by USS-Parks · MCP Server · ★ 62
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Local-first, multi-provider coding desktop with Codex-style Steering, task controls, inline artifacts, PR review, tools, skills, MCP, and research.
| Stars | 62 |
| Forks | 2 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 50.0705557489523/100 |
| Open Issues | 3 |
| Last Updated | 2026-09-07 |
| Created | 2026-05-30 |
| Platforms | codex, mcp, node |
| Est. Tokens | ~13k |
These tools work well together with Lamprey-Harness for enhanced workflows:
Explore other popular mcp server tools:
Lamprey-Harness is Local-first, multi-provider coding desktop with Codex-style Steering, task controls, inline artifacts, PR review, tools, skills, MCP, and research.. It is categorized as a MCP Server with 62 GitHub stars.
Lamprey-Harness is primarily written in TypeScript.
You can find installation instructions and usage details in the Lamprey-Harness GitHub repository at github.com/USS-Parks/Lamprey-Harness. The project has 62 stars and 2 forks, indicating an active community.
Lamprey-Harness is released under the MIT license, making it free to use and modify according to the license terms.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: