t2000-mcp
t2000-mcp is an MCP server development skill for AI agents, published by mission69b in the t2000 repository on GitHub. Skillspace rates t2000-mcp F (15/100) and the safety scan rated it unsafe; the rating is based on static analysis only.
Unsafe. This skill has patterns associated with malicious or dangerous behaviour. We do not recommend running it.
Connect a t2000 Agent Wallet to Claude Desktop, Cursor, Cline, Continue, or any MCP-compatible client. Use when asked to set up MCP, paste an MCP server config, install @t2000/mcp, or troubleshoot why the MCP server "doesn't do anything" when run from a terminal. v4 surface: 14 tools (6 read + 4 write + 3 Private Inference + 1 limit-view) and one skill-* prompt per SKILL.md in t2000-skills/skills/.
- Grade
- F
- Quality
- 15 / 100
- Safety
- Unsafe
- GitHub stars
- 22
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 84 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- Critical-risk patterns
- License
- MIT
- Adoption
- Adopted by 1 other repositories, in 0 collections
What the scanner flagged
- destructive rm -rf on home/root
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.