my-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATABASE_URL | No | Connection string for the database tool, typically configured in mcp.yaml and accessed via the environment. | |
| WEATHER_API_KEY | No | API key for the weather tool, typically configured in mcp.yaml and accessed via the environment. | |
| MCP_TRANSPORT_MODE | No | The transport mode for the MCP server (e.g., 'http' or 'stdio'). Defaults to 'stdio'. | stdio |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
},
"prompts": {
"get": {}
},
"resources": {
"read": {}
}
}
} |
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| getTinyImageA | Returns a small test image to demonstrate image content in MCP tool responses. Returns: A base64-encoded 1x1 PNG image as image content |
| sampleLLMC | Demonstrates LLM sampling capability using the MCP sampling feature. Requests the MCP client to sample from an LLM on behalf of this tool. Args: prompt: The prompt to send to the LLM maxTokens: Maximum number of tokens to generate (default: 100) Returns: The generated LLM response text |
| getResourceReferenceA | Returns a resource reference that can be used by MCP clients to fetch a resource. The resource ID must be between 1 and 100. Args: resourceId: ID of the resource to reference (1-100) Returns: A list containing a text introduction, an embedded resource reference, and instructions for using the resource URI |
| startElicitationB | Demonstrates MCP elicitation by requesting structured input from the user via the MCP client. Elicitation allows servers to interactively ask users for information during a tool call. Args: message: The prompt message to display to the user (default: "Please provide your name:") Returns: The user's response from the elicitation, or an error if not supported |
| listRootsA | Lists the current MCP roots as reported by the connected MCP client. Roots define the filesystem or URI boundaries the client exposes to the server. Returns: A formatted list of roots provided by the client, or an indication that the client does not support roots |
| echoB | Echo a message back to the client. Args: message: The message to echo Returns: The echoed message with any configured prefix |
| sumA | Add two numbers together. Use this tool when you need to sum or add two numbers. Args: a: The first number to add b: The second number to add Returns: The sum of the two numbers |
| structuredContentA | Returns structured content that conforms to a well-defined JSON schema. Demonstrates MCP's structured output / schema-validated tool responses. Args: includeOptionalFields: Whether to include optional fields in the response (default: False) Returns: A structured dict with schema-validated fields |
| longRunningOperationB | Demonstrates a long-running operation with progress notifications. Args: duration: Total duration of the operation in seconds (default: 10) steps: Number of progress steps to report (default: 5) Returns: Completion message with duration and steps info |
| annotatedMessageA | Demonstrates different annotation patterns for MCP tool responses. Returns content with metadata annotations based on the message type. Args: messageType: Type of message to demonstrate - "error", "success", or "debug" includeImage: Whether to include an example image in the response (default: False) Returns: Annotated content demonstrating MCP annotation capabilities |
| printEnvA | Prints all current environment variables. Useful for debugging server configuration and available environment context. Returns: A formatted list of all environment variables |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 11 tools
Most tools have distinct purposes focused on demonstrating different MCP capabilities, with clear boundaries between them. However, 'annotatedMessage' and 'structuredContent' both demonstrate response formatting, which could cause some confusion about which to use for structured output scenarios.
The naming is inconsistent with mixed conventions: 'annotatedMessage' uses camelCase while most others use snake_case. There's also inconsistency in verb usage - some start with verbs (get, list, print, start), others are nouns (echo, sum), and some are descriptive phrases (longRunningOperation).
With 11 tools, this is well-scoped for a demonstration server covering various MCP features. Each tool serves a distinct demonstration purpose, and the count feels appropriate for showing the breadth of MCP capabilities without being overwhelming.
For a demonstration server, it covers most key MCP features well: annotations, resources, images, roots, operations, environment, LLM sampling, elicitation, structured content, and basic operations. The main gap is the lack of a tool demonstrating MCP prompts, but otherwise it's quite comprehensive for its purpose.