← Index

io.github.xiaolai/claude-octopus

io.github.xiaolai/claude-octopus·v1.1.10·Other

Spawn multiple specialized Claude Code agents as MCP servers, each independently configured.

Trust verdict · v1 advisory · method
NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

Environment variables
ANTHROPIC_API_KEY
secret

Anthropic API key (leave unset to inherit from parent process)

CLAUDE_TOOL_NAME

Tool name prefix (default: claude_code)

CLAUDE_MODEL

Model: sonnet, opus, haiku, or full ID

CLAUDE_PERMISSION_MODE

Permission mode: default, acceptEdits, bypassPermissions, plan

CLAUDE_ALLOWED_TOOLS

Comma-separated list of available tools (e.g. Read,Grep,Glob for read-only)

CLAUDE_APPEND_PROMPT

Additional system prompt appended to the default

CLAUDE_FACTORY_ONLY

Set to true to expose only the factory wizard tool

MCP quality score · maturity, not trust · methodology
freshness
25
completeness
10
installability
25
documentation
15
stability
10
Alternatives in Other