Tellermcp MCP Skill for Openclaw

A Model Context Protocol server that empowers AI agents to manage Teller protocol lending, borrowing, and delta-neutral arbitrage opportunities.

rbcp18
v0.2.3
Feb 16, 2026
0
1.4k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install teller-borrow-agents

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install teller-borrow-agents 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 comprehensive integration for the Model Context Protocol, designed to bridge the gap between AI agents and the Teller lending protocol. It provides a ready-to-deploy server that surfaces essential DeFi data, including borrow pool discovery, loan terms, and transaction builders. By leveraging this skill within the ecosystem of Openclaw Skills, developers can build autonomous agents capable of analyzing on-chain lending markets and executing complex financial strategies.

The skill handles the heavy lifting of interacting with Teller's REST APIs, offering typed responses and structured content payloads. This allows agents to not only read data but also prepare the necessary transaction hex for borrowing and repayment operations, making it a critical component for any automated DeFi workflow.

Tellermcp MCP Skill Use Cases

  • Discovering and analyzing delta-neutral arbitrage opportunities in real-time.
  • Automating the search for specific borrow pools and loan terms based on collateral types.
  • Building and preparing on-chain transactions for borrowing and repaying loans.
  • Tracking active loans within a specific wallet to manage liquidation risks or repayment schedules.
  • Integrating DeFi market intelligence into custom agentic workflows using Openclaw Skills.

How Tellermcp MCP Skill Works

  1. The skill initializes a Node.js-based MCP server located in the scripts directory.
  2. It establishes a connection to the Teller API using a typed REST client to ensure data accuracy.
  3. Six core tools are registered with the server: get-delta-neutral-opportunities, get-borrow-pools, get-borrow-terms, build-borrow-transactions, get-wallet-loans, and build-repay-transactions.
  4. When an agent requests data, the server fetches the information from Teller and returns a structured JSON payload.
  5. The agent uses the generated transaction data to facilitate on-chain interactions, all managed through the Openclaw Skills framework.

Tellermcp MCP Skill Setup

To get started with the Tellermcp server, navigate to the server directory and install the necessary dependencies:

cd scripts/tellermcp-server
npm install

Build the TypeScript project to generate the executable files:

npm run build

Launch the server using the start command to begin using it with your Openclaw Skills agents:

npm start

Tellermcp MCP Skill Data Schema & Taxonomy

The skill organizes its data and interactions through a well-defined TypeScript structure to ensure reliability.

Component Description
src/types.ts Contains the TypeScript interfaces for Teller API responses, ensuring data consistency.
src/client.ts A wrapper for the Teller REST API, handling timeouts and base URL configurations.
Tool Payloads Every tool returns a structuredContent.payload containing raw JSON for agent automation.
Configuration Supports environment variables like TELLER_API_BASE_URL for flexible deployment.

Tellermcp MCP Skill Advanced Features

  • Transaction Hex Generation: Directly creates the necessary hex data for on-chain borrow and repay actions.
  • Deep Filtering: Support for advanced parameters when fetching opportunities and borrow pools.
  • Standardized Integration: Fully compatible with mcporter and OpenClaw for seamless agent transport.
  • Multi-Agent Support: Designed to be used by multiple agents simultaneously as part of a broader set of Openclaw Skills.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*