mcp-everything
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": {}
}
}
} |
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": true,
"listChanged": true
} |
| completions | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| echoA | Echoes back the input string |
| get-annotated-messageC | Demonstrates how annotations can be used to provide metadata about content. |
| get-envA | Returns all environment variables, helpful for debugging MCP server configuration |
| get-resource-linksA | Returns up to ten resource links that reference different types of resources |
| get-resource-referenceC | Returns a resource reference that can be used by MCP clients |
| get-structured-contentB | Returns structured content along with an output schema for client data validation |
| get-sumA | Returns the sum of two numbers |
| get-tiny-imageA | Returns a tiny MCP logo image. |
| gzip-file-as-resourceA | Compresses a single file using gzip compression. Depending upon the selected output type, returns either the compressed data as a gzipped resource or a resource link, allowing it to be downloaded in a subsequent request during the current session. |
| toggle-simulated-loggingA | Toggles simulated, random-leveled logging on or off. |
| toggle-subscriber-updatesA | Toggles simulated resource subscription updates on or off. |
| trigger-long-running-operationB | Demonstrates a long running operation with progress updates. |
| simulate-research-queryA | Simulates a deep research operation that gathers, analyzes, and synthesizes information. Demonstrates MCP task-based operations with progress through multiple stages. If 'ambiguous' is true and client supports elicitation, sends an elicitation request for clarification. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| simple-prompt | A prompt with no arguments |
| args-prompt | A prompt with two arguments, one required and one optional |
| completable-prompt | First argument choice narrows values for second argument. |
| resource-prompt | A prompt that includes an embedded resource reference |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| architecture.md | Static document file exposed from /docs: architecture.md |
| extension.md | Static document file exposed from /docs: extension.md |
| features.md | Static document file exposed from /docs: features.md |
| how-it-works.md | Static document file exposed from /docs: how-it-works.md |
| instructions.md | Static document file exposed from /docs: instructions.md |
| prompts-guide.md | Static document file exposed from /docs: prompts-guide.md |
| resources-guide.md | Static document file exposed from /docs: resources-guide.md |
| startup.md | Static document file exposed from /docs: startup.md |
| structure.md | Static document file exposed from /docs: structure.md |
TDQS
Scored across 13 tools
Most tools target distinct MCP demos, but several overlap: get-resource-links and get-resource-reference both concern resources, get-annotated-message and get-structured-content both return content metadata, and trigger-long-running-operation and simulate-research-query both demonstrate long-running progress. Descriptions help, but boundaries are not always crisp.
All tool names use kebab-case and are almost entirely verb-first or get_-prefixed. Minor variations like echo and gzip-file-as-resource still fit the overall verb-led convention.
At 13 tools, the set is well-scoped for a feature-demonstration server. Each tool appears to demonstrate a specific MCP capability, so the count does not feel bloated or thin.
The implied domain is demonstrating MCP features, but the surface leaves notable gaps such as prompts, sampling, and full resource lifecycle operations. It covers many individual demos without providing complete coverage of the protocol area it claims to represent.