About lp-copilot
lp-copilot is presented as an LP copilot for enumerating positions across seven chains and analyzing liquidity strategies. However, the supplied README describes a general PulseNetwork pay-per-call API wallet and does not document LP-specific capabilities.
Key features
- 01Search a catalog of about 900 APIs
- 02Call APIs with x402 USDC payments
- 03Generate or use an EVM wallet key
- 04View balance, spending reports, and caps
- 05Enforce per-call and daily limits in code
Use cases
- 01Find an intelligence API by keyword
- 02Make paid data calls from an AI agent
- 03Review wallet balance and recent spending
MCP support
The supplied README documents a local MCP server with tools for discovering and calling PulseNetwork APIs, checking wallet status, and viewing spending controls. It does not describe the LP-specific capabilities in the tagline.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
5Saved tool list · updated 3w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| chain | string | No | Chain slug, default robinhood — one of: ethereum, optimism, bsc, polygon, robinhood, base, arbitrum |
| address | string | Yes | Wallet address (0x…) whose positions to list — usually the user's own |
Details
From the project README@pulsenetwork/mcp
Give your AI agent a wallet and 900+ pay-per-call intelligence APIs.
A local MCP server that connects any MCP host (Cursor, Claude Code, Claude Desktop, …) to PulseNetwork — 74 intelligence verticals covering finance, crypto, health, law, travel, climate, safety, and more. No accounts, no API keys: every endpoint is paid per call in USDC on Base via the x402 protocol.
{ "mcpServers": { "pulsenetwork": { "command": "npx", "args": ["-y", "@pulsenetwork/mcp", "mcp"] } } }
What you get
| Tool | Cost | What it does |
|---|---|---|
pulse_discover | FREE | Search the full catalog (~900 endpoints) by keyword |
pulse_call | pays the listed price | Call an endpoint; payment settles automatically |
pulse_balance | FREE | Wallet address + USDC balance |
pulse_report | FREE | Local spend report |
pulse_guardrail | FREE | Show active spend caps |
Zero-config wallet
On first run the server generates a wallet (standard BIP-39 phrase, imports into
MetaMask/Rabby) and prints the address. Fund it with a few dollars of USDC on Base
and paid calls just work. The recovery phrase is stored at ~/.pulsepay/wallet.json
(file mode 600) — back it up. Prefer your own key? Set PULSEPAY_EVM_KEY and nothing
is written to disk.
Spend safety, enforced below the model
Guardrails run in code, before anything is signed — a confused or prompt-injected agent cannot bypass them:
- $0.50 per call / $5 per day by default (change in
~/.pulsepay/config.jsonor viaPULSEPAY_MAX_PER_CALL/PULSEPAY_MAX_PER_DAY) - The model has no tool to raise caps — only you can, by editing the file
- The wallet only pays
*.theaslangroupllc.com(the PulseNetwork fleet) — nothing else - Prices are checked against the endpoint's live 402 challenge, not a cached catalog
- Unpriceable calls are blocked, not waved through (fail-closed)
Example prompts
"Check if a 5-hour delayed flight from FRA to JFK qualifies for EU261 compensation."
"Is this token safe? 0x… on Base — run a safety scan before I ape."
"Any product recalls for 'baby teether' in the EU this year?"
"What's my agent wallet's balance and what did it spend this week?"
Most endpoints cost $0.01–$0.25. The agent discovers for free, quotes the price, and pays only when you ask it to.
License
MIT © The Aslan Group LLC. Terms: https://pulse.theaslangroupllc.com/terms.html
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.