# Osmosis Agent Toolkit

> Osmosis protocol tools for LLMs

- **Type:** MCP server
- **Install:** `agentstack add mcp-jonator-osmosis-agent-toolkit`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [jonator](https://agentstack.voostack.com/s/jonator)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [jonator](https://github.com/jonator)
- **Source:** https://github.com/jonator/osmosis-agent-toolkit
- **Website:** https://deepwiki.com/jonator/osmosis-agent-toolkit

## Install

```sh
agentstack add mcp-jonator-osmosis-agent-toolkit
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Osmosis Agent Toolkit

## Overview

This repository contains a collection of packages that are used to build the Osmosis Agent Toolkit.
Large Language Models (LLMs) can use these tools to interact with the Osmosis protocol.

## Packages

### `@osmosis-agent-toolkit/core`

The core package contains the core functionality that is used by the other packages.
This is where registry data, query clients, and sign and broadcast logic is defined.

### `@osmosis-agent-toolkit/ai-sdk`

An implementation of Vercel's [AI SDK](https://sdk.vercel.ai/) for the Osmosis Agent Toolkit.

### `@osmosis-agent-toolkit/mcp`

Model Context Protocol (MCP) server implementation of the Osmosis Agent Toolkit.

#### Usage with Claude Desktop or Cursor

Add the following to your `claude_desktop_config.json` or `.cursor/mcp.json`. See [here](https://modelcontextprotocol.io/quickstart/user) for more details.

```json
{
    "mcpServers": {
        "Osmosis": {
            "command": "npx",
            "args": [
                "-y",
                "@osmosis-agent-toolkit/mcp"
            ],
            "env": {
                "OSMOSIS_MNEMONIC": ""
            }
        }
    }
}
```

## Development

Install dependencies using yarn or bun:
```bash
bun i
```

Start watch mode for local development:
```bash
bun run dev
```

To build:
```bash
bun run build
```

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [jonator](https://github.com/jonator)
- **Source:** [jonator/osmosis-agent-toolkit](https://github.com/jonator/osmosis-agent-toolkit)
- **License:** MIT
- **Homepage:** https://deepwiki.com/jonator/osmosis-agent-toolkit

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-jonator-osmosis-agent-toolkit
- Seller: https://agentstack.voostack.com/s/jonator
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.