Skip to main content
Glama
Sign In
Backlog MCP Server

Backlog MCP Server

by nulab
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

get_issue_attachment

Read-only

Downloads an issue attachment by ID and returns it as MCP image or embedded resource, or as base64 JSON for programmatic processing.

Instructions

Downloads one attachment of an issue. Returns it as MCP image or embedded resource content by default, or as base64 in a JSON object with format: 'base64'. Call get_issue first to obtain the attachmentId from the issue's attachments array.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "attachmentId": "<attachmentId>"
    },
    "name": "get_issue_attachment"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatNoHow to return the file. 'auto' (default) returns a verified raster image as MCP image content and anything else as an embedded resource, so a client can render it. 'base64' returns a single JSON object with the encoded bytes in `content`, for callers that process the file programmatically — note that this puts the whole encoding in the caller's context.
issueIdNoThe numeric ID of the issue (e.g., 12345)
issueKeyNoThe key of the issue (e.g., 'PROJ-123')
maxBytesNoMaximum raw attachment size in bytes. Defaults to 5242880 and cannot exceed 7340032.
attachmentIdYesThe numeric ID of the attachment. Get it from get_issue (the issue's `attachments` array).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.20.5

TDQS

A4.2/5.0
Behavior4/5

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

With readOnlyHint/destructiveHint/openWorldHint already declaring a safe read, the description adds real behavioral context: the default auto behavior of rendering raster images as MCP image content, and the warning that base64 mode places the whole encoding in the caller's context. It omits the maxBytes cap and default, which is a meaningful behavioral detail.

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 tight sentences: purpose first, return modes second, prerequisite last. Nothing is padded and the most decision-relevant information leads.

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?

With no output schema, the description correctly compensates by describing return shapes (image content, embedded resource, base64 JSON). It falls short on the optional issueId/issueKey parameters and the maxBytes default, which an agent needs to call the tool optimally.

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 coverage is 100% and the schema already documents format, attachmentId provenance, and maxBytes limits, so the description largely mirrors structured data. It offers no explanation of why issueId/issueKey are accepted alongside attachmentId, leaving the multi-param authorization semantics unaddressed.

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?

States a specific verb and resource ('Downloads one attachment of an issue') and immediately clarifies the return shape, which lets an agent distinguish it from get_issue or the comment/wiki siblings.

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?

Explicitly routes the agent: 'Call get_issue first to obtain the attachmentId', and distinguishes the two return modes. It does not state when not to use the tool or how issueId/issueKey interact with attachmentId, so it stops short of full when/when-not coverage.

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

Deploy Server

Other Tools