Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Pre-execution audit for autonomous agents. Independent receipt before irreversible actions.
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.
XAPS_AGENT_KEY, XAPS_API_URLValues marked secret are keys to your account. Never share them or paste them into a chat.
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": {
"xaps": {
"command": "uvx",
"args": [
"xaps-sdk"
],
"env": {
"XAPS_AGENT_KEY": "your-value",
"XAPS_API_URL": "your-value"
}
}
}
}Run this in your terminal
claude mcp add xaps --env XAPS_AGENT_KEY=your-value --env XAPS_API_URL=your-value -- uvx xaps-sdkFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"xaps": {
"command": "uvx",
"args": [
"xaps-sdk"
],
"env": {
"XAPS_AGENT_KEY": "your-value",
"XAPS_API_URL": "your-value"
}
}
}
}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": {
"xaps": {
"type": "stdio",
"command": "uvx",
"args": [
"xaps-sdk"
],
"env": {
"XAPS_AGENT_KEY": "your-value",
"XAPS_API_URL": "your-value"
}
}
}
}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.
XAPS_API_URL envThese 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 6, 2026
The registry name was verified with the GitHub account APMC1, 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.
You need to fill in: XAPS_AGENT_KEY
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 (0.1.2) reached the registry 5 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, yontu
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.
Türkçe yazı denetimi: TDK kuralları, yapay zekâ izleri, metin türüne göre üslup.
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.
The Cognitive Circuit Breaker for Autonomous Agents
Xaps is an economic security layer for autonomous AI agents. Before executing a smart contract, transfer, or financial action, your agent calls Xaps for an independent dual-agent audit. Standard Web3 tools verify signatures — Xaps verifies intent and logic.
pip install xaps-sdk
Or install from this repository:
pip install "xaps-sdk @ git+https://github.com/APMC1/xaps-sdk.git@v0.1.3"
from xaps import XapsClient, XapsRejectedError
client = XapsClient(api_key="your_agent_key")
receipt = client.audit( action="execute_smart_contract", contract_address="0x742d35Cc6634C0532925a3b844Bc9e7595f0bEb", amount=1000.0, )
audit = receipt["audit"] if audit["status"] == "REJECTED": raise XapsRejectedError(audit["beta_attack"], receipt=receipt)
print(f"Approved: {audit['alpha_defense']}") print(f"Balance remaining: ${receipt['remaining_balance']:.2f}")
from xaps import XapsClient
async with XapsClient(api_key="your_agent_key") as client: receipt = await client.audit_async( action="execute_smart_contract", contract_address="0x742d35Cc6634C0532925a3b844Bc9e7595f0bEb", amount=1000.0, )
Use the XAPS MCP server to audit high-stakes actions from Claude Desktop, Cursor, or any MCP host. See docs/mcp-host-integration.md for full setup.
xaps_audit in 60 Secondsxaps-mcp console command): pip install xaps-sdk
export XAPS_AGENT_KEY="your_agent_key"
~/Library/Application Support/Claude/claude_desktop_config.json): {
"mcpServers": { "xaps-audit": { "command": "xaps-mcp" } } }
For local dev from a git clone, use python /path/to/xaps_mcp_server.py with XAPS_MCP_DEV=1 instead.
Full example: examples/mcp_claude_desktop_config.json
Before any
send_transaction,approve, ordepositcall: invokexaps_auditwithaction,contract_address, andamount.
Agent rule templates: examples/.agentrc
| Variable | Default | Description |
|---|---|---|
XAPS_AGENT_KEY | — | Agent billing key (alternative to constructor arg) |
XAPS_API_URL | https://api.xaps.network | API base URL |
# Or pass explicitly
client = XapsClient(api_key="...", base_url="https://api.xaps.network")
XapsClient(api_key=None, base_url=..., timeout=10.0)Create a client. Raises ValueError if no API key is provided.
client.audit(action, contract_address, amount, payload_override=None)Synchronous audit. Returns receipt dict:
{
"xaps_receipt": true, "agent_key": "...", "remaining_balance": 9.99, "audit": { "status": "APPROVED", "alpha_defense": "...", "beta_attack": "..." } }
await client.audit_async(...)Async variant for agents running on asyncio.
audit_then_query / query_sinkAfter a Tollbooth receipt, agents can call the subsidized Sink for real structured data (GitHub / HTTP). That is the integration carrot: rails → utility.
from xaps import XapsClient
with XapsClient() as client:
result = client.audit_then_query( "github repo anthropics/anthropic-sdk-python", oracle_url="http://localhost:8766", # or XAPS_ORACLE_URL ) print(result"sink")
receipt = client.audit_auto("query_oracle", "", 0.01) data = client.query_sink("search github MCP agents", receipt)
Env: XAPS_ORACLE_URL (sink base), XAPS_API_URL + XAPS_AGENT_KEY (tollbooth).
MCP: xaps_audit_then_query, xaps_sink_query, xaps_sink_health.
| Exception | When |
|---|---|
XapsAuthError | Invalid or missing API key (401) |
XapsPaymentError | Insufficient prepaid balance (402) |
XapsRateLimitError | Too many requests (429) |
XapsAPIError | Other API errors |
XapsRejectedError | Audit returned REJECTED (optional helper) |
git clone https://github.com/APMC1/xaps-sdk.git
cd xaps-sdk pip install -e ".[dev]" pytest
The sovereign node (
xap-sovereign-node) is private. This public repo contains only the SDK.
Your Xaps Agent Key is a billing identifier, not a cryptographic secret. Do not commit it to version control.
MIT — see LICENSE.