Collection of example MCP servers demonstrating various protocol features including tools, resources, prompts, tasks, authentication, pagination, and transport mechanisms
This is a collection of 19 example servers demonstrating MCP patterns. Tool definitions are present with basic schemas and descriptions, but quality is inconsistent. Most tools have 1-2 parameter descriptions and minimal context. No tool annotations (readOnlyHint, destructiveHint, idempotentHint) are visible. Error handling guidance is absent. Output schemas are not documented. Many descriptions are generic (e.g., 'Fetch the content of a website') without actionable context for LLM selection. Parameter descriptions exist but lack constraints (enums, ranges, formats). Tools like 'long_running_operation' and 'process_streamable_http' lack clarity on expected behavior and return structure.
Add two numbers together
Close a server-sent event stream
Create a task that requires user interaction
Create a new task
Echo back the input text
Fetch the content of a website
Get an interactive task by ID
Get a customizable prompt template
Get a sample text resource
No tool annotations (readOnlyHint, destructiveHint, idempotentHint) present. LLMs cannot distinguish safe read-only tools from destructive operations without explicit hints.
Output schemas not documented. Tools like 'list_tools', 'list_resources', 'long_running_operation' lack clarity on return structure, pagination format, and field types.
Generic descriptions lack actionable context. 'Fetch the content of a website', 'Echo back the input text', 'Simulate a long-running operation' do not explain WHEN to use the tool or what makes it distinct from similar tools.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 53 | 2026-07-28+ | v2 |
Get a server-sent event stream for long-running tasks
Get a task by ID
List all available prompts with pagination support
List all available resources with pagination support
List all available tools with pagination support
Simulate a long-running operation with progress updates
Process a request via stateless StreamableHttp transport
Process a request via StreamableHttp transport
Submit a response to an interactive task
Update a task
No error handling guidance. Tools do not document what errors can occur, whether they are retryable, or what the LLM should do next (e.g., 'URL not reachable, try a different URL or check network connectivity').
Parameter constraints missing. 'duration_seconds' in 'long_running_operation' lacks min/max bounds; 'cursor' in pagination tools lacks format guidance; 'status' in 'update_task' lacks enum values.