Osmosis Agent Toolkit

Created By
jonatora year ago
Osmosis protocol tools for LLMs
Overview

What is Osmosis Agent Toolkit?

The Osmosis Agent Toolkit is a collection of packages designed to enable Large Language Models (LLMs) to interact with the Osmosis protocol effectively.

How to use Osmosis Agent Toolkit?

To use the toolkit, integrate the core package and configure it with your desired settings in your application. For example, you can add the MCP server configuration to your claude_desktop_config.json or .cursor/mcp.json file.

Key features of Osmosis Agent Toolkit?

  • Core functionality for registry data, query clients, and transaction logic.
  • Integration with Vercel's AI SDK for enhanced capabilities.
  • Model Context Protocol (MCP) server implementation for seamless communication.

Use cases of Osmosis Agent Toolkit?

  1. Building applications that require interaction with the Osmosis protocol.
  2. Enhancing LLM capabilities with protocol-specific tools.
  3. Developing AI-driven applications that utilize the Model Context Protocol.

FAQ from Osmosis Agent Toolkit?

  • What programming language is used in the toolkit?

The toolkit is primarily developed in TypeScript.

  • Is there a license for using the Osmosis Agent Toolkit?

Yes, it is available under the MIT license.

  • How can I contribute to the project?

Contributions are welcome! You can fork the repository and submit a pull request.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
jonator
Star
9
Language
TypeScript
License
MIT license

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

an hour ago
Gpt Scrambler

2 days ago