Orcareplay runs on your own machine — the client starts it, so there is no endpoint to ping. 957 installs a week from npm. Last commit 16 Sep 2026.
Read, replay and fork recorded coding-agent runs.
We read the source, 21 h ago · rules 3dff92dd89df
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
`manifest will not parse cannot be opened at all. Narrow the match, or: rm -rf ${runDir}`
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.
этот файл ставится пользователю, но в репозитории его нет
const r = spawnSync(exe, args, { encoding: 'utf8', ...opts });
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Orcareplay and you get told the day something new turns up.
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 orcareplay -- npx -y orcareplay
{
"mcpServers": {
"orcareplay": {
"args": [
"-y",
"orcareplay"
],
"command": "npx"
}
}
}
[mcp_servers.orcareplay]
command = "npx"
args = ["-y", "orcareplay"]
{
"mcpServers": {
"orcareplay": {
"args": [
"-y",
"orcareplay"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"orcareplay": {
"args": [
"-y",
"orcareplay"
],
"command": "npx"
}
}
}
Record and replay AI agent execution for debugging
Read-only MCP for OpenVibeCoding runs, workflows, proof, queue, replay, and incident reads.
Session memory for AI coding agents: records decisions and dead ends, flags what went stale.
Read-only, commit-pinned repository context for coding agents.
Gives your coding agent the captured console, network, replay and screenshot evidence for a bug.
Snapshot tests and CI for agent workflows: record a run, replay it at 0 tokens, diff for drift.
Create and manage secure sandboxes for running AI agent code
Sandboxed repo access for coding agents: search, read, patch, run, git -- confined to a repo root.
Answers built from our own checks of this server.