Fetches Jira issue attachments, returning inline images or cached file paths.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
A tiny local MCP server that fetches Jira attachments and returns them to an MCP client such as Claude Code.
Images (PNG, JPEG, GIF, WebP) under ~3 MB are returned inline, so the model can see them directly.
Larger images and all other file types are saved to
~/.cache/jira-attachment-mcp/ and the local path is returned.
It runs over stdio and exposes a single tool, jira_get_attachment, which takes
a numeric Jira attachment ID.
Node.js >= 18
An Atlassian API token: https://id.atlassian.com/manage-profile/security/api-tokens
Related MCP server: Simple Jira MCP
npm install
node setup.jssetup.js prompts for your Atlassian email, API token, and Jira base URL
(e.g. https://your-company.atlassian.net), then writes them to
~/.config/jira-attachment-mcp/config.json with 0600 permissions.
Then register the server with Claude Code (use the absolute path to index.js):
claude mcp add --transport stdio jira-attach -- node /absolute/path/to/index.jsRestart Claude Code (or reload MCP servers) so the new server is picked up.
Your credentials never leave your machine and are never committed: they live
only in ~/.config/jira-attachment-mcp/config.json (mode 0600). The token is
used solely to build the HTTP Basic auth header for requests to your own Jira
instance.
MIT — see LICENSE.
This server cannot be deployed
Convert PDFs, Office files, spreadsheets and images to clean Markdown, sized for agent context.
Convert and resize static image URLs to WebP, PNG or JPEG for uploads and agent workflows.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Convert PDF, DOCX, PPTX, XLSX and HTML links to clean Markdown with tables and RAG chunks.