Code Interpreter Agent by Nova (CIVAI)

co.civai.novaPublished by nova.civai.coOfficial publisherv1.0.0Updated Oct 24, 2026

I do everything related to coding and execution tasks

The publisher's own server: Blogger Agent by Nova (CIVAI)

VerifiedStreamable HTTPWeb executableCloud & Infrastructure Developer Tools

Server details

Identifier: co.civai.nova/code-interpreter-agent
Transport: Streamable HTTP
Runtime: Web executable
Trust: Verified
Published: Sep 21, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified that this server's namespace belongs to nova.civai.co, which also runs its endpoint. That identifies the publisher; it does not make the server's tools safe.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/co.civai.nova%2Fcode-interpreter-agent.svg)](https://sourceweft.com/mcp/co.civai.nova%2Fcode-interpreter-agent?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

A remote code interpreter that lets an assistant generate, run, and debug code and execute bash, sh, or zsh terminal commands.

What you can do: This remote server exposes a code interpreter that can generate code without running it, generate and execute code, and debug or update existing code. It also offers terminal command tools for bash, sh, and zsh, plus conversational tools for clarifying ambiguous requests. The provider describes it as covering coding and execution tasks generally.
When to use it: Useful when an assistant needs to actually run code or shell commands rather than only draft them, for example to compute results, test snippets, or debug existing scripts. Less useful if you only need code suggestions without execution.
Requirements: Connects to a remote streamable HTTP endpoint at nova.civai.co; no local package, environment variables, or headers are declared. The manifest declares no authentication, though the provider's site may impose its own access terms.

Before you install

Code and shell commands are executed on the provider's remote service, so anything sent there leaves your machine. The bash, sh, and zsh tools can run arbitrary terminal commands with whatever access the remote runner grants; avoid sending secrets or sensitive data, and review what the assistant is about to execute.

Installation

In SourceWeft

Open Code Interpreter Agent by Nova (CIVAI) in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/co.civai.nova%2Fcode-interpreter-agent/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "code-interpreter-agent-by-nova-civai": {
      "type": "http",
      "url": "https://nova.civai.co/mcp/agents/code-interpreter-agent"
    }
  }
}

Tools

interpreter__generate_code_only

Code interpreter (runner operator): generate code only

Parametersdetail

interpreter__generate_and_execute_code

Code interpreter (runner operator): generate and execute code

Parametersdetail

interpreter__debug_update_existing_code

Code interpreter (runner operator): debug update existing code

Parametersdetail

interpreter__converse

Reply conversationally when the request is ambiguous or needs clarification.

Parametersreply_hint

command__bash

Terminal command (runner operator): bash

Parametersdetail

command__sh

Terminal command (runner operator): sh

Parametersdetail

command__zsh

Terminal command (runner operator): zsh

Parametersdetail

command__converse

Reply conversationally when the request is ambiguous or needs clarification.

Parametersreply_hint

Version history

v1.0.0LatestSep 21, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
LicenseNot applicable
A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.