Tools
Everything
Get started instantly by running the Everything MCP toolkit as a service agent and connecting an LLM chatbot that can use all its tools.
1. Install Meshagent
2. Set Up and Authenticate Your Meshagent Account
- Sign up and authenticate with Meshagent
(Follow instructions for creating an account and authenticating your CLI.)
3. Start the MCP Everything Service in a Room
- This launches the MCP Everything server as a callable service agent in the “test” room.
- Note: Rooms will close if left inactive.
4. Start a Chatbot Agent with the MCP Everything Toolkit
- This launches a chatbot agent in the same room, with access to the MCP Everything toolkit.
- Tip: Multiple toolkits can be loaded in the same room with the same agent, enabling rich workflows.
- The output of this command includes a link to the Meshagent Room UI, where you can interact live with the agent and tools.
Tools Available
The Meshagent MCP Everything service exposes the following tools from the reference server:
| Tool | Short Description |
|---|---|
add | Adds two numbers |
annotatedMessage | Demonstrates how annotations can be used to provide metadata |
echo | Echoes back the input |
getResourceReference | Returns a resource reference usable by MCP clients |
getTinyImage | Returns the MCP_TINY_IMAGE |
longRunningOperation | Demonstrates a long running operation with progress updates |
printEnv | Prints all environment variables, for debugging configuration |
sampleLLM | Samples from an LLM using MCP’s sampling feature |
Tools Details
add
Adds two numbers
| Parameter | Type | Description |
|---|---|---|
| a | number | First number |
| b | number | Second number |
annotatedMessage
Demonstrates how annotations can be used to provide metadata about content
| Parameter | Type | Description |
|---|---|---|
| messageType | string | Type of message to demonstrate different patterns |
| includeImage | boolean | optional Whether to include an example image |
echo
Echoes back the input
| Parameter | Type | Description |
|---|---|---|
| message | string | Message to echo |
getResourceReference
Returns a resource reference that can be used by MCP clients
| Parameter | Type | Description |
|---|---|---|
| resourceId | number | ID of the resource to reference (1-100) |
getTinyImage
Returns the MCP_TINY_IMAGE
longRunningOperation
Demonstrates a long running operation with progress updates
| Parameter | Type | Description |
|---|---|---|
| duration | number | optional Duration (seconds) |
| steps | number | optional Number of steps |
printEnv
Prints all environment variables, helpful for debugging MCP server configuration
sampleLLM
Samples from an LLM using MCP’s sampling feature
| Parameter | Type | Description |
|---|---|---|
| prompt | string | The prompt to send to the LLM |
| maxTokens | number | optional Max tokens to generate |
References & Further Reading
- Meshagent Website: https://www.meshagent.com/
- Room API Getting Started: https://docs.meshagent.com/room_api/get_started
- Room API Overview: https://docs.meshagent.com/room_api/overview
- Meshagent MCP Everything Tool Image: https://hub.docker.com/r/meshagent/mcp-everything
- What is an MCP Server? Anthropic: The Model Context Protocol
- MCP Everything Reference Server Repo: https://github.com/modelcontextprotocol/servers