@arcis/mcp
OfficialClick on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@@arcis/mcpWhat's the TVL on Arcis?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@arcisprotocol/mcp
Arcis Protocol MCP Server — connect any AI agent to DeFi vaults in one tool call.
Three deployment modes. 9 tools. Rate-limited writes.
Mode 1: Local (Claude Desktop / Claude Code)
{
"mcpServers": {
"arcis": { "command": "npx", "args": ["@arcisprotocol/mcp"] }
}
}Related MCP server: Universal Crypto MCP
Mode 2: Self-Hosted HTTP
PORT=3001 npx @arcisprotocol/mcp start:remoteDeploy to Railway, Render, or any VPS.
Mode 3: Vercel Serverless (Claude.ai Custom Connector)
Import this repo at vercel.com/new
Deploy — zero config
Your MCP endpoint:
https://your-project.vercel.app/api/mcp
Then in Claude.ai: Settings → Connectors → Add → paste the URL.
Tools
Read (7 tools)
Tool | Description |
| TVL, exchange rate, supply, capacity, reserve/deployed |
| Agent position: shares, value, USDC wallet |
| Preview shares for a deposit amount |
| Lending pool, total borrowed, utilization |
| ERC-8004 reputation tier table |
| Loan health + total owed |
| All deployed contract addresses |
Write (2 tools, 60s rate limit)
Tool | Description |
| Deposit USDC → raUSDC (auto-approval) |
| Redeem raUSDC → USDC (supports withdraw_all) |
How It Connects
AI Agent ←→ MCP Server ←→ Base Mainnet ←→ Arcis ContractsCUSTOS (the Arcis keeper agent) uses the same contract interfaces. If CUSTOS can operate the protocol autonomously, any agent can.
Related Repos
Repo | Description |
Smart contracts — 17 contracts, 116 tests | |
| |
Framework & runtime integrations (npm + PyPI) | |
CUSTOS — autonomous keeper agent | |
ATI v1.1, integration guide, demo scripts |
Any of the framework packages in integrations can talk to this server, and any MCP client can connect directly at https://mcp.arcis.money/mcp.
ARCIS · @arcisprotocol/mcp · MMXXVI
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseCqualityDmaintenanceEnables AI agents to interact with cryptocurrency ecosystems through wallet management, trading operations (swaps, DCA, limit orders), staking, and multi-chain support starting with Solana.Last updated37GPL 3.0
- Alicense-qualityDmaintenanceEnables AI agents to interact with any EVM-compatible blockchain through natural language, supporting token swaps, cross-chain bridges, staking, lending, governance, gas optimization, and portfolio tracking across networks like Ethereum, BSC, Polygon, Arbitrum, and more.Last updated1239Inno Setup
- AlicenseCqualityDmaintenanceA single source for integrating AI Agents with the Crypto ecosystem, including wallet creation, swaps, transfers, and event-based trades like DCA and stop loss.Last updated37GPL 3.0
- FlicenseBqualityDmaintenanceEnables AI assistants to discover, evaluate, and execute DeFi yield strategies across EVM and Solana chains through natural conversation, with transactions signed locally.Last updated15241
Related MCP Connectors
USDC treasury vaults, streaming payments, and DeFi yield for AI agents
DeFi interface for AI agents: swap, bridge, yield, lending. Live at syenite.ai.
Non-custodial DeFi for AI agents: swaps, concentrated liquidity (V3/V4) zaps + ranges, 5 EVM chains
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Arcis-Protocol/mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server