What does the Osmosis Agent Toolkit do?
It provides a set of tools that allow LLMs to interact with the Osmosis protocol, including querying data and executing transactions.
@jonator
Basic information
Osmosis protocol tools for LLMs
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"osmosis-agent-toolkit": {
"command": "bun",
"args": [
"run",
"dev"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
The Osmosis Agent Toolkit is a collection of packages that enables Large Language Models (LLMs) to interact with the Osmosis protocol using programmable tools. It includes a Model Context Protocol (MCP) server implementation that integrates seamlessly with AI assistants like Claude Desktop and Cursor.
Run the MCP server via npx with the command npx -y @osmosis-agent-toolkit/mcp and set the OSMOSIS_MNEMONIC environment variable to your Osmosis wallet mnemonic. Add the server configuration to your claude_desktop_config.json (for Claude Desktop) or .cursor/mcp.json (for Cursor) to enable LLMs to interact with Osmosis.
OSMOSIS_MNEMONIC)It provides a set of tools that allow LLMs to interact with the Osmosis protocol, including querying data and executing transactions.
Add the provided configuration block to your `claude_desktop_config.json`, specifying `npx -y @osmosis-agent-toolkit/mcp` as the command and your Osmosis wallet mnemonic in the `OSMOSIS_MNEMONIC` environment variable.
Only `OSMOSIS_MNEMONIC` is required, which must contain the mnemonic phrase of your Osmosis wallet.
GoBuy gives AI agents marketplace-evidence trust scores. One call returns a 0–100 Evidence Score with observed/missing signals, freshness, and product context. Tools: • check_product_trust — inspect one Amazon, Walmart,

scvd.store is an evidence observatory for agentic commerce. Independent signed observation of what other people's endpoints, artifacts and payments actually did among other things. USDC on Base, Arbitrum One, World Chain
Detect and redact PII, PHI, PCI and secrets — SSNs, credit cards, passports, API keys and cloud credentials — in text and in local files, using the Strac DLP API. Five tools: redact_text, detect_sensitive_data, detect_fi

Build and edit landing pages and websites from your AI assistant, and pull how they are performing.
MCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.
Comments