io.github.shinpr/sub-agents-mcp

io.github.shinpr/sub-agents-mcpv0.14.2Other

MCP server for delegating tasks to specialized AI sub-agents across coding tools

The current version, v0.14.2, was published to the official MCP registry on 2026-09-06. It is distributed as sub-agents-mcp on npm, filed under Other by this index, and declares 12 environment variables. Removals and unreachable sources are measured across every server this index tracks, contract drift across the servers that answer in consecutive snapshots; the index's current counts put this record in context.

In-path gate · all MCP tools

Using io.github.shinpr/sub-agents-mcp in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

uv tool install mcpindex-gate && mcpindex-config-wire

Auditable install path →Watch it hold a drift →

Trust verdict · v1 advisory · method

REVIEWstatus: PARTIALfresh until 2026-09-29 04:05 UTC

screened 2026-08-30tier: scannedgranularity: description-levelsource: registry

Semantic screen found no manipulation pattern in the description. Conformance probe not yet run.

mcpindex.integrity.descriptionpassINFO

evidence“Normal capability description”via static_description

Limits of this verdict

- Semantic screen only - the deterministic conformance probe has not run on this server
- Confidence is reported but not yet calibrated (v1)
- Screen reads the tool description, not the live behavior
- advisory
- registry description only no input schema
- screen model 8b
- The registry listing (version, packages, links) changed after this screen ran - the description we assessed did not

Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page.

Own this server? Screen its description →

That verdict was true at screening time (snapshot 2026-09-14).

Contracts can change after screening, with no version bump. The gate pins io.github.shinpr/sub-agents-mcp’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

See your first HOLD in 2 minutes →

Cite this record

People vet a server before wiring it in. One line on your project site or docs answers that with an independent record: screening verdict, registry provenance, contract drift history. It stays current as new screens and drift events land.

Markdown

[Independent trust record for io.github.shinpr/sub-agents-mcp](https://mcpindex.ai/server/io-github-shinpr-sub-agents-mcp) - screening verdict, registry provenance, and contract drift monitoring.

HTML

<a href="https://mcpindex.ai/server/io-github-shinpr-sub-agents-mcp">Independent trust record for io.github.shinpr/sub-agents-mcp</a> - screening verdict, registry provenance, and contract drift monitoring.

Embed this badge

A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does.

Markdown

[![mcpindex](https://mcpindex.ai/api/v1/badge/io-github-shinpr-sub-agents-mcp)](https://mcpindex.ai/server/io-github-shinpr-sub-agents-mcp)

HTML

<a href="https://mcpindex.ai/server/io-github-shinpr-sub-agents-mcp"><img src="https://mcpindex.ai/api/v1/badge/io-github-shinpr-sub-agents-mcp" alt="mcpindex verdict" height="20" /></a>

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', 'codex', 'command-code', 'glm', 'kimi', 'grok', 'antigravity', or 'opencode'

AGENT_PERMISSION

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

AGENT_MODEL

Optional model override applied to every sub-agent execution by this MCP server

AGENT_EFFORT

Optional backend-specific reasoning effort or model variant. Supported by codex, claude, command-code, glm, kimi, grok, antigravity, and opencode.

CURSOR_API_KEY

secret

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

CLI_API_KEY

secret

Provider API key for AGENT_TYPE=glm or kimi (passed to the claude binary via env, never via CLI args). Restart/reconnect the MCP server after changing it.

EXECUTION_TIMEOUT_MS

Agent execution timeout in milliseconds, as a positive whole number (default: 300000). The server refuses to start on an invalid value such as "5min".

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: 1)

AGENTS_SETTINGS_PATH

Path to CLI settings file/directory. Claude: --settings arg, Cursor: CURSOR_CONFIG_DIR, Codex: CODEX_HOME. GLM/Kimi/Gemini/Grok/Antigravity/OpenCode/Command Code not supported.

MCP quality score · maturity, not trust · methodology

freshness

completeness

installability

documentation

stability

Alternatives in Other

AgentRoam

ai.agentroam/agentroam

Buy travel eSIMs, gift cards and mobile top-ups with crypto — user confirms before any order.

Authoryze

ai.authoryze/authoryze

Give your AI agent a spending limit: approval controls and single-use virtual cards.

io.github.shinzarou-eng/dsh-codebase-chat

Local-first codebase intelligence: cited answers, audits, reports. EN/FR.

Install this server

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "sub-agents-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "--",
        "sub-agents-mcp"
      ],
      "env": {
        "AGENTS_DIR": "<agents_dir>",
        "AGENT_TYPE": "<agent_type>",
        "AGENT_PERMISSION": "<agent_permission>",
        "AGENT_MODEL": "<agent_model>",
        "AGENT_EFFORT": "<agent_effort>",
        "CURSOR_API_KEY": "<your-cursor_api_key>",
        "CLI_API_KEY": "<your-cli_api_key>",
        "EXECUTION_TIMEOUT_MS": "<execution_timeout_ms>",
        "SESSION_ENABLED": "<session_enabled>",
        "SESSION_DIR": "<session_dir>",
        "SESSION_RETENTION_DAYS": "<session_retention_days>",
        "AGENTS_SETTINGS_PATH": "<agents_settings_path>"
      }
    }
  }
}

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "sub-agents-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "--",
        "sub-agents-mcp"
      ],
      "env": {
        "AGENTS_DIR": "<agents_dir>",
        "AGENT_TYPE": "<agent_type>",
        "AGENT_PERMISSION": "<agent_permission>",
        "AGENT_MODEL": "<agent_model>",
        "AGENT_EFFORT": "<agent_effort>",
        "CURSOR_API_KEY": "<your-cursor_api_key>",
        "CLI_API_KEY": "<your-cli_api_key>",
        "EXECUTION_TIMEOUT_MS": "<execution_timeout_ms>",
        "SESSION_ENABLED": "<session_enabled>",
        "SESSION_DIR": "<session_dir>",
        "SESSION_RETENTION_DAYS": "<session_retention_days>",
        "AGENTS_SETTINGS_PATH": "<agents_settings_path>"
      }
    }
  }
}

Cline (cline_mcp_settings.json)

npx -y -- sub-agents-mcp

Claude Code (claude mcp add)

claude mcp add --scope user sub-agents-mcp -- npx -y -- sub-agents-mcp

Gemini CLI (gemini mcp add)

gemini mcp add -s user sub-agents-mcp npx -y -- sub-agents-mcp

Verdict API

curl -s mcpindex.ai/api/v1/trust/server/io-github-shinpr-sub-agents-mcp

Free-tier verdict as JSON: decision + dimensions + severity. Call it from your agent before it invokes a tool it just discovered.

Details

version: v0.14.2
category: Other
verdict expires: 2026-09-29
quality: 80 / 100
operator: shinpr

Listing

Listed from the official MCP registry. Unclaimed by its maintainer. Maintainer? Email us →

Provenance

Each verdict is bound to a hash of the exact description it judged, so a re-crawl that changes the text produces a new record rather than silently inheriting this one. Verdict history is hash-chained and anchored to Bitcoin via OpenTimestamps (latest confirmed at block 966,775). Verify it yourself.

Links

Repository →