Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Create and manage residential and mobile proxies: geo targeting, usage limits, spend reports.
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.
AuthorizationYou need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Run this in your terminal
claude mcp add --transport http 2extract https://mcp.2extract.com/mcp --header 'Authorization: Bearer {api_key}'Fill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"2extract": {
"url": "https://mcp.2extract.com/mcp",
"headers": {
"Authorization": "Bearer {api_key}"
}
}
}
}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": {
"2extract": {
"type": "http",
"url": "https://mcp.2extract.com/mcp",
"headers": {
"Authorization": "Bearer {api_key}"
}
}
}
}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 address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Your choice stays on this device in a cookie; no account needed.
Authorization required HTTP headerThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
We have not read this server’s tool list yet; we check endpoints in rotation.
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 6, 2026
The registry name was verified against the domain 2extract.com (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
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.
You need to fill in: Authorization
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.0.2) reached the registry 16 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, Symantec Cloud DLP AIops
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.
Governed Symantec Cloud DLP — 14 MCP tools, read-only with audit.
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.
VS Code asks for the API key on install and does not store it in the config. Cursor installs with a placeholder: replace 2xt_your_api_key in mcp.json with your key.
Remote Model Context Protocol server for 2extract. It lets an AI agent create and manage residential and mobile proxies, pick geo targeting down to city, ZIP or carrier, set traffic and spend limits, and report on usage and cost.
This is a hosted server. There is nothing to install or run locally: your MCP client connects to the URL below with your 2extract API key.
| Endpoint | https://mcp.2extract.com/mcp |
| Transport | Streamable HTTP |
| Auth | Authorization: Bearer 2xt_... (2extract API key) |
proxies:read, proxies:write, balance:read, stats:read, geo:read. Write scopes do not include read access, so most workflows need both proxies:read and proxies:write.A read-only key (no proxies:write) is enough for reporting and lookups.
claude mcp add --transport http 2extract https://mcp.2extract.com/mcp \
--header "Authorization: Bearer 2xt_your_api_key"
The key is read from the EXTRACT_API_KEY environment variable; Codex adds Bearer itself:
export EXTRACT_API_KEY=2xt_your_api_key
codex mcp add 2extract --url https://mcp.2extract.com/mcp --bearer-token-env-var EXTRACT_API_KEY
Or edit ~/.codex/config.toml (or .codex/config.toml in a trusted project):
[mcp_servers.2extract]
url = "https://mcp.2extract.com/mcp" bearer_token_env_var = "EXTRACT_API_KEY"
gemini mcp add -s user --transport http \
--header "Authorization: Bearer 2xt_your_api_key" \ 2extract https://mcp.2extract.com/mcp
Or edit ~/.gemini/settings.json (or .gemini/settings.json in a project):
{
"mcpServers": { "2extract": { "httpUrl": "https://mcp.2extract.com/mcp", "headers": { "Authorization": "Bearer 2xt_your_api_key" } } } }
opencode.json in your project (or ~/.config/opencode/opencode.json). The key is read from the EXTRACT_API_KEY environment variable:
{
"$schema": "https://opencode.ai/config.json", "mcp": { "2extract": { "type": "remote", "url": "https://mcp.2extract.com/mcp", "enabled": true, "headers": { "Authorization": "Bearer {env:EXTRACT_API_KEY}" } } } }
claude_desktop_config.json:
{
"mcpServers": { "2extract": { "type": "http", "url": "https://mcp.2extract.com/mcp", "headers": { "Authorization": "Bearer 2xt_your_api_key" } } } }
~/.cursor/mcp.json or .cursor/mcp.json:
{
"mcpServers": { "2extract": { "url": "https://mcp.2extract.com/mcp", "headers": { "Authorization": "Bearer 2xt_your_api_key" } } } }
.vscode/mcp.json (the key is requested on first use and not stored in the file):
{
"inputs": [ { "type": "promptString", "id": "2extract-api-key", "description": "2extract API key", "password": true } ], "servers": { "2extract": { "type": "http", "url": "https://mcp.2extract.com/mcp", "headers": { "Authorization": "Bearer ${input:2extract-api-key}" } } } }
Open the Cline panel, click MCP Servers, then Configure MCP Servers, and add to cline_mcp_settings.json:
{
"mcpServers": { "2extract": { "type": "streamableHttp", "url": "https://mcp.2extract.com/mcp", "headers": { "Authorization": "Bearer 2xt_your_api_key" }, "disabled": false } } }
Keep "type": "streamableHttp": without it Cline falls back to the older SSE transport.
Any client that supports remote MCP servers works. Give it the endpoint URL, the Streamable HTTP transport and the Authorization header.
| Tool | What it does | Scope |
|---|---|---|
getAccountBalance | Available funds, whether a new proxy can be created, and the proxy username prefix | balance:read |
getAccountTrafficUsage | Traffic and spend over a period, for the account or one proxy | stats:read |
listAccountBalanceHistory | Deposits and charges over a period | stats:read |
| Tool | What it does | Scope |
|---|---|---|
listGeoCountries | Countries available for targeting | geo:read |
searchGeoRegions | Regions and states within a country | geo:read |
searchGeoCities | Cities within a country or region | geo:read |
searchGeoZips | ZIP and postal codes within a country | geo:read |
searchGeoISP | Mobile carriers for ISP targeting | geo:read |
| Tool | What it does | Scope |
|---|---|---|
listProxyPlans | Available plans and their prices | proxies:read |
| Tool | What it does | Scope |
|---|---|---|
listProxyResources | Every proxy on the account, with traffic and spend | proxies:read |
getProxyResource | Full detail for one proxy | proxies:read |
createProxyResource | Create a proxy (billable) | proxies:write |
updateProxyResource | Change description, status, geo, whitelist or limits | proxies:write |
deactivateProxyResource | Stop traffic without deleting the proxy | proxies:write |
deleteProxyResource | Permanently remove a proxy (asks for confirmation) | proxies:write |
regenerateProxyPassword | Issue a new password (asks for confirmation) | proxies:write |
setProxyLimits | Cap traffic or spend per day or month | proxies:write |
setProxyIpWhitelist | Restrict which IP addresses can use the proxy | proxies:write |
setProxyTargetHosts | Restrict which domains the proxy can reach (wildcards like *.example.com) | proxies:write |
buildConnectionString | Ready-to-use username and connection string with geo, carrier and sticky-session parameters | proxies:read, balance:read |
Confirmation for destructive tools happens in your client. If the client does not ask, any key with proxies:write can run them, so scope keys accordingly.
| Prompt | Arguments | What it does |
|---|---|---|
create-proxy-resource | purpose, proxy_type?, country? | Creates a proxy for a stated job and returns a connection string |
build-connection-string | proxy_id?, purpose? | Builds a connection string for an existing proxy |
monthly-cost-report | period | Traffic and spend per proxy for a period, with outliers flagged. Read-only |
cleanup-unused-proxies | none | Finds proxies with no traffic in 30 days and deactivates them after you confirm. Never deletes |
serp_us proxy."The server source code is not published. This repository holds the public listing, client configuration examples and the registry manifest (server.json).