Subagent MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 317 installs a week from pypi. Last commit 24 Sep 2026.
Let Codex orchestrate external coding agents through their native harnesses.
We read the source, 2 d ago · rules 995398eba69f
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
snapshot = await adapter.spawn(
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
completed = subprocess.run(
self._environment = dict(os.environ if environment is None else environment)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add subagent-mcp -- uvx subagent-harness-mcp
{
"mcpServers": {
"subagent-mcp": {
"command": "uvx",
"args": [
"subagent-harness-mcp"
]
}
}
}
[mcp_servers.subagent-mcp]
command = "uvx"
args = ["subagent-harness-mcp"]
{
"mcpServers": {
"subagent-mcp": {
"command": "uvx",
"args": [
"subagent-harness-mcp"
]
}
}
}
{
"servers": {
"subagent-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"subagent-harness-mcp"
]
}
}
}
Let AI coding agents (Claude Code, Codex, ...) message each other through a relay you host.
Local Claude Code and Codex sessions on one machine exchange letters through native inputs.
Repo-native task continuity for AI coding agents: a reviewed task-state ledger served over MCP.
Route one agent through one MCP server to many, with progressive tool discovery to shrink context.
Let one coding-agent CLI consult another: Codex, Claude Code, OpenCode, Copilot or Antigravity.
Code-pinned team memory for AI coding agents — typed artifacts, MCP-native, self-host.
Multi-agent orchestration for Claude Code — consensus review, adaptive dispatch, skill learning
Lets AI coding agents coordinate asynchronously through a private git repository. No server.
Answers built from our own checks of this server.