Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Conversation drift visualization for Claude. Color-coded inflection points and one-click forking.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"threadmap": {
"command": "npx",
"args": [
"-y",
"threadmap-mcp"
]
}
}
}Run this in your terminal
claude mcp add threadmap -- npx -y threadmap-mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"threadmap": {
"command": "npx",
"args": [
"-y",
"threadmap-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"threadmap": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"threadmap-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account Advertflair, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (1.0.0) reached the registry 7 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, EmbeddedCI BenchPod
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Drive a BenchPod hardware-in-the-loop bench: power, flash, UART, I2C, CAN, analog and logic.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Conversation drift visualization and forking for Claude.
Stop losing your original intent. See exactly where your conversation drifted. Fork from any point and pick up with clean context.
Color dots on every message — live drift tracking:
Timeline panel with fork buttons at every inflection point:
| MCP Server | Chrome Extension | |
|---|---|---|
| Works in | Claude Code (terminal) | claude.ai (browser) |
| Install | claude mcp add threadmap npx threadmap-mcp | Load unpacked from chrome-extension/ folder |
| What you get | 7 tools — track, timeline, fork, branch | Color dots on every message, timeline panel, one-click fork |
| Best for | Developers building with Claude Code | Anyone using claude.ai daily |
Both are in this repo. Use one or both.
The Chrome extension injects ThreadMap directly into the claude.ai interface. No config. Just install and open Claude.
1. Clone or download this repo
chrome-extension/
├── manifest.json — Extension config (Manifest v3) ├── content.js — Core drift engine + DOM injection ├── threadmap.css — All injected styles ├── popup.html — Extension popup with color legend ├── icon16.png — Icons ├── icon48.png └── icon128.png
Heads up: The extension uses Developer mode (load unpacked). A Chrome Web Store version is on the roadmap.
The MCP server adds 7 tools to Claude Code for programmatic drift tracking.
claude mcp add threadmap npx threadmap-mcp
Or manually add to ~/.claude/claude_desktop_config.json:
{
"mcpServers": { "threadmap": { "command": "npx", "args": ["threadmap-mcp"] } } }
threadmap_track(sessionId="myproject", role="user", content="build me a login system with JWT auth")
→ 🔵 Blue — Drift: 0% — Origin intent set
threadmap_track(sessionId="myproject", role="user", content="the refresh token keeps expiring after 30 seconds") → 🟠 Orange — Drift: 63% — ⚡ INFLECTION POINT detected
threadmap_timeline(sessionId="myproject") → Full color-coded map of all messages with fork instructions
threadmap_fork(sessionId="myproject", messageIndex=6, branchName="jwt-debug") → 🌿 Branch created — clean context from messages 1–7
| Tool | What it does |
|---|---|
threadmap_track | Track a message, get drift score + color |
threadmap_timeline | Full color-coded conversation map |
threadmap_fork | Fork from any message index |
threadmap_branch_context | Clean context packet for any branch |
threadmap_status | Quick current drift check |
threadmap_reset | Archive thread, start fresh |
threadmap_legend | Show color reference guide |
| Color | Drift | Meaning |
|---|---|---|
| 🔵 Blue | 0–15% | On track — core intent |
| 🟢 Green | 16–35% | Productive expansion |
| 🟡 Yellow | 36–55% | Adjacent drift |
| 🟠 Orange | 56–72% | Inflection point — meaningful pivot |
| 🔴 Red | 73–88% | Full context break |
| 🟣 Purple | 89–95% | Meta — talking about the conversation |
| ⚪ White | 96–100% | Resolution |
Orange and Red = fork candidates. The conversation has left your original intent behind.
Claude Code — architecture integrity Track every message while building. Orange = scope creep. Fork before the drift gets worse. Architecture decisions from the first 10 messages stay clean.
Long previous conversations Click ↺ rescan in the Chrome extension. ThreadMap scrolls to the top, loads all messages, scans every one, then returns you to the bottom — all dots appear.
Team handoffs Use threadmap_branch_context to extract a clean summary of what was decided. Paste it into a new session — no scrolling through 200 messages.
Non-linear conversation navigation is the missing primitive for AI-native work. Right now Claude conversations are books with no table of contents, no chapters, no bookmarks.
ThreadMap is the table of contents. If this becomes the standard, it travels across Claude, GPT, Gemini, anything. Nobody owns it. Everybody benefits.
MIT licensed. See CONTRIBUTING.md.
git clone https://github.com/Advertflair/threadmap-mcp
cd threadmap-mcp npm install npm run build
PRs welcome especially for: better drift scoring, Chrome extension improvements, and other AI platform support.
MIT — see LICENSE
*Built by Advertflair. Open source. Ship it.*