/ 100

11 days ago

glama

Super Subagents

Spawn parallel autonomous AI agent sessions from a single MCP client. Each agent gets its own workspace, tools, and execution context.

→ yigitkonur/mcp-supersubagents · listed on glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.

Install from

Glama

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings

⚠️

Known vulnerabilities in dependencies: 2 high

Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.

✅

No credential exfiltration, no sensitive file access, no obfuscation

Static analysis found nothing flowing your secrets to unexpected places.

🔐

You'll be asked for 5 credentials: CODEX_API_KEY, GH_PAT_TOKEN, GH_TOKEN, GITHUB_TOKEN, OPENAI_API_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// required environment variables

This server reads these from process.env. You'll be asked to provide them before it can run.

configBROKEN_PIPE_FORCE_EXIT_TIMEOUT_MS— 15000 (15s) Max wait time for graceful shutdown after broken pipe

configCLAUDE_FALLBACK_MAX_BUDGET_USD

configCLAUDE_FALLBACK_MAX_TURNS

configCLAUDE_FALLBACK_MODEL

configCLAUDE_FALLBACK_PERMISSION_MODE

configCLAUDE_FALLBACK_TOOL_POLICY

🔐 secretCODEX_API_KEY— OPENAI_API_KEY / -- API key for Codex provider

configCODEX_APPROVAL_POLICY

configCODEX_MODEL— o4-mini Default model for Codex tasks

configCODEX_PATH

configCODEX_SANDBOX_MODE— workspace-write Sandbox mode: read-only, workspace-write, danger-full-access

configCOPILOT_PATH

configCOPILOT_PERMISSION_MODE

configCOPILOT_STRICT_HEALTH_CHECK

configDISABLE_CLAUDE_CODE_FALLBACK— false Disable automatic fallback to Claude Agent SDK

configDISABLE_CODEX_FALLBACK— false Disable Codex SDK in the provider chain

configDISABLE_COPILOT

🔐 secretGH_PAT_TOKEN— Fallback PAT token(s), comma-separated

🔐 secretGH_TOKEN— GITHUB_TOKEN / -- Single token fallback

configGITHUB_PAT_TOKENS— header ": ghp_token1,ghp_token2"

🔐 secretGITHUB_TOKEN— / GH_TOKEN -- Single token fallback

configMAX_CONCURRENT_CLAUDE_FALLBACKS— 3 Max simultaneous Claude sessions

configMAX_CONCURRENT_CODEX_SESSIONS— 5 Max simultaneous Codex sessions

configMCP_ENABLED_TOOLS

configMCP_FUNC_SCENARIO

configMCP_FUNC_TASK_TIMEOUT_MS

configMCP_FUNC_WAIT_TIMEOUT_MS

configMCP_SMOKE_EXPECT_FALLBACK_ACTIVATED

configMCP_SMOKE_EXPECT_PROVIDER

configMCP_SMOKE_REQUIRE_COMPLETED

configMCP_SMOKE_SCENARIO

configMCP_SMOKE_TASK_TIMEOUT_MS

configMCP_SMOKE_WAIT_TIMEOUT_MS

configMODEL_OVERRIDE

🔐 secretOPENAI_API_KEY— codex OpenAI Codex SDK

configPROVIDER_CHAIN— codex,copilot,!claude-cli (default)

// full audit trail

The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.

// improvement guidance — verified publishers only

We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Score](https://m8ven.ai/badge/mcp/yigitkonur-mcp-supersubagents-13bb8d)](https://m8ven.ai/mcp/yigitkonur-mcp-supersubagents-13bb8d)

commit: c30fd7c128c97d9b62eba329251b7e040aa64a36

code hash: 9befc693d2d8708043483fb5e8203a6bf6e81e992028bf27531702120c19e2cd

verified: 6/15/2026, 12:47:37 PM

view raw JSON →