Atlas / MCP servers / ttommyth / Interactive

InteractiveSAFE

mcp/ttommyth/interactive

Vibe coding should have human in the loop! interactive-mcp: Local, cross-platform MCP server for interact with your AI Agent

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
5 3r · 2w · 0d
Transport
stdio
License
MIT
Stars
352
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://www.npmjs.com/package/interactive-mcp) [](https://www.npmjs.com/package/interactive-mcp) [](https://smithery.ai/server/@ttommyth/interactive-mcp) [](https://github.com/ttommyth/interactive-mcp/blob/main/LICENSE) [](https://github.com/prettier/prettier) [](https://github.com/ttommyth/interactive-mcp) [](https://github.com/ttommyth/interactive-mcp/commits/main)

[](https://cursor.com/install-mcp?name=interactive&config=eyJjb21tYW5kIjoibnB4IC15IGludGVyYWN0aXZlLW1jcCJ9)

A MCP Server implemented in Node.js/TypeScript, facilitating interactive communication between LLMs and users. Note: This server is designed to run locally alongside the MCP client (e.g., Claude Desktop, VS Code), as it needs direct access to the user's operating system to display notifications and command-line prompts.

(Note: This project is in its early stages.)

Want a quick overview? Check out the introductory blog post: Stop Your AI Assistant From Guessing — Introducing interactive-mcp

Demo Video

Read from source at commit f6e99b677b35OBSERVED · 2026-10-02
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add interactive-mcp -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "interactive-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
03

Exposed tools (5)

3 read · 2 write · 0 destructive.

ToolRiskDescription
ask_intensive_chatread
message_complete_notificationread
request_user_inputread
start_intensive_chatwrite
stop_intensive_chatwrite
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (7 observation(s))
Network
none-observed
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (11)

LOWInventory / provenance · inv.hidden_file · CWE-1104
.releaserc.yml
.releaserc.yml
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/commands/input/index.ts:10
import logger from '../../utils/logger.js';
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/commands/input/ui.tsx:7
import logger from '../../utils/logger.js';
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/commands/input/ui.tsx:8
import { InteractiveInput } from '../../components/InteractiveInput.js'; // Import shared component
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/commands/intensive-chat/index.ts:7
import logger from '../../utils/logger.js';
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/commands/intensive-chat/ui.tsx:9
import logger from '../../utils/logger.js';
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@inkjs/ui, @modelcontextprotocol/sdk, @types/yargs, ink, node-notifier, pino, react, react-dom
Why it matters. 35 dependency range(s) float
Fix. pin exact versions or ship a lockfile
INFOInventory / provenance · inv.oversize · CWE-1104
docs/assets/end-intensive-chat.gif
docs/assets/end-intensive-chat.gif
Why it matters. 3959598 bytes not read
INFOInventory / provenance · inv.oversize · CWE-1104
docs/assets/end-notification.gif
docs/assets/end-notification.gif
Why it matters. 5625192 bytes not read
INFOInventory / provenance · inv.oversize · CWE-1104
docs/assets/normal-question.gif
docs/assets/normal-question.gif
Why it matters. 4487339 bytes not read
INFOInventory / provenance · inv.oversize · CWE-1104
docs/assets/start-intensive-chat.gif
docs/assets/start-intensive-chat.gif
Why it matters. 5789326 bytes not read

Gates applied: no_behavioural_pass.

Audited 2026-10-02 · audit v0.4.1 · source sha f6e99b677b35full audit observations/trust-audit/mcp-server/ttommyth__interactive.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-02f6e99b677b35SAFEB89first audit
06

Questions

What is the Interactive MCP server?

Vibe coding should have human in the loop! interactive-mcp: Local, cross-platform MCP server for interact with your AI Agent

What tools does Interactive expose?

5 in total: 3 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Interactive safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Interactive need?

No credential environment variables were found in its source, so it appears to need none.

How does Interactive run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as interactive-mcp at 1.0.0.

How current is this page?

The grade is for one exact copy of the source (f6e99b677b35), read on 2026-10-02. The repository is watched and re-audited when it changes.

Advertisement