reevesagents runs on your own machine — the client starts it, so there is no endpoint to ping. 600 installs a week from npm. Last commit 16 Oct 2026.
Spawn, read and steer AI coding CLIs (Claude Code, Codex, Kimi and more) in local tmux windows.
We read the source, 22 h ago · rules ccca72095570
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.
postinstall: node -e "try{process.env.npm_config_global==='true'&&process.stdout.isTTY&&!process.env.CI&&process.stdout.write('\nReevesAgents installed. Run: reevesagents attach to connect your AI CLIs, then restart them.\n\n')}catch(e){}"
const out = execFileSync(LOOKUP, [bin], { encoding: 'utf8' }).trim()
for (const [key, value] of Object.entries(process.env)) {
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
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 reevesagents -- npx -y reevesagents
{
"mcpServers": {
"reevesagents": {
"args": [
"-y",
"reevesagents"
],
"command": "npx"
}
}
}
[mcp_servers.reevesagents]
command = "npx"
args = ["-y", "reevesagents"]
{
"mcpServers": {
"reevesagents": {
"args": [
"-y",
"reevesagents"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"reevesagents": {
"args": [
"-y",
"reevesagents"
],
"command": "npx"
}
}
}
Start, prompt and read AI coding agent sessions (Claude Code, Codex, Gemini CLI and more) in Codeman
Tokens and cost for Claude Code, Codex and 22 more AI coding agents, from local session files.
Local codebase memory and repository code search for Codex, Claude Code, and MCP coding agents.
Read local AI agent sessions (Claude Code, Codex, OpenCode, Antigravity, Pi): intents, plans, tools
Local MCP runtime for coordinating Freebuff, Codex, OpenCode, Claude Code, and Cursor agents.
Local long-term memory MCP server (SQLite) for AI coding agents — OpenCode, Claude Code, Cursor
Local code search for AI coding agents: hybrid keyword + semantic + SQL over an index in your repo.
Shared memory and mail for your AI agents. Verified with Claude Code; other MCP clients in testing.
Answers built from our own checks of this server.