Osmosis
Provides a bridge to the Osmosis blockchain protocol for executing decentralized finance operations ...
Choose how you’ll obtain a mnemonic (recommended: Keplr browser extension)
- Install Keplr (browser extension) and create a new wallet or open an existing mnemonic-based wallet. When you create a new wallet Keplr will show a recovery (seed) phrase — write it down exactly (12/24 words). If you already have a Keplr wallet you can view/export the mnemonic from the account menu (you’ll be asked for your Keplr password). (help.keplr.app)
(Alternative) Create or export a mnemonic with another Cosmos-compatible wallet
- You may instead use Osmosis-compatible wallets (Keplr, Leap, Cosmostation, etc.) to create or export a seed phrase. Always follow the wallet’s official export instructions and store the phrase securely. (keplr.crunch.help)
Secure the mnemonic before using it
- Store the phrase offline (paper/hardware wallet) and do NOT paste it into untrusted sites or share it. For testing, consider creating a new account with minimal funds to avoid risking mainnet assets. (Security best practice; do not share your mnemonic.)
Open the FastMCP connection interface and click “Install Now”
- In the FastMCP connection UI use the provided “Install Now” button to add the Osmosis MCP server.
Fill the ENV field named OSMOSIS_MNEMONIC in the FastMCP connection form
- In the form field labeled OSMOSIS_MNEMONIC paste your full mnemonic exactly as shown (all words in order, separated by single spaces). Do not add extra surrounding quotes unless the UI explicitly requires them.
- Example value (do NOT use this example; replace with your real phrase):
OSMOSIS_MNEMONIC: word1 word2 word3 … word12/24. - The Osmosis MCP server reads the mnemonic from this environment variable. (playbooks.com)
Save the connection and start the MCP server
- After saving the env value in FastMCP, start the server via the UI’s start/launch action (or use the equivalent npx command locally:
npx -y @osmosis-agent-toolkit/mcp --mnemonic='your mnemonic here'or export OSMOSIS_MNEMONIC and run the package). (playbooks.com)
- After saving the env value in FastMCP, start the server via the UI’s start/launch action (or use the equivalent npx command locally:
(Optional) Debug with the MCP Inspector
- If you need to debug the MCP server, run the MCP Inspector and start the server there; follow the MCP Inspector workflow to Connect and test tools. (modelcontextprotocol.io)
Verify and test
- Once running, verify the server responds in FastMCP/your MCP client (e.g., Claude Desktop) and test only safe operations first. If anything looks wrong, remove the mnemonic from the UI, rotate the account (create/import a new mnemonic), and investigate logs.
If you prefer CLI setup instead of FastMCP
- You can set the environment variable locally and run:
- Unix/macOS:
export OSMOSIS_MNEMONIC='your mnemonic here'thennpx -y @osmosis-agent-toolkit/mcp - Windows (PowerShell):
$env:OSMOSIS_MNEMONIC='your mnemonic here'; npx -y @osmosis-agent-toolkit/mcp
(This mirrors the package’s documented usage.) (playbooks.com)
- Unix/macOS:
- You can set the environment variable locally and run:
Quick Start
Choose Connection Type for
Authentication Required
Please sign in to use FastMCP hosted connections
Run MCP servers without
local setup or downtime
No local setup or infra
Run MCP servers without Docker, ports, or tunnels.
Always online
Your MCP keeps working even when your laptop is off.
One secure URL
Use the same MCP from any agent, anywhere.
Secure by default
Encrypted connections. Secrets never stored locally.
Configure Environment Variables for
Please provide values for the following environment variables:
started!
The MCP server should open in . If it doesn't open automatically, please check that you have the application installed.
Copy and run this command in your terminal:
Make sure Gemini CLI is installed:
Visit Gemini CLI documentation for installation instructions.
Make sure Claude Code is installed:
Visit Claude Code documentation for installation instructions.
Installation Steps:
Configuration
Installation Failed
More for Finance
View All →Fear & Greed Index
Provides real-time access to CNN's Fear & Greed Index for US stock market sentiment analysis, retrieving current composite scores and seven individual market indicators including S&P 500 momentum, options ratios, and volatility measures with historical comparisons.
More for Developer Tools
View All →
GitHub
Extend your developer tools with the GitHub MCP Server—a powerful Model Context Protocol server enhancing automation and AI interactions with GitHub APIs. It supports diverse functionalities like managing workflows, issues, pull requests, repositories, and security alerts. Customize available toolsets to fit your needs, enable dynamic tool discovery to streamline tool usage, and run the server locally or remotely. With read-only mode and support for GitHub Enterprise, this server integrates deeply into your GitHub ecosystem, empowering data extraction and intelligent operations for developers and AI applications. Licensed under MIT, it fosters flexible and advanced GitHub automation.
Desktop Commander
Desktop Commander MCP transforms Claude Desktop into a powerful AI assistant for managing files, running terminal commands, and editing code with precision across your entire system. It supports in-memory code execution, interactive process control, advanced search and replace, plus comprehensive filesystem operations including reading from URLs and negative offset file reads. With detailed audit and fuzzy search logging, it enables efficient automation, data analysis, and multi-project workflows—all without extra API costs. Designed for developers seeking smarter automation, it enhances productivity by integrating all essential development tools into a single, intelligent chat interface.
Chrome DevTools
Provides direct Chrome browser control through DevTools for web automation, debugging, and performance analysis using accessibility tree snapshots for reliable element targeting, automatic page event handling, and integrated performance tracing with actionable insights.
FreeCAD
Enables AI-driven CAD modeling by providing a remote procedure call (RPC) server that allows programmatic control of FreeCAD, supporting operations like creating documents, inserting parts, editing objects, and executing Python code for generative design workflows.