← Index

io.github.shinpr/sub-agents-mcp

io.github.shinpr/sub-agents-mcp·v0.8.0·AI & LLMs

MCP server for delegating tasks to specialized AI assistants in Cursor, Claude, and Gemini

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
AGENTS_DIR
required

Absolute path to the directory containing agent definition files (.md or .txt)

AGENT_TYPE
required

Type of AI CLI to use: 'cursor', 'claude', 'gemini', or 'codex'

AGENT_PERMISSION

Approval/sandbox level for sub-agents: 'read-only', 'safe-edit' (default), or 'yolo'

CURSOR_API_KEY
secret

API key for cursor-agent authentication (used only when AGENT_TYPE=cursor; passed via env, never via CLI args)

EXECUTION_TIMEOUT_MS

Maximum execution time for agents in milliseconds (default: 300000, max: 600000)

SESSION_ENABLED

Enable session management to maintain execution history across agent calls (default: false)

SESSION_DIR

Directory path for storing session files (default: .mcp-sessions in current working directory)

SESSION_RETENTION_DAYS

Number of days to retain session history before automatic cleanup (default: 7)

AGENTS_SETTINGS_PATH

Path to CLI settings file/directory. Claude: --settings arg, Cursor: CURSOR_CONFIG_DIR, Codex: CODEX_HOME. Gemini not supported.

MCP quality score · maturity, not trust · methodology
freshness
24
completeness
10
installability
25
documentation
15
stability
5
Alternatives in AI & LLMs