pictshare
:camera: PictShare is an open source image, mp4, pastebin hosting service with a simple resizing and upload API that you can host yourself. :rice_scene:
PictShare is a self-hosted media and text hosting service with an integrated MCP server that allows AI agents to upload, transform, and manage images, videos, audio files, and text through the Model Context Protocol. The MCP endpoint exposes tools for uploading files from URLs or base64 data, retrieving metadata, deleting content, creating albums, and generating transformed image URLs with resizing and filters. Agents can connect via the streamable HTTP transport at the /mcp endpoint, making it useful for workflows where AI assistants need persistent file storage and dynamic media manipulation. The service supports automatic format conversion (GIF to MP4, WebP optimization), removes EXIF metadata for privacy, and handles duplicate detection to save storage space.
Key Features
Use Cases
- 01Enable Claude Desktop or other MCP clients to store and retrieve generated images, screenshots, or diagrams
- 02Build AI workflows that download remote media, optimize it, and generate shareable links automatically
- 03Create chatbot assistants that manage user-uploaded photos with privacy (EXIF removal) and organize them into albums
- 04Deploy self-hosted media storage for AI agents in enterprise environments with upload access control
- 05Generate dynamic placeholder images and identicons programmatically through agent tool calls
- 06Implement AI-assisted content moderation pipelines with file metadata retrieval and deletion capabilities
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
pictshare — FAQ
What is the PictShare MCP server?+
PictShare is a self-hosted media hosting service with a built-in Model Context Protocol server that exposes file upload, management, and transformation tools to AI agents. It supports images, videos, audio, and text files with automatic format optimization and URL-based transformations.
How do I connect PictShare to Claude Desktop?+
Run your PictShare instance via Docker or PHP 8.2+, then register it in Claude Desktop using 'claude mcp add --transport http pictshare https://your.pictshare.host/mcp'. If your instance has UPLOAD_CODE configured, you'll need to provide it as a bearer token in the Authorization header.
Which AI clients work with the PictShare MCP server?+
PictShare uses the streamable HTTP transport for MCP, so it works with Claude Desktop, Claude Code, and any other MCP client that supports HTTP transport. The README specifically shows configuration examples for Claude Code.
Do I need API keys or special prerequisites?+
You need to self-host PictShare using Docker or a PHP 8.2+ server with write permissions to the storage directory. If you configure UPLOAD_CODE for access control, AI clients must send that code as a bearer token. FFmpeg is required for video conversion features.
Is PictShare free and open source?+
Yes, PictShare is open source under the Apache license and completely free to self-host. You maintain full control over your data and can deploy it on your own infrastructure without external dependencies.
What can AI agents do with the PictShare MCP tools?+
Agents can upload files from URLs or base64 data, retrieve file metadata (size, MIME type, upload time), delete files using delete codes, create albums from multiple files, and generate transformed image URLs with specific dimensions or filters applied.
How do I install pictshare?+
Open the source repository on GitHub and follow its README. pictshare is a mcp server — MCP Agents Market links you directly to the official repo.
Is pictshare free?+
pictshare is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.