Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Cross-chain bridge aggregator — compares LI.FI, deBridge, Relay, Across & more for best rates.
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.
LIFI_API_KEY, SQUID_INTEGRATOR_IDValues 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": {
"bridgekitty": {
"command": "npx",
"args": [
"-y",
"@persistenceone/bridgekitty"
],
"env": {
"LIFI_API_KEY": "your-value",
"SQUID_INTEGRATOR_ID": "your-value"
}
}
}
}Run this in your terminal
claude mcp add bridgekitty --env LIFI_API_KEY=your-value --env SQUID_INTEGRATOR_ID=your-value -- npx -y @persistenceone/bridgekittyFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"bridgekitty": {
"command": "npx",
"args": [
"-y",
"@persistenceone/bridgekitty"
],
"env": {
"LIFI_API_KEY": "your-value",
"SQUID_INTEGRATOR_ID": "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": {
"bridgekitty": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@persistenceone/bridgekitty"
],
"env": {
"LIFI_API_KEY": "your-value",
"SQUID_INTEGRATOR_ID": "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.
SQUID_INTEGRATOR_ID 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 persistenceOne, 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: LIFI_API_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 (0.3.1) reached the registry 8 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, FOGA node
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.
A Finch OG Agent cell as an MCP server: read the world, dry-run and take ERC-8414 tenders by policy.
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.
Cross-chain bridge aggregator MCP server for AI agents. One server, 5 bridge backends, best routes across EVM, Solana, and Cosmos chains.
BridgeKitty gives AI agents (Claude, Cursor, GPT, or any MCP-compatible AI) the ability to find and execute cross-chain bridge transfers — with automatic route optimization, fee comparison, balance checks, and safety warnings.
Latest npm release: @persistenceone/bridgekitty@0.3.9
xprt-farming-toolkit packageWhat's New in v0.3.0
What's New in v0.2.0
| Backend | Type | Chains | Strength |
|---|---|---|---|
| deBridge (DLN) | Direct | EVM + Solana | Fast intent-based fills, Solana support |
| Relay | Direct | EVM + Solana | No protocol fee, gas-optimized |
| LI.FI | Aggregator | EVM | Widest coverage (30+ bridges, any-to-any swap) |
| Across | Direct | EVM | Fastest fills (~6s), same-token bridging |
| Squid (Axelar) | Aggregator | EVM + Cosmos | Only option for EVM → Cosmos routes |
| Direction | Backends | Status |
|---|---|---|
| EVM → EVM | All 5 | ✅ Production |
| EVM → Solana | deBridge, Relay | ✅ Production |
| Solana → EVM | deBridge | ✅ Production |
| EVM → Cosmos | Squid | ✅ Production |
npx @persistenceone/bridgekitty
Add to your MCP config (~/.claude/claude_code_config.json):
{
"mcpServers": { "bridgekitty": { "command": "npx", "args": ["@persistenceone/bridgekitty"] } } }
Add to Cursor's MCP settings (Settings > MCP Servers):
{
"bridgekitty": { "command": "npx", "args": ["@persistenceone/bridgekitty"] } }
Add to claude_desktop_config.json:
{
"mcpServers": { "bridgekitty": { "command": "npx", "args": ["@persistenceone/bridgekitty"] } } }
BridgeKitty can manage wallets for autonomous bridging. Run wallet_setup to create wallets for EVM, Cosmos, and Solana — or provide your own addresses in quotes.
Wallet config is stored in ~/.bridgekitty/.env (or the directory you run from). Keys never leave the local machine.
| Variable | Description |
|---|---|
PRIVATE_KEY | EVM private key (hex) |
MNEMONIC | BIP-39 mnemonic (derives EVM, Cosmos, Solana keys) |
SOLANA_PRIVATE_KEY | Solana private key (base58) |
By default, bridge_execute returns unsigned transactions for the agent or user to sign externally.
Set sign_and_send: true to enable autonomous signing — BridgeKitty will use the wallet keys stored in ~/.bridgekitty/.env to handle the full flow:
eth_estimateGas pre-flight check| Variable | Description |
|---|---|
LIFI_API_KEY | LI.FI API key (higher rate limits) |
DEBRIDGE_API_KEY | deBridge API key |
SQUID_INTEGRATOR_ID | Squid integrator ID |
| Tool | Description |
|---|---|
bridge_get_quote | Get competitive quotes from all backends. Shows fees, time estimates, balance warnings. |
bridge_execute | Build transaction(s) from a quote. Handles approvals, auto-refreshes expired quotes. Set sign_and_send: true to auto-sign and broadcast. |
bridge_status | Track bridge progress. On-chain fallback when API hasn't indexed yet. |
bridge_chains | List supported chains with provider coverage. |
bridge_tokens | Search tokens on a chain. |
| Tool | Description |
|---|---|
bridge_quote_multi | Multi-hop route resolution when no direct route exists. |
bridgekitty_help | Agent onboarding guide with examples and tool usage. |
xprt_onboard | Guided onboarding flow for first-time users. |
| Tool | Description |
|---|---|
wallet_setup | Create wallets for EVM, Cosmos, Solana from a single mnemonic. |
wallet_import | Import an existing wallet from a mnemonic or private key. |
wallet_status | Show configured wallet addresses and key source. |
wallet_balance | Check balances across all chains with USD prices (CoinGecko). |
XPRT staking & farming has moved to the standalone
xprt-farming-toolkitpackage.
Agent: "Bridge 100 USDC from Base to Arbitrum"
→ bridge_get_quote: Gets quotes from deBridge, Relay, LI.FI, Across → Shows: best rate, fees, estimated time, balance check → bridge_execute: Builds approval tx + bridge tx → Agent signs and sends both transactions → bridge_status: Tracks until destination confirmed
Agent: "Bridge 100 USDC from Base to Arbitrum"
→ bridge_get_quote: Gets quotes from all backends → bridge_execute with sign_and_send: true → Auto-signs approval tx + bridge tx using local wallet keys → Returns tx hash + explorer link → bridge_status: Tracks until destination confirmed
Agent → MCP Tools → Routing Engine → [deBridge, Relay, LI.FI, Across, Squid]
↓ Quote Cache (60s) + Circuit Breaker ↓ Best Quote → buildTransaction ↓ ┌──────────┴──────────┐ ↓ ↓ Unsigned TX Signed + Broadcast (default) (sign_and_send)
sign_and_send uses locally-stored keys only (never transmitted over the network).env file permission checks + overwrite protectionwallet_balance (only native SOL)MIT