PasteAI

Human review of beautiful reports, generated by AI

AI publishes markdown documents via MCP. You read them in a clean, themed web UI.

Run/setupin Claude Code — it installs the binary and configures MCP. Then restart your editor to activate.

# macOS brew install pasteai/pasteai/pasteai # Windows scoop bucket add pasteai https://github.com/pasteai/scoop-pasteai scoop install pasteai # Linux (Debian/Ubuntu) # Download the .deb from https://github.com/pasteai/pasteai/releases/latest # Any platform — prebuilt binary curl -sSL https://raw.githubusercontent.com/pasteai/pasteai/main/install.sh | sh # With Go go install github.com/pasteai/pasteai/cmd/pasteai@latest

Then runpasteai setupto register with your AI editor(s). It configuresClaude Code,Kiro, andopencodesimultaneously.

To configure manually, add the entry to the appropriate config file:

Claude Code(~/.claude.json) andKiro(~/.kiro/settings/mcp.json):

{ "mcpServers": { "pasteai": { "command": "/full/path/to/pasteai", "args": ["mcp"] } } }

opencode(~/.config/opencode/opencode.json):

{ "mcp": { "pasteai": { "type": "local", "command": ["/full/path/to/pasteai", "mcp"] } } }

Use the absolute path fromwhich pasteaior$(go env GOPATH)/bin/pasteai— AI editors do not inherit your shell PATH.

Restart your editor, then ask:"Summarise what we discussed and publish it."

Add the MCP config above and restart Claude Code. When Claude first calls a tool, PasteAI starts a local server automatically. Documents stored at~/.pasteai/documents.dband as plain markdown files at~/.pasteai/documents/{id}.md— readable without the server running.

Run the server persistently with Docker Compose and point the MCP client at it:

# docker-compose.yml services: pasteai: image: ghcr.io/pasteai/pasteai:latest ports: - "8080:8080" volumes: - ${HOME}/.pasteai:/data restart: unless-stopped

mkdir -p ~/.pasteai docker compose up -d

{ "mcpServers": { "pasteai": { "command": "/full/path/to/pasteai", "args": ["mcp"], "env": { "PASTEAI_URL": "http://localhost:8080" } } } }

Good when you want the server always running, independent of Claude Code. For systemd, launchd, or nohup alternatives, seedocs/server-setup.md.

pasteai serve -api-key <your-key> -base-url https://your-server.example.com

{ "mcpServers": { "pasteai": { "command": "/full/path/to/pasteai", "args": ["mcp"], "env": { "PASTEAI_URL": "https://your-server.example.com", "PASTEAI_API_KEY": "your-key" } } } }

To read documents from your phone or another machine, use Tailscale. Startpasteai serve, then browse tohttp://<tailscale-ip>:8080from any device on your tailnet. Set-base-url http://<tailscale-ip>:8080so document links resolve correctly.

publish_document— publish a markdown document, returns a shareable URL.

list_documents— returns recent public documents.

get_document— retrieve a document by ID, including its full markdown content.

update_document— update the title or content of an existing document.

delete_document— permanently delete a document by ID.

claude.ai Custom Connectors (streamable-HTTP MCP)

To connect a deployed PasteAI server toclaude.aias a Custom Connector, start the server with-enable-mcp-http. This mounts a stateless streamable-HTTP MCP endpoint at/mcpalongside the web UI:

pasteai serve \ -api-key <your-key> \ -base-url https://your-server.example.com \ -enable-mcp-http

Then in claude.ai → Settings → Connectors, add:

The/mcpendpoint requires the same Bearer token as the API when-api-keyis set. The stdio transport (pasteai mcp) is unaffected — both can run simultaneously.

curl -X POST http://localhost:8080/api/documents \ -H 'Content-Type: application/json' \ -d '{"title": "My Report", "content": "# Hello\n\nThis is my report.", "author": "Claude"}'

Response includes aurlfield:http://localhost:8080/d/{id}

Switch themes using the selector in the top nav. Choice is saved inlocalStorage.

Light · Dark · Emerald · Arctic · Catppuccin Mocha · Catppuccin Latte · Catppuccin Frappé

AI-powered reading triage MCP. 26 tools with a 24h burn timer. Read less, absorb more.

Generates professional PDF cover letters using LaTeX. Requires Docker for local execution.

Create and manipulate PowerPoint presentations programmatically using JSON or Markdown.

An MCP server designed to assist with novel writing, configurable via JSON project files.

Remote MCP server for Docsie video-to-docs automation and workspace knowledge search.

Evaluates technical documentation against globalization standards, analyzing for translation issues, ambiguity, and sentence length.

A Model Context Protocol (MCP) server for integrating Google Docs with AI clients.

An MCP server that enables LLMs to create or update Notion pages and generate Markdown Books (mdbooks).

Score, tailor, and edit your resume from Claude Code and any MCP client.

Tailor resumes to job postings, generate cover letters, and export PDFs through AI agents