pulsemcp verified Safe content atomic mcp-remote

HT Terminal

This MCP server provides AI assistants with direct access to headless terminal sessions through a high-performance Rust implementation that integrates the HT (headless terminal) library via git submodule. Built by Memex Tech using Rust with tokio for async operations and direct HT library integration, it offers six core tools for terminal automation: session creation with optional web server preview, keystroke sending with special key support, terminal snapshots, command execution with output capture, session listing, and session management. The implementation delivers significant performance improvements over TypeScript equivalents (40x faster startup, 70% less memory usage) while providing a single 4.7MB binary deployment, cross-platform support including Windows, and optional live terminal preview through HT's native web server, making it valuable for terminal automation workflows, headless server management, and building AI assistants that need programmatic terminal access without manual SSH or console interaction.

Cognium trust score
74%
Tier
Verified

Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.

Scan details: Circle-IR · 2026-09-19 · Appeal

View full trust & usage report →

Metadata

Version
1.0.0
Skill type
atomic
Execution layer
mcp-remote
Category
version-control
Source
PulseMCP
Author type
human
Last scanned
2026-09-19
Updated
2026-09-19
View source Find related skills

Use via MCP

MCP

Resolve HT Terminal from your agent

Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.

One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.

claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
Swap --scope user for --scope project to commit it to .mcp.json.

Search SkillsRegistry