# load_buffer

Source: https://libtmux.org/en/py/latest/mcp/tools/load_buffer/

> Load text into a new agent-namespaced tmux paste buffer.

MCP is in development

Server behavior and tool contracts may change. Tool availability depends on the server configuration.

Load text into a new agent-namespaced tmux paste buffer.

Each call allocates a fresh buffer name — two concurrent calls will land in distinct buffers even if they pass the same `logical_name`. Agents MUST use the returned :attr:`~libtmux_mcp.models.BufferRef.buffer_name` on subsequent paste/show/delete calls.

**When to use this vs. [paste\_text](https://libtmux.org/en/py/latest/mcp/tools/paste_text/):** `load_buffer` is the stage-then-fire path — you get a handle back and can inspect via [`show_buffer`](https://libtmux.org/en/py/latest/mcp/tools/show_buffer/), paste into multiple panes via [`paste_buffer`](https://libtmux.org/en/py/latest/mcp/tools/paste_buffer/), or hold the content for later. Use [`paste_text`](https://libtmux.org/en/py/latest/mcp/tools/paste_text/) for a simple one-shot paste with no follow-up.

[All Python tools](../) · [JSON](../load_buffer.json) · [Source](https://github.com/tmux-python/libtmux-mcp/blob/4daddc0dfca96c43bf521d818bf91564e1434760/src/libtmux_mcp/tools/buffer_tools.py#L386)

## Arguments

* `content` required · string

  The text to stage. Can be multi-line. Redacted in audit logs.

* `logical_name` optional

  Short label for the buffer. Limited to \`\`\[A-Za-z0-9\_.-]{1,64}\`\` so the final name stays safe on the tmux command line. Empty or \`\`None\`\` uses \`\`"buf"\`\`.

  Default: `null`.

* `socket_name` optional

  tmux socket name.

  Default: `null`.

## Schemas

The schema defines required fields, nested values, defaults, and validation constraints.