Orcareplay logo

Orcareplay

Records coding-agent runs, replays them offline, and forks them from checkpoints onto another model.

Install Orcareplay

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "orcareplay": {
      "command": "uvx",
      "args": [
        "orcareplay-langgraph"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

uvx orcareplay-langgraph

Process exited before answering initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked .

Overview

orcareplay MCP server records coding-agent sessions and stores their model requests, responses, tool activity, and workspace events in a trace. It can replay a recorded run without calling a model, or fork from a checkpoint and continue with a different model. Use it to investigate agent behavior, reproduce failures, compare models, or inspect runs after the original terminal session has ended.

Use cases

  • Record a coding-agent run for later debugging
  • Replay a failed run without calling a model
  • Fork a run from a checkpoint onto another model
  • Compare model results against the same project state

Key features

  • Coding-agent run recording
  • Offline trace replay
  • Checkpoint-based model forking
  • Timeline capture for tools and workspace events
  • System-prompt capture
  • Optional TLS interception

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked

Recent health check succeeded.

20/20 checks healthy over the last 53d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 6d ago via OSV.dev · orcareplay-langgraph (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars1.1kStargazers on the source repository.
Last commit1mo agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.

How Orcareplay works

What orcareplay MCP server does

orcareplay MCP server is designed for recording and examining coding-agent runs. It captures more than model traffic: the trace can include streamed output, tool calls and results, shell exit codes, timing, file writes, and other events observed by its capture layers. This gives developers a timeline for investigating what an agent did, including actions that may not be visible through an SDK wrapper.

A recorded run can be replayed from disk. Exact replay blocks unmatched model egress, so the model is not called and the replay does not consume additional model tokens. The project also supports starting from a selected checkpoint and continuing with another model. That makes it possible to compare model behavior while preserving the earlier conversation and workspace state.

How it works

The CLI places a local proxy in front of the agent and supplies environment settings rather than requiring changes to the agent itself. The proxy observes requests and streamed responses, while additional capture layers cover process output, MCP configuration rewriting, workspace changes, and selected hardcoded network origins. Events are written into a single ordered trace.

During replay, the proxy serves matching responses from that trace. The default mode refuses requests that are not represented in the recording. A loose mode can forward an unmatched request to the provider and marks the replay as live on divergence. Recorded tool calls still execute for real, so replay is not a security sandbox; shell commands or MCP servers that open their own connections may access the network.

Setup and configuration

The package is installed globally with npm and exposes the orca command:

Terminal
npm i -g orcareplay
orca record claude
orca replay last

The repository states that Node.js 20 or newer is supported. An agent must be installed for the record and replay examples, and normal recording may require a provider key, network access, and model tokens. The orca quickstart command creates a small project, a genuine bug, and a sample recording so the workflow can be tried without supplying an existing agent setup.

Tools and capabilities

The documented command-level capabilities include:

  • Recording an unmodified coding-agent run.
  • Replaying the latest or another saved run from its trace.
  • Forking from a chosen step with a different model.
  • Comparing outcomes by grading the resulting project, such as with npx tsc --noEmit.
  • Capturing an agent’s assembled system prompt with the capture script.
  • Inspecting runs after the original terminal has closed because traces are stored as files.

orcareplay MCP server also supports recording agents whose model endpoint cannot be redirected, using the optional TLS interception mode described by the project.

Limitations and notes

It also does not provide client-specific setup for Cursor or other MCP hosts. Treat the documented interface as the orca CLI unless the repository’s current documentation supplies additional MCP configuration.

Exact replay only guarantees model-response reuse for requests present in the trace. Tools run again, and network behavior from those tools is outside that guarantee. TLS interception can record metadata for tunneled hosts, but it does not turn replay into isolation. Use a separate sandbox when filesystem or network side effects must be contained.

Written by AllMCPs with AI assistance from the project’s README and listing data. How we build listings

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Orcareplay

orcareplay is an MCP server that connects coding agents to recorded execution traces. Its main tools are recording runs, replaying them offline without a model call, and forking from a checkpoint onto another model. The project also captures tool activity, process events, workspace changes, and selected network details for later investigation.

Install it with `npm i -g orcareplay`, which places the `orca` command on your PATH. The repository specifies Node.js 20 or newer.

Yes. Normal replay serves matching model responses from the saved trace and blocks unmatched model egress, so no model is called and no new model tokens are spent. Recorded tool calls still execute, and tools that make their own network connections are not automatically isolated.

The README names Claude Code and Codex among supported agent contexts, but it does not provide Cursor configuration or claim compatibility with that client.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewOrcareplay AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/orcareplay?style=directory)](https://allmcps.com/mcp/orcareplay)
HTML Embed
<a href="https://allmcps.com/mcp/orcareplay"><img src="https://allmcps.com/api/badge/orcareplay?style=directory" alt="Orcareplay on AllMCPs" /></a>