault, parses it into column/card structure, and returns the board representation with filePath, totalCards, and columns (each with name, cardCount, and cards).
    export async function parseKanbanBoard(
      context: DomainContext,
      args: { filePath: string; vaultPath?: string },
    ) {
      const vaultRoot = requireVaultPath(context, args.vaultPath);
      const absolutePath = resolveVaultPath(vaultRoot, args.filePath);
      const content = await readUtf8(absolutePath);
      const board = parseKanbanStructure(content, args.filePath);
      return {
        filePath: args.filePath,
        totalCards: board.columns.reduce(
          (count, column) => count + flattenCards(column.cards).length,
          0,
        ),
        columns: board.columns.map((column) => ({
          name: column.name,
          cardCount: flattenCards(column.cards).length,
          cards: column.cards,
        })),
      };
    }
  • Input schema for kanban.parse. Accepts filePath (vault-relative .md path) and optional vaultPath.
    export const kanbanParseArgsSchema = z
      .object(commonBoardFields)
      .strict()
      .describe("Arguments for `kanban.parse`.");
    export type KanbanParseArgs = z.input<typeof kanbanParseArgsSchema>;
  • Output schema for kanban.parse. Defines the response shape with filePath and an array of columns, each containing a name and cards array with text and completed status.
    export const kanbanBoardOutputSchema = z
      .object({
        filePath: z.string(),
        columns: z.array(
          z
            .object({
              name: z.string(),
              cards: z.array(
                z
                  .object({
                    text: z.string(),
                    completed: z.boolean(),
                  })
                  .passthrough(),
              ),
            })
            .passthrough(),
        ),
      })
      .passthrough();
  • Tool registration for kanban.parse. Defines name, description, input/output schemas, annotations (READ_ONLY), and the inline handler that delegates to parseKanbanBoard in the domain layer.
    {
      name: "kanban.parse",
      title: "Parse Kanban Board",
      description:
        "Parse a markdown Kanban board file into its column/card structure. Use this when you need the full board content — each column's name and its cards with their completion state. Works with the obsidian-kanban plugin's markdown format. Read-only. For completion counts and ratios instead of the full card list, use `kanban.stats`.",
      inputSchema: kanbanParseArgsSchema,
      outputSchema: kanbanBoardOutputSchema,
      annotations: READ_ONLY,
      handler: async (context, rawArgs) => {
        const args = kanbanParseArgsSchema.parse(rawArgs) as KanbanParseArgs;
        return parseKanbanBoard(context, args);
      },
    },
  • Tool registry that includes kanbanTools (which contains kanban.parse) via spread into the central toolRegistry array.
    import { kanbanTools } from "./tools/kanban.js";
    import { linkTools } from "./tools/links.js";
    import { marpTools } from "./tools/marp.js";
    import { noteTools } from "./tools/notes.js";
    import { systemTools } from "./tools/system.js";
    import { tagTools } from "./tools/tags.js";
    import { taskTools } from "./tools/tasks.js";
    import { templateTools } from "./tools/templates.js";
    import { vaultTools } from "./tools/vaults.js";
    import { wikiTools } from "./tools/wiki.js";
    
    export const toolRegistry: ToolDefinition[] = [
      ...vaultTools,
      ...noteTools,
      ...tagTools,
      ...linkTools,
      ...analyticsTools,
      ...taskTools,
      ...dataviewTools,
      ...blocksTools,
      ...marpTools,
      ...kanbanTools,
      ...canvasTools,
      ...templateTools,
      ...apiTools,
      ...wikiTools,
      ...systemTools,
    ];
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and idempotentHint=true; description reinforces read-only nature. It adds value by explaining vault behavior (session-active vault vs explicit vaultPath) and format specificity. Slightly more detail on error handling would push it higher.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact with two focused paragraphs. No unnecessary words; each sentence contributes distinct information (purpose, usage, vault behavior). Excellent structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with output schema, the description covers all necessary aspects: purpose, usage guidance, behavioral constraints, parameter semantics for the undocumented parameter, and sibling differentiation. No gaps given the context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers filePath adequately; description compensates for vaultPath's missing schema description by explaining its override behavior. Since schema coverage is 50% and description fills the gap, this is a solid 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it parses a markdown Kanban board file into column/card structure, specifying the output includes column names, cards, and completion state. It also distinguishes itself from sibling tool `kanban.stats` by noting the difference in output purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Use this when you need the full board content' and provides an alternative for stats. It also mentions compatibility with obsidian-kanban plugin. However, it does not specify when not to use this tool, so it's not a full 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/bezata/kObsidian'

If you have feedback or need assistance with the MCP directory API, please join our Discord server