Skip to main content
Glama

Claude Paste MCP

A Windows-native MCP server that allows you to paste images, Excel tables, rich text, and plain text directly into Claude via a popup interface.

Requirements

  • Windows 10/11

  • Node.js 18+

  • PowerShell 5.1+ (Standard on Windows)

Related MCP server: MCP Desktop Tools

Setup

  1. Install Dependencies:

    npm install
  2. Configure Claude: Add the following to your ~/.claude/config.json (create it if it doesn't exist):

    {
      "mcpServers": {
        "claude-paste": {
          "command": "node",
          "args": ["C:\\path\\to\\claude-paste-mcp\\src\\index.js"]
        }
      }
    }

    Note: Replace C:\\path\\to\\... with the actual absolute path to this folder.

Usage

  1. Open Claude CLI or Desktop.

  2. Type a prompt that triggers the tool, for example:

    "I'm seeing a bug, here is the screenshot: /pic"

    Note: Use /pic (slash command) instead of @pic.

  3. A Windows Popup will appear.

  4. Press Ctrl+V to paste content. Supported formats:

    • Images (screenshots, copied images)

    • Excel tables (copied cells from Excel/Google Sheets)

    • Rich Text (formatted text from Word, etc.)

    • Plain Text

  5. You can paste multiple items. Select items to preview or delete.

  6. Click Confirm.

  7. Claude will receive the content paths and context.

Phases

  • Phase 1: Single image paste.

  • Phase 2: Multiple images, list view, delete capability.

  • Phase 3: Support for Excel tables, Rich Text, and plain text.

  • Phase 4 (In Progress): Moodle Code generation - auto-convert Excel tables to Moodle Cloze format (red text = correct answers).

See PROGRESS.md for detailed progress tracking.

Available Tools

1 tool
collect_pasted_itemsA

Opens a Windows popup to let the user paste images, Excel tables, rich text, or plain text from their clipboard. Use this when the user indicates they want to attach content (e.g. via @pic).

ParametersJSON Schema
NameRequiredDescriptionDefault
prompt_contextNoOptional context about what the user is expected to paste.

TDQS

A4.2/5.0
Behavior3/5

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

With no annotations provided, the description carries the full burden. It successfully discloses the UI interaction model (Windows popup) and supported data formats, but lacks details on return values, blocking behavior, or failure modes (e.g., user cancellation), leaving gaps in behavioral disclosure.

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?

Two sentences with zero redundancy: the first establishes capability and mechanism, the second provides usage conditions with an example. Perfectly front-loaded and economically structured.

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?

Given 100% schema coverage and the tool's narrow scope, the description adequately covers the interaction model and supported formats. Minor deduction for lacking mention of return behavior or error states given the absence of an output schema, but sufficient for correct invocation.

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% (one optional parameter fully documented), establishing a baseline of 3. The description does not add supplementary details, examples, or semantic clarifications beyond what the schema already provides for 'prompt_context'.

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 provides a specific action ('Opens a Windows popup'), clearly identifies the resource (clipboard content), and enumerates supported formats (images, Excel tables, rich text, plain text), leaving no ambiguity about the tool's function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use the tool ('when the user indicates they want to attach content') and provides a concrete example trigger ('e.g. via @pic'), giving the agent clear signals for invocation without ambiguity.

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

TDQS

A4/5.0
Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly distinct as the sole function of the server.

Naming Consistency5/5

A single tool inherently has perfect naming consistency, as there are no other tools to compare against. The name 'collect_pasted_items' follows a clear verb_noun pattern.

Tool Count2/5

One tool is too few for a server's purpose, as it severely limits functionality and scope. This feels thin and incomplete for handling pasted content, lacking operations like viewing, managing, or deleting collected items.

Completeness2/5

The server is severely incomplete for handling pasted content. It only allows collection but provides no way to list, retrieve, update, or delete pasted items, leaving significant gaps that will cause agent failures in workflows.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • F
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that gives Claude and other AI assistants access to your Maccy clipboard history, allowing search, retrieval, and management of copied content through natural conversation.
    9
  • F
    license
    A
    quality
    D
    maintenance
    An MCP server that provides Claude with comprehensive desktop automation capabilities including browser control, window management, and native mouse/keyboard input on Windows. It enables users to capture screenshots, launch applications, and interact with the system clipboard through natural language.
    20
  • A
    license
    A
    quality
    B
    maintenance
    MCP server that reads and writes the system clipboard — tables, text, code, JSON, URLs, images, and more. Preserves spreadsheet structure (rows/columns) that is lost when pasting into Claude directly.
    4
    5
    Apache 2.0
  • A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server for capturing screen regions directly into Claude Code conversations via hotkeys or tool calls. It provides Windows-specific screen snipping with multi-monitor support, persistent storage, and automatic management of captured images.
    MIT

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/G3sparky/claude-paste-mcp'

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