Gmail
Integrates with Gmail to enable natural language-based email management, including searching, readin...
Get the Systemprompt API key
- Open the Systemprompt console at systemprompt.io/console and sign in (or create an account). (systemprompt.io)
- In the console look for an "API Keys" or "Create API Key" area, create a new key, and copy the key to your clipboard. (Save it somewhere safe; you will paste it into FastMCP in a later step.) (systemprompt.io)
Create Google Cloud credentials (GOOGLE_CREDENTIALS) for Gmail access
- Open the Google Cloud Console and either select an existing project or create a new one. (cloud.google.com)
- Enable the Gmail API for that project (APIs & Services → Library → search “Gmail API” → Enable). (developers.google.com)
- Configure the OAuth consent screen (Google Auth / OAuth consent) — set app name, user support email, user type (External for personal/testing use), and add any test users if required. (ai.google.dev)
- Create OAuth 2.0 credentials: go to OAuth Clients (Credentials → Create Client → choose “Desktop app”), create the client, then download the JSON credentials file (rename to something like client_secret.json). This file is your Google credentials JSON. (ai.google.dev)
Generate the Google OAuth token file (GOOGLE_TOKEN)
- Use the google-auth helper included in the multimodal-mcp-client repository to run the OAuth flow and produce a token JSON (the repository includes a scripts/google-auth README with the exact commands). Clone or download the repo and follow the instructions in scripts/google-auth to run the authorization script and obtain the token JSON. (github.com)
- (If you prefer) you can follow Google’s Gmail quickstart / OAuth examples to perform the installed-app OAuth flow and save the resulting token JSON (token.json). (developers.google.com)
Base64-encode the two JSON files
- On macOS / Linux:
- Credentials: base64 client_secret.json > client_secret.json.b64
- Token: base64 token.json > token.json.b64
- On PowerShell (Windows):
- Credentials: [Convert]::ToBase64String([IO.File]::ReadAllBytes("client_secret.json")) > client_secret.json.b64
- Token: [Convert]::ToBase64String([IO.File]::ReadAllBytes("token.json")) > token.json.b64
- Open each .b64 file and copy the full base64 string (no newlines ideally; if your tooling adds newlines it still usually works but a single-line base64 string is safest).
- On macOS / Linux:
Fill the FastMCP connection interface (use the “Install Now” button you already have)
- Open the FastMCP connection interface and click the "Install Now" / add ENVs action.
- Add an environment variable for the Systemprompt API key:
- Key name: (as required by the server; if the server README only says “API KEY”, use the FastMCP field for API Key or a variable named e.g.
SYSTEMPROMPT_API_KEY) — paste the API key you copied in step 1. (systemprompt.io)
- Key name: (as required by the server; if the server README only says “API KEY”, use the FastMCP field for API Key or a variable named e.g.
- Add an environment variable named
GOOGLE_CREDENTIALSand paste the base64 string produced from your credentials JSON (from step 4). (ai.google.dev) - Add an environment variable named
GOOGLE_TOKENand paste the base64 string produced from your token JSON (from step 4). (developers.google.com) - Save/confirm the connection settings in FastMCP. The MCP server should now have the encoded credentials/token and the Systemprompt API key available.
Post-setup notes & security
- Keep your API key, credentials JSON, and token JSON private — treat them like passwords. Do not commit them to source control. (systemprompt.io)
- The token JSON often contains a refresh token; if you re-run the auth script it may overwrite the token — keep backups if you need to preserve access for multiple environments. (developers.google.com)
- If you have trouble with the multimodal-mcp-client helper, open the repo’s scripts/google-auth README for exact commands and troubleshooting. (github.com)
If you want, tell me the exact field names shown in your FastMCP interface (or paste a screenshot of that form) and I’ll produce the exact text you should paste into each field (including a copy-paste–safe single-line base64 example).
Quick Start
Choose Connection Type for
Authentication Required
Please sign in to use FastMCP hosted connections
Run MCP servers without
local setup or downtime
Access to 1,000+ ready-to-use MCP servers
Skip installation, maintenance, and trial-and-error.
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.
Configuration for
Environment Variables
Please provide values for the following environment variables:
HTTP Headers
Please provide values for the following HTTP headers:
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 Productivity
View All →Task Master
Task Master is an AI-powered task management system designed for development projects using Claude and Cursor AI. It helps break down product requirements into clear, manageable tasks, supports multiple AI models for main, research, and fallback roles, and enables seamless task planning, implementation, and research within your editor environment. With support for Claude Code CLI and integration across popular editors, Task Master streamlines project workflows by guiding you through parsing PRDs, generating tasks, and staying updated with best practices - all while enhancing productivity in AI-driven software development.
Notion
Unlock powerful AI-driven interactions with Notion data using our MCP server tailored for the Notion API. This project enables advanced AI agents to efficiently read, comment, and organize Notion content while optimizing token use. It supports key operations like searching, page creation, and content retrieval, allowing seamless natural language commands to manage your workspace. Designed with security in mind, it provides scoped access options to protect your data. Ideal for developers building intelligent applications that integrate deeply with Notion, it simplifies complex tasks and enhances productivity through AI automation.
Excel
Unlock powerful Excel automation with this MCP server that reads and writes Excel files effortlessly. It supports text, formulas, sheet creation, and works with XLSX, XLSM, XLTX, and XLTM formats. Windows users benefit from live editing and screen capture features. The server offers tools to describe sheets, read cell ranges with pagination, write values or formulas, create tables, and copy sheets. Configurable paging limits help manage large data efficiently. Designed for seamless Excel data manipulation, it enhances workflow automation and integration with other systems through the Model Context Protocol.
TaskManager
Manage and execute tasks efficiently with MCP TaskManager in a queue-based system. This server supports planning by accepting and organizing task lists, and execution by delivering tasks one at a time with feedback on completion. It tracks tasks via unique IDs, ensuring smooth workflow coordination through clear stages: planning, executing, and completing. Designed for integration with MCP clients like Claude Desktop, TaskManager simplifies complex task handling and improves automation by providing structured task queues and real-time updates. Its straightforward action parameters allow easy control over task flow, making it a powerful tool for effective task management.
More for Communication
View All →
Slack
Experience the most powerful MCP server for Slack workspaces with advanced message and channel support. This feature-rich server allows fetching messages from channels, threads, DMs, and group DMs with embedded user info and smart history pagination by date or count. It supports enterprise workspaces, caching for faster access, and flexible transports like Stdio and SSE with proxy settings. Designed for stealth operation or secure access via OAuth, it integrates channel and thread lookups by name or ID to give rich, contextual Slack workspace data efficiently and reliably. Perfect for developers needing robust Slack data handling.