A Model Context Protocol server that enables AI agents to interact with Teller Protocol for arbitrage discovery and on-chain transaction building.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install tellermcp
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install tellermcp using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Tellermcp MCP Skill?
The Tellermcp MCP Skill is a robust technical bridge that exposes the Teller Protocol's delta-neutral and lending models to AI agents via the Model Context Protocol. It allows for seamless discovery of borrow pools, loan terms, and arbitrage opportunities directly within an agentic workflow. By utilizing Openclaw Skills, developers can deploy this server to provide agents with the necessary tools to analyze DeFi data and construct ready-to-execute on-chain transaction builders.
Tellermcp MCP Skill Use Cases
- Deploying automated agents to scan for delta-neutral arbitrage opportunities across Teller pools.
- Building custom DeFi dashboards that utilize AI to analyze loan terms and borrowing costs.
- Automating the generation of transaction payloads for borrowing and repayment processes.
- Managing on-chain lending positions and wallet loan monitoring through structured agent interactions.
How Tellermcp MCP Skill Works
- The skill sets up a dedicated MCP server using a Node.js environment within the scripts/tellermcp-server directory.
- Upon initialization, the server connects to the Teller REST API using a typed TypeScript client.
- Six specialized tools are registered, including opportunity discovery and transaction construction logic.
- When an agent requires DeFi data, it calls the MCP tool, which fetches live data from the Teller API.
- The server processes the API response and returns structured JSON content compatible with Openclaw Skills transports like mcporter.
Tellermcp MCP Skill Setup
Navigate to the server directory and install dependencies:
cd scripts/tellermcp-server
npm install
Build the TypeScript project and start the server:
npm run build
npm start
To integrate with Openclaw Skills, add the following configuration to your mcporter settings:
{
"name": "tellermcp",
"command": "npm",
"args": ["start"],
"cwd": "/absolute/path/to/scripts/tellermcp-server"
}
Tellermcp MCP Skill Data Schema & Taxonomy
The skill organizes its operations through a set of distinct tools, each returning structured data for automation:
| Tool Name | Purpose | Key Data Fields |
|---|---|---|
| get-delta-neutral-opportunities | Arbitrage discovery | ROI, strategy type, pool addresses |
| get-borrow-pools | Discovery | Available assets, liquidity, APY |
| get-borrow-terms | Analysis | Duration, interest rates, collateral ratios |
| build-borrow-transactions | Execution | Transaction hex, gas estimates, target addresses |
Tellermcp MCP Skill Advanced Features
- Direct integration with on-chain transaction builders for borrow and repayment cycles.
- Environment-variable-driven configuration for API base URLs and request timeouts.
- Support for structuredContent payloads, ensuring AI agents receive clean JSON for logic processing.
- Compatibility with the Openclaw Skills packager for creating redistributable .skill bundles.
SKILL.md
Loading
Related Openclaw Skills
Tellermcp MCP Skill
An MCP server that enables AI agents to discover arbitrage opportunities, fetch borrow terms, and build on-chain transactions for the Teller protocol.
Tellermcp MCP Skill
A Model Context Protocol server that empowers AI agents to manage Teller protocol lending, borrowing, and delta-neutral arbitrage opportunities.
AgentComm
AgentComm provides a decentralized communication layer for AI agents to exchange messages and files over the internet or local networks.
AgentComm
AgentComm is a decentralized communication layer that allows AI agents to exchange encrypted messages and files without central servers.
Predicate Snapshot Engine
An ML-powered DOM pruning engine that reduces browser prompt tokens by 95% for more efficient AI agents.
Gemini Image Remix
A sophisticated AI tool for text-to-image generation and complex multi-image remixing powered by Google Gemini models.
METADATA
Featured*
