FRENES

Code execution · MCP server

OrcaReplay: MCP server, setup and security

OrcaReplay is an open-source MCP server that lets an AI agent read, replay, and fork recorded runs of coding agents. Its repository has 281 stars and its last commit is from October 1, 2026 and it is licensed under Apache-2.0.

Actively maintainedSystem access

What OrcaReplay does

According to its repository: “Read, replay and fork recorded coding-agent runs.”

An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. OrcaReplay is listed under Code execution, a category of 32 servers in the directory, where it ranks #8 by stars.

Topics declared by the repository: agent-debugging, agent-tracing, ai-agent, ai-agents, ai-debugger, ai-debugging.

Installing and connecting OrcaReplay

Distribution modes declared in the official MCP registry:

  • npm package (Node.js, usually started with npx)

Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: TypeScript.

Security: what to check

An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.

Points found for OrcaReplay:

  • System access: the Code execution category gives the agent control over files, a terminal, code or a browser. A booby-trapped instruction in content the agent reads (prompt injection) can then turn into an action.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on August 29, 2026, the Continuum-AI-Corp/OrcaReplay repository has 281 stars and 66 forks, with 0 open issues. It has more stars than 82% of the servers in the directory. It received changes this month. Version published in the registry: 0.5.0 (September 29, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

Container useContainer use : 4.1K4.1KMATLAB MCP ServerMATLAB MCP Server : 1.7K1.7KLLM SandboxLLM Sandbox : 1.1K1.1KTidewave PhoenixTidewave Phoenix : 858858Tidewave RailsTidewave Rails : 476476SuperserveSuperserve : 466466IPhone UseIPhone Use : 345345OrcaReplayOrcaReplay : 281281
GitHub stars of the most followed servers in the category (log scale); OrcaReplay in orange. Checked October 25, 2026.

Verdict

OrcaReplay is a reasonable choice; check the points below before connecting it.

Strengths

  • Active project: recent commit
  • Widely followed: 281 stars
  • Listed in the official MCP registry
  • Permissive licence (Apache-2.0)

Avoid if…

  • You cannot isolate the agent (sandbox, container)

Frequently asked questions

How do I install OrcaReplay?

OrcaReplay is distributed as npm package (Node.js, usually started with npx). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of Continuum-AI-Corp/OrcaReplay.

Is OrcaReplay free?

The code is published under the Apache-2.0 licence and can be used free of charge.

Is OrcaReplay safe?

Points to watch: system access. Give it minimum rights and approve sensitive actions.

Is it an official server?

Nothing says so: it is a project published by Continuum-AI-Corp on GitHub. Check who maintains it before giving it access.

What are the alternatives to OrcaReplay?

In the same category: Container use, LLM Sandbox, Tidewave Phoenix, and Superserve.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score