About sudobase-ai MCP Servers
sudobase-ai MCP Servers is a catalog of MCP server definitions and installable bundles. It is intended for people adding or selecting servers, with YAML files describing launch settings, configuration and grouped functionality.
Key features
- 01YAML server definitions
- 02Local or hosted launch settings
- 03Configuration schema fields
- 04Bundles of related servers
Use cases
- 01Adding a server definition to the repository
- 02Grouping servers for a shared purpose
MCP support
It catalogs MCP servers rather than implementing server tools itself. Each server definition describes its functionality and launch parameters; bundles list servers that can be installed together.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEsudobase-ai MCP Servers
Adding servers
Open a PR to this repo, adding the appropriate yaml file. See below for file details. The file must be placed in a new directory of this repo with an appropriate name.
MCP Servers
An MCP server is defined by a directory with a sudomcp.yml file, describing the MCP server and how to launch it.
In some cases, the directory may also contain code, but in general commands such as npx and uvx are used to launch servers without needing to download code.
Available attributes include:
| attribute | description |
|---|---|
name | The unique short name for the server (no spaces). |
title | The full name of the server. |
description | Description of the MCP server's functionality. |
local | (Optional) boolean determining whether the server should launch on the client machine, or be hosted. Defaults to false (hosted) |
logo_url | Url of an image for the server. Can refer to this repository. |
config_schema | If configuration options are required for the server (such as API keys), these options are described here. See below for examples. |
stdio_server_parameters | The command, args (command line arguments) and env (environment variables) required to launch the server. |
For examples, see:
- Dune for a hosted server with a single API key.
- Slack for a hosted server with multiple config options.
- Google drive for a local server with configuration options.
Name Collisions
Server names must be unique across all servers. Names may contain slashes, as in my_github_handle/my_server. Server titles do not need to be unique.
Bundles
Bundles are a set of MCP servers that can be installed together to provide a logical unit of functionality. For example, the blockchain bundle provides a suite of servers exposing functionality related to querying blockchains.
A bundle is defined by a single yaml file in the bundles directory. Bundle attributes include:
| attribute | description |
|---|---|
name | The unique short name for the bundle (no spaces). |
title | The full name of the bundle |
description | Description of the bundle |
logo_url | Url of an image for the bundle |
servers | A list of server names that make up the bundle |
For examples, see:
- Blockchain for a bundle of blockchain-related servers
- Travel for travel related servers
- Research for assisting with research queries
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.