Skip to main content
Glama

create_local

Create a persistent local terminal session on the host machine. Get a session ID to run commands interactively across multiple calls.

Instructions

Creates a persistent local terminal session (PTY on supported platforms)
on the machine hosting this MCP server. The session stays active across
tool calls; drive it with `execute` and close it with `disconnect`.

WHEN TO USE:
- Use this for a shell on the LOCAL host (the machine running this server).
  For a shell on a REMOTE host, use `connect_ssh` instead.
- Reuse an existing session_id rather than creating one per command.

BEHAVIOR & SIDE EFFECTS:
- Spawns a shell with the permissions of the user running the MCP server —
  full read/write file access and execution privileges on the host.
- No rate limits or destructive-command filters are applied.
- Leaks a process if left open; call `disconnect` when finished.

Returns:
    A unique session_id used to drive (`execute`) and close (`disconnect`)
    this shell.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
shellNoOptional absolute path or executable name of the shell to use (e.g., 'powershell.exe', '/bin/bash', '/bin/zsh'). If omitted, defaults to cmd.exe on Windows or /bin/bash on Unix/macOS.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

Discloses side effects beyond annotations: spawns shell with full user permissions, no rate limits, no destructive filters, leaks if not closed. Annotations only provide basic hints; description adds critical safety context.

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?

Well-structured with clear sections (purpose, when to use, behavior, returns). Every sentence adds value; no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Provides complete context: creation, driving with execute, closing with disconnect, side effects, return format. Output schema exists but description explains it adequately.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% coverage for one parameter (shell) with description. Description adds platform-specific defaults (cmd.exe, /bin/bash) beyond schema, adding useful 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?

Describes creating a persistent local terminal session (PTY) and distinguishes from sibling connect_ssh for remote hosts. Clearly states the tool's verb and resource.

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 tells when to use (local shell) and when not (remote shell use connect_ssh). Advises reusing session_id instead of creating per command. Also mentions closing with disconnect.

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

Install Server

Other Tools

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/QiuwenZheng/interminal'

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