Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcpdemos run the polite CLI demo"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
8 runnable demos showcasing Model Context Protocol capabilities - from text-only tools to interactive MCP Apps with bidirectional communication.
node --version # Requires Node 20+
npm install
npm run dev # Start MCP server (stdio transport)For production:
npm run build
npm startRelated MCP server: UI5con 2026 MCP Apps
Add to .vscode/settings.json to auto-discover the server:
{
"mcp": {
"servers": {
"mcpdemos": {
"command": "node",
"args": ["dist/index.js"],
"cwd": "${workspaceFolder}"
}
}
}
}For development with tsx:
{
"mcp": {
"servers": {
"mcpdemos": {
"command": "npx",
"args": ["tsx", "src/index.ts"],
"cwd": "${workspaceFolder}"
}
}
}
}# | Demo | Category | Tools | Resources |
1 | Hook |
| - | |
2 | Negotiation |
| - | |
3 | Security |
| - | |
4 | Coordination |
| - | |
5 | Coordination |
| - | |
6 | Shared Artifacts |
|
| |
7 | Shared Artifacts |
|
| |
8 | Platform |
| - |
ShowRun All Demos - All Demos Walkthrough Script
5-Minute Runbook - Quick highlights (Demos 1, 2, 3, 4, 6, 8)
15-Minute Runbook - Full walkthrough with stage timing for all 8 demos
src/
index.ts ← Server entry point (stdio transport)
demos/
demo1-polite-cli.ts ← Tool: verbose CLI responses
demo2-elicitation.ts ← Tools: scaffold start + confirm
demo3-oauth.ts ← Tools: consent → approve → action
demo4-async-progress.ts ← Tools: pipeline + progress polling
demo5-cancel-retry.ts ← Tools: cancel, retry, list tasks
demo6-color-picker.ts ← Tool + Resource: colour picker UI
demo7-component-gallery.ts ← Tool + Resource: gallery UI
demo8-export-artifacts.ts ← Tool: report generation
examples/
demo{1-8}/README.md ← Per-demo docs with stage scripts
docs/
5-minute-runbook.md
15-minute-runbook.md
outputs/ ← Generated reports (Demo 8)If a host doesn't support MCP Apps (ui:// resources), all demos fall back to text-only tool interactions. The UI resources are optional enhancements.
@modelcontextprotocol/sdk - MCP server framework
zod - Schema validation
tsx (dev) - TypeScript execution
No external APIs, databases, or cloud services required
MIT
Verbose CLI-style helper – returns long text/JSON requiring multiple round-trips. Demonstrates the 'before' experience of chatting with a polite but wordy tool.
| Name | Required | Description | Default |
|---|---|---|---|
| command | Yes | The CLI command to run | |
| verbose | No | Enable verbose output (default: true for demo) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses key behavioral traits: verbosity, long output, and requirement for multiple round-trips. However, with no annotations, it does not cover side effects, safety, or permissions. The disclosure is adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, but the second sentence adds meta-demo context that is not useful for an agent. It could be more tightly focused on the tool's function without the demo commentary.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple 2-parameter tool, the description lacks details about what each command returns or its behavior. The enum values (status, list-files, deploy-check) are not explained, leaving the agent to guess outputs and effects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% coverage with descriptions for both parameters (command enum, verbose boolean). The description adds no additional parameter semantics beyond the schema, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'Verbose CLI-style helper' but does not clearly state the action performed (e.g., 'runs CLI commands'). It focuses on output characteristics (long text/JSON) and a meta-demo context, making the purpose vague for an AI agent.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs siblings or alternatives. The description does not mention use cases, prerequisites, or exclusions. The meta-demo language ('before experience') is unhelpful for operational use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Complete project scaffolding after user has made their choices. Resumes the flow started by demo2_scaffold_start.
| Name | Required | Description | Default |
|---|---|---|---|
| projectName | Yes | ||
| template | Yes | ||
| includeDocker | No | ||
| includeCI | No | ||
| license | No | MIT |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden but fails to disclose any behavioral traits such as side effects, permissions required, or state changes beyond 'complete scaffolding'. This is insufficient for safe invocation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is short (two sentences) and front-loaded with the core purpose. However, it sacrifices necessary detail for brevity, lacking any parameter or behavioral context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 5 parameters (2 required) and no output schema, the description omits return value info, error conditions, and behavioral details, making it incomplete for reliable agent use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% and the description does not mention any parameters, leaving all five properties (including required ones) unexplained beyond their names and enums. The agent gains no additional meaning from the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool completes project scaffolding and resumes a flow started by a specific sibling tool, demo2_scaffold_start, distinguishing its role as a follow-up step.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly says 'after user has made their choices' and 'resumes the flow started by demo2_scaffold_start', providing clear context for when to invoke. No explicit exclusions are given, but the sequential relationship is well-defined.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Begin project scaffolding – presents configuration choices via structured elicitation. Returns a structured prompt for the user to choose template, name, and options.
| Name | Required | Description | Default |
|---|---|---|---|
| projectName | Yes | Name for the new project |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should fully disclose behavior. It mentions returning a structured prompt but does not describe if the tool has side effects, whether it modifies state, or what the prompt format is. The behavioral disclosure is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two sentences. It front-loads the key action and adds detail in the second sentence. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity (one param, no output schema), the description is incomplete. It lacks details about return value format, how the tool fits in the scaffolding workflow, and whether it is safe to call repeatedly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema provides 100% coverage for the single parameter, so the description adds minimal value beyond restating 'name'. It mentions 'name' in the context of the prompt but does not elaborate on the parameter's meaning or constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states it begins project scaffolding and returns a structured prompt, which is somewhat clear. However, the description mentions choosing template and options, but the input schema only accepts a projectName, creating a mismatch. It also does not distinguish from the sibling tool demo2_scaffold_confirm.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage context is provided. The description does not indicate when to use this tool versus siblings like demo2_scaffold_confirm, nor does it mention prerequisites or follow-up actions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Approve a pending consent request and receive a scoped mock token. The token is ephemeral and never leaves the server process.
| Name | Required | Description | Default |
|---|---|---|---|
| consentId | Yes | The consent ID from demo3_request_consent |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and effectively discloses key behaviors: the token is scoped, mock, ephemeral, and never leaves the server process. This informs the agent of important constraints and safety aspects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no wasted words, front-loaded with the main action. Every sentence adds essential information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers purpose and key behavioral traits. However, given no output schema and no annotations, it could be more complete by describing what the token can be used for (e.g., with demo3_protected_action) or error handling (e.g., invalid consentId). It is still fairly complete for a simple approval tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with the consentId parameter already described as from demo3_request_consent. The description adds no additional semantics beyond that, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Approve) and the resource (a pending consent request), and specifies the output (a scoped mock token). This distinguishes it from sibling tools like demo3_request_consent, which likely handles the request side.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage after obtaining a consent ID from demo3_request_consent (via parameter description), but does not explicitly state when to use this tool versus alternatives, nor does it provide exclusions or prerequisite conditions beyond the consent ID.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Execute a protected action using the mock token from demo3_approve_consent. Validates the token is present, unexpired, and properly scoped.
| Name | Required | Description | Default |
|---|---|---|---|
| token | Yes | Mock token from demo3_approve_consent | |
| action | Yes | Action to perform |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses that the token is validated for presence, expiry, and scoping, which are important behavioral traits. However, it does not describe return values, error conditions, side effects, or what happens on success/failure, leaving gaps for agent decision-making.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, zero wasted words. Information is front-loaded and every sentence adds value. The format is clean and appropriate for the tool's simplicity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has only two parameters, no output schema, and is part of a clear sequence (consent then action), the description covers the essential flow and validation. It lacks detail on return values and error handling, but for a simple mock tool this is acceptable. The description is mostly complete for the context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with both parameters described. The description adds the origin of the token ('mock token from demo3_approve_consent') which provides value beyond the schema, but this is minimal. For action, it adds no new meaning. Baseline 3 applies with minor addition.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Execute' and resource 'protected action', and ties it to the token from demo3_approve_consent. While 'protected action' is somewhat generic, the context of token validation provides specificity and distinguishes it from sibling tools like demo3_request_consent or demo3_approve_consent.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly mentions using the token from demo3_approve_consent and validates its properties, implicitly telling the agent to call this only after obtaining a consent token. It does not explicitly list when not to use or alternatives, but the prerequisite is clear enough. Sibling tools like demo3_approve_consent are distinct in purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Initiate a secure OAuth-style handoff. Returns a mock authorization prompt that the user must approve before the protected action can proceed. No real secrets are involved – this is a simulation.
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | The protected action being requested | |
| userId | No | Simulated user ID | demo-user |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Lacks annotations; description notes simulation and no real secrets but does not detail side effects or idempotency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three succinct sentences front-loaded with core purpose, no extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given two well-documented parameters and no output schema, description sufficiently explains the tool's behavior and return value.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema descriptions cover both parameters fully; description adds no extra meaning beyond what schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it initiates a secure OAuth-style handoff and returns a mock authorization prompt, distinguishing itself from sibling consent and action tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies usage before a protected action but does not explicitly exclude alternatives or provide when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check progress of a running pipeline task. Returns current step, percentage, and log entries.
| Name | Required | Description | Default |
|---|---|---|---|
| taskId | Yes | Task ID from demo4_start_pipeline |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavioral traits. It only mentions return values and not side effects, safety, rate limits, or whether it is read-only. This is insufficient for full transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that front-loads the purpose and immediately follows with key output information. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, the description provides a minimal but adequate overview. It covers purpose and returns, but omits details on error conditions, prerequisite state, and whether log entries are paginated.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description adds meaning by specifying that taskId comes from 'demo4_start_pipeline', guiding the agent on data provenance. This goes beyond the basic schema description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'Check', resource 'progress of a running pipeline task', and explicitly lists return values (step, percentage, log entries). It effectively distinguishes from siblings like demo4_start_pipeline and demo5_cancel_task.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context (after a pipeline is started) by referencing 'task ID from demo4_start_pipeline' but does not explicitly state when to use versus alternatives or when not to use. It provides clear context but lacks exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Start a long-running build pipeline with 12 steps. Returns progress updates as the task runs. Use demo4_check_progress to poll status.
| Name | Required | Description | Default |
|---|---|---|---|
| project | No | Project name | acme-app |
| stepDelayMs | No | Delay between steps in ms (for demo pacing) | |
| failAtStep | No | Inject failure at this step (0 = no failure) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must cover behavioral traits. It states the tool is long-running and returns progress updates, but does not disclose failure behavior, idempotency, or authorization needs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences, front-loaded with purpose and action, followed by a clear sibling reference. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Lacks output schema and does not explain the format of progress updates or mention a returned task identifier. While the parameter schema is good, the description could better connect with the polling sibling.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already explains each parameter. The description does not add any additional parameter-specific meaning beyond what is in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('start'), the resource ('long-running build pipeline with 12 steps'), and the outcome ('returns progress updates'). This differentiates it from sibling tools like demo4_check_progress.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly mentions using demo4_check_progress to poll status, providing guidance on the next step. However, it does not elaborate on when to start versus when not to, or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Cancel a running pipeline task. The task will stop at its current step.
| Name | Required | Description | Default |
|---|---|---|---|
| taskId | Yes | Task ID to cancel | |
| reason | No | Cancellation reason | User requested cancellation |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It states the task will stop, but does not address reversibility, side effects, or potential failures, which is critical for a cancellation action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, no unnecessary words. Could be more concise by combining, but still efficient. Missing opportunity to include usage guidance concisely.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a cancellation action, the description lacks important context: what happens to the task's state, whether it can be resumed, confirmation steps, or output. More completeness would aid agent decision-making.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (both parameters have descriptions). The tool description adds no extra meaning beyond the schema, meeting the baseline expectation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Cancel') and the resource ('running pipeline task'), and adds specificity with 'stop at its current step'. It distinguishes well from sibling tools like retry_task and list_tasks.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives (e.g., retry_task), no prerequisites or exclusions. The description implies basic usage but offers no decision support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all tasks (running, completed, failed, cancelled) for visibility.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description should disclose behavioral traits. It only states 'list' with no mention of side effects, rate limits, or read-only nature. Minimal behavioral information.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single 10-word sentence that starts with the action verb 'List' and is front-loaded with key information. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema, so the description should explain what is returned (e.g., task IDs, statuses). It does not. While simple, it lacks completeness for a list tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, so schema coverage is 100%. The description adds no parameter information beyond the empty schema, but none is needed. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it lists all tasks with specific statuses (running, completed, failed, cancelled). It distinguishes from sibling tools (cancel, retry) by focusing on listing. However, 'all tasks' lacks context about which tasks, making it slightly ambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives or when not to use it. The description does not mention any prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retry a failed or cancelled task. Can resume from where it stopped or restart entirely with modified parameters.
| Name | Required | Description | Default |
|---|---|---|---|
| taskId | Yes | Original task ID to retry | |
| mode | No | Resume from last step or restart from beginning | resume |
| fixFailingStep | No | If true, the previously failing step will succeed on retry | |
| stepDelayMs | No | Delay between steps |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It explains resume vs restart and hints at modifying parameters, but does not disclose whether retrying creates a new task, what happens to the original task, or prerequisites like task state requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with no unnecessary words. The main action is front-loaded, and each sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the basic purpose but lacks details on return values, side effects, and how 'modified parameters' relate to the schema. Given moderate complexity and no output schema, more completeness would be beneficial.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all parameters. The description adds context about resume/restart and modified parameters but does not add syntax or format details beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'retry' and the resource 'task', and specifies it's for failed or cancelled tasks. It distinguishes from sibling tools like demo5_cancel_task and demo5_list_tasks.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when a task is failed or cancelled, and mentions two modes (resume/restart) to guide selection. However, it does not explicitly exclude other scenarios or compare to alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get all saved colors from the palette.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It only states the action without revealing potential side effects, authentication needs, rate limits, or whether the operation is read-only. Minimal disclosure beyond the basic function.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, front-loaded sentence that efficiently conveys the tool's purpose with no extraneous words. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
While the tool is simple (no params, no output schema), the description lacks details like response format, existence of multiple palettes, or error handling. It is minimally adequate but could provide more context given no other structured fields.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so schema coverage is 100% by default. The description adds no parameter info, but none is needed. Baseline for 0 params is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Get all saved colors from the palette' with a specific verb ('get') and resource ('colors from palette'). It unambiguously indicates the tool's purpose and is distinct from sibling tools like 'demo6_save_color'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for retrieving all saved colors, but provides no guidance on when to use this tool versus alternatives (e.g., demo7_gallery_state or other getters). No exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Save a color to the server palette. Can be called by the Color Picker UI or directly by an agent.
| Name | Required | Description | Default |
|---|---|---|---|
| color | Yes | ||
| name | Yes | Human-readable color name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fails to disclose behavioral traits like side effects, permissions, idempotency, or what happens on success/failure. The word 'save' implies mutation, but no further details are given.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two sentences and no wasted words. However, it could be slightly more informative without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 2 required parameters and no output schema, the description is too minimal. It omits return values, error states, and whether the operation overwrites existing colors, leaving gaps for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not add any meaning beyond the input schema. It does not explain the 'color' parameter's format or the purpose of the 'name' parameter, despite the schema having 50% coverage (only name has a description).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Save' and the resource 'color to the server palette', making the tool's purpose unambiguous. It effectively distinguishes itself from sibling tools like demo6_get_palette.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives or when not to use it. The note about being callable by UI or an agent is context, not usage guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get or set the component gallery state. When setting, the server updates its state which the UI can read on next render.
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | Get current state or set new state | |
| component | No | Component to display (for set) | |
| variant | No | Variant to display (for set) | |
| theme | No | Theme (for set) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It explains that setting updates server state for the next UI render, but does not confirm that get is read-only or disclose other behavioral traits like idempotency or error handling.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the purpose, and contains no unnecessary words. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, and the description does not explain what get returns (e.g., the current state structure) or what set returns (e.g., success/error). For a tool with 4 parameters, this leaves a significant gap for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with parameter descriptions. The description adds context about the server-side update and UI render for set, which enhances understanding beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool gets or sets the component gallery state, with a specific verb and resource. It distinguishes this tool from sibling tools which handle different domains (e.g., CLI, scaffolds, consent, palette, exports).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use set (to update UI state) but does not explicitly guide on when to use get vs set, nor compare with alternative tools. No when-not or exclusionary criteria are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate a markdown report of all demos and write it to /outputs. Includes sharing guidance, VS Code config, and dev mode checklist.
| Name | Required | Description | Default |
|---|---|---|---|
| title | No | Report title | MCP Demos Report |
| includeDevMode | No | Include dev mode section | |
| format | No | Output format | markdown |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description effectively discloses the side effect of writing to /outputs and the report contents (sharing guidance, VS Code config, dev mode checklist). However, it does not address whether the tool overwrites existing files or requires specific permissions, which would enhance transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with two sentences, the first stating the core action and output, the second listing included content. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given three optional parameters, no output schema, and no annotations, the description adequately covers the tool's purpose and output location. It could mention whether the output file is overwritten or appended, and what the return value is, but overall it is sufficiently complete for its complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, so the schema already documents all three parameters (title, includeDevMode, format). The description adds no additional meaning beyond stating the report is markdown (while format can also be JSON) and listing included sections which are not controlled by parameters. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool generates a markdown report of all demos and writes it to /outputs, specifying the verb 'generate' and the resource 'report of all demos'. This distinguishes it from sibling tools like demo8_list_exports which likely list exports rather than generate a comprehensive report.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like demo8_list_exports or other demo tools. The description does not mention prerequisites, when not to use, or specify the context in which this tool is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all exported reports in the /outputs directory.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only states the action without disclosing behavior such as return format, error handling, or side effects. It assumes a read-only operation but provides no detail.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no wasted words. It efficiently conveys the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description should provide more context about the return format or behavior. It is sufficient for a simple list but lacks completeness for an agent to fully understand the tool's output.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, so the baseline is 4. The description adds no parameter information, but none is needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly specifies the action (List), the resource (exported reports), and the location (/outputs directory). It distinguishes from the sibling demo8_export_report, which creates exports.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. There is no mention of prerequisites, ordering, or context where listing exports is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0demo1_polite_clidemo2_scaffold_confirmdemo2_scaffold_startdemo3_approve_consentdemo3_protected_actiondemo3_request_consentdemo4_check_progressdemo4_start_pipelinedemo5_cancel_taskdemo5_list_tasksdemo5_retry_taskdemo6_get_palettedemo6_save_colordemo7_gallery_statedemo8_export_reportdemo8_list_exportsScored across 16 tools
Each tool targets a distinct demo scenario and action, with no overlapping purposes. The demoX prefix clearly groups related tools, and individual tool descriptions specify unique roles (e.g., start vs. confirm vs. check progress).
All tools follow a consistent snake_case verb_noun pattern (e.g., demo1_polite_cli, demo2_scaffold_start, demo3_request_consent). The naming is uniform across all 16 tools with no deviations.
With 16 tools, the count is slightly above the ideal 3-15 range, but given the multi-demo scope, it remains well-scoped. Each tool serves a distinct purpose, and none feel redundant.
The tool surface covers the core workflows for each demo scenario (e.g., scaffolding, consent flow, pipeline management, palette operations). Minor gaps exist (e.g., no tool to reset a demo), but overall it supports the intended demonstrations adequately.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
327 dev tools via REST API and MCP. Generate Dockerfiles, schemas, K8s, APIs, and more.
MCP Hub: AI service discovery, per-user OAuth, and multi-service workflow orchestration
MCP server for mandates, delegation, policy-gated execution, credential grants, and audit.
