Skip to main content
Glama
tan-yong-sheng

TriliumNext Notes' MCP Server

read_attributes

View labels, relations, and metadata for any note in TriliumNext. Inspect current attributes like #tags and ~template relations to understand note structure.

Instructions

Read all attributes (labels and relations) for a note. View existing labels (#tags), template relations (~template), and note metadata. This tool provides read-only access to inspect current attributes assigned to any note. Returns structured data with labels, relations, and summary information.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteIdYesID of the note to read attributes from

Implementation Reference

  • MCP handler for read_attributes tool: validates noteId, checks READ permission, calls core read_attributes function, handles errors, and formats MCP response.
    export async function handleReadAttributes(
      args: ReadAttributesParams,
      axiosInstance: AxiosInstance,
      permissionChecker: PermissionChecker
    ): Promise<any> {
      try {
        // Validate required parameters
        if (!args.noteId) {
          return {
            content: [
              {
                type: "text",
                text: "❌ Missing required parameter: noteId"
              }
            ],
            isError: true
          };
        }
    
        // Check READ permission
        if (!permissionChecker.hasPermission("READ")) {
          throw new McpError(ErrorCode.InvalidRequest, "Permission denied: Not authorized to read attributes.");
        }
    
        // Execute the read operation
        const result = await read_attributes(args, axiosInstance);
        return format_read_attribute_response(result, args.noteId);
    
      } catch (error) {
        return {
          content: [
            {
              type: "text",
              text: `❌ Attribute read operation failed: ${error instanceof Error ? error.message : 'Unknown error'}`
            }
          ],
          isError: true
        };
      }
    }
  • Core implementation of read_attributes: fetches note from Trilium API, maps attributes to structured format (labels/relations), provides summary.
    export async function read_attributes(
      params: ReadAttributesParams,
      axiosInstance: AxiosInstance
    ): Promise<AttributeOperationResult> {
      try {
        const response = await axiosInstance.get(`/notes/${params.noteId}`);
    
        const attributes: Attribute[] = response.data.attributes.map((attr: any) => ({
          type: attr.type,
          name: attr.name,
          value: attr.value,
          position: attr.position,
          isInheritable: attr.isInheritable
        }));
    
        // Separate labels and relations for better organization
        const labels = attributes.filter(attr => attr.type === 'label');
        const relations = attributes.filter(attr => attr.type === 'relation');
    
        return {
          success: true,
          message: `Retrieved ${attributes.length} attributes for note ${params.noteId} (${labels.length} labels, ${relations.length} relations)`,
          attributes,
          // Add structured summary for easier parsing
          summary: {
            total: attributes.length,
            labels: labels.length,
            relations: relations.length,
            noteId: params.noteId
          }
        };
      } catch (error) {
        return {
          success: false,
          message: `Failed to retrieve attributes: ${error instanceof Error ? error.message : 'Unknown error'}`,
          errors: [error instanceof Error ? error.message : 'Unknown error']
        };
      }
    }
  • Input schema definition for the read_attributes tool, requiring noteId.
    {
      name: "read_attributes",
      description: "Read all attributes (labels and relations) for a note. View existing labels (#tags), template relations (~template), and note metadata. This tool provides read-only access to inspect current attributes assigned to any note. Returns structured data with labels, relations, and summary information.",
      inputSchema: {
        type: "object",
        properties: {
          noteId: {
            type: "string",
            description: "ID of the note to read attributes from"
          }
        },
        required: ["noteId"]
      }
    }
  • src/index.ts:115-116 (registration)
    Registration of read_attributes tool in main switch handler, routing to handleReadAttributes.
    case "read_attributes":
      return await handleReadAttributes(request.params.arguments as any, this.axiosInstance, this);
  • TypeScript interface defining input parameters for read_attributes (noteId).
    export interface ReadAttributesParams {
      noteId: string;
    }
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states 'read-only access' (safety profile), describes what gets returned ('structured data with labels, relations, and summary information'), and specifies the scope ('all attributes'). It doesn't mention error conditions or performance characteristics, but provides solid behavioral context.

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?

Three sentences with zero waste. First sentence states purpose and scope, second clarifies access type, third describes return format. Every sentence adds value and the description is appropriately sized for a single-parameter read tool.

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

Completeness4/5

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

For a simple read operation with no annotations and no output schema, the description provides good coverage: purpose, scope, safety profile, and return format. It could benefit from mentioning what happens with invalid note IDs or whether it returns empty results for notes without attributes, but overall it's quite complete for this complexity level.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already fully documents the single 'noteId' parameter. The description doesn't add any parameter-specific information beyond what's in the schema, but doesn't need to since schema coverage is complete. Baseline 3 is appropriate when schema does the heavy lifting.

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 the specific action ('Read all attributes'), the resource ('for a note'), and what it returns ('labels and relations'). It distinguishes from siblings like 'get_note' by focusing specifically on attributes rather than the full note content, and from 'manage_attributes' by being read-only.

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 provides clear context for when to use it ('to inspect current attributes assigned to any note') and implicitly distinguishes it from write operations. However, it doesn't explicitly state when NOT to use it or name specific alternatives like 'get_note' for full note content versus just attributes.

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/tan-yong-sheng/triliumnext-mcp'

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