Provides AI-powered diagnosis of nTop errors and supports parallel swarm diagnosis with multiple agents using OpenAI models.
Click on "Deploy 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., "@ntop-ai-helper-mcp diagnose this error: Failed to generate lattice structure"
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.
MCP server that helps troubleshoot nTop issues with:
AI diagnosis (diagnose_ntop_error)
20-agent parallel swarm mode (swarm_diagnose_ntop)
Screen capture (capture_screen)
Macro automation (save_macro, list_macros, run_macro)
Optional direct terminal execution (run_terminal_command)
cd "$HOME\Documents\ntop-ai-helper-mcp"
npm install
npm run buildRun directly:
npm startRun in dev mode:
npm run devRelated MCP server: Error Debugging MCP Server
Copy .env.example to .env and set values:
OPENAI_API_KEY (required for real AI diagnosis/swarm)
OPENAI_MODEL (default: gpt-5.2)
ENABLE_COMMAND_TOOL (false by default; set to true to allow shell command tool)
Use the built server file as the MCP command target:
{
"mcpServers": {
"ntop-ai-helper": {
"command": "node",
"args": [
"C:\\Users\\sohum\\Documents\\ntop-ai-helper-mcp\\dist\\server.js"
],
"env": {
"OPENAI_API_KEY": "YOUR_KEY_HERE",
"OPENAI_MODEL": "gpt-5.2",
"ENABLE_COMMAND_TOOL": "false"
}
}
}
}capture_screen
Inputs: label?
Output: file path to PNG in captures/
list_macros
Inputs: none
Output: all macros from data/macros.json
save_macro
Inputs: name, description?, steps[]
Step types:
sleep: { "type": "sleep", "ms": 500 }
sendKeys: { "type": "sendKeys", "keys": "^l" }
command: { "type": "command", "command": "dir" }
run_macro
Inputs: name, dryRun?
Executes macro step-by-step and returns a run report
diagnose_ntop_error
Inputs: errorText, context?, goal?
Uses OpenAI if available; otherwise local fallback heuristics
swarm_diagnose_ntop
Inputs: errorText, context?, goal?, agentCount?
Runs up to 40 agents in parallel (default 20), plus final synthesis
run_terminal_command
Inputs: command, cwd?, timeoutMs?
Disabled by default for safety
Screen capture and sendKeys are Windows-oriented.
Macro steps are intentionally explicit for predictable automation.
If you want stricter safety, keep ENABLE_COMMAND_TOOL=false.
Capture the current primary screen and save a PNG under ./captures.
| Name | Required | Description | Default |
|---|---|---|---|
| label | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It mentions the output destination but omits details about directory creation, file overwriting, the role of the 'label' parameter, and failure behavior. This leaves the tool's behavior largely unspecified.
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 sentence that front-loads the verb and resource, with no unnecessary words. It is concise and clearly structured.
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?
Despite the tool's simplicity, the description is incomplete for invocation: it fails to explain the 'label' parameter, what the tool returns (e.g., a file path), and any preconditions or error handling. The lack of output schema and annotations increases the need for description detail, which is absent.
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 defines a single optional 'label' parameter with no description (0% coverage), and the description does not mention 'label' at all. An agent has no information about how this parameter affects the capture or output.
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 'Capture' and the resource 'current primary screen', along with the output ('save a PNG under ./captures'). This differentiates it from sibling tools that handle macros, diagnostics, and terminal commands.
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 its usage by stating the action, but it does not explicitly say when to use it or mention alternatives. There is no context about prerequisites like screen recording permissions or scenarios where this tool is preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Diagnose an nTop error. Uses OpenAI if OPENAI_API_KEY is set; otherwise returns a local fallback diagnosis.
| Name | Required | Description | Default |
|---|---|---|---|
| goal | No | ||
| context | No | ||
| errorText | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden of disclosing behavior. It usefully reveals that the tool uses OpenAI if OPENAI_API_KEY is set and otherwise returns a local fallback diagnosis. However, it does not mention side effects, permission requirements, or the format of the diagnosis.
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 and well-structured: the first sentence states the purpose, the second explains the conditional behavior. Every sentence contributes value with no redundancy or irrelevant details.
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 presence of three parameters, no annotations, and no output schema, the description is incomplete. It lacks parameter semantics, usage context, and expected output details, making it difficult for an agent to invoke the tool correctly without additional information.
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 has 0% description coverage, and the tool description does not explain the 'goal', 'context', or 'errorText' parameters. While 'errorText' can be inferred from the tool name and description, the purpose of 'goal' and 'context' remains ambiguous, and the description fails to compensate for the lack of schema documentation.
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's purpose with a specific verb and resource: 'Diagnose an nTop error'. However, it does not explicitly differentiate from the sibling tool 'swarm_diagnose_ntop', which may similarly diagnose errors, so it is clear but not fully distinguishing.
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 provides no guidance on when to use this tool versus alternatives like 'swarm_diagnose_ntop' or 'run_terminal_command'. It only states the core action, with no mention of use cases, prerequisites, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List available automation macros.
| 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 the full burden of behavioral disclosure. It only says 'List', which implies a safe read operation, but does not describe what 'available' means, the return format, or any potential side effects. This is little more than a restatement of the tool name.
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, focused sentence that gets straight to the point. It is appropriately sized and front-loaded, with 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?
Given the low complexity (0 params, no output schema), the description is minimally viable but not complete. It does not explain what the output looks like or how 'available' is determined, which could be ambiguous for an agent. However, the simplicity of the tool makes this a minor gap.
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 the baseline is 4. There is no parameter information needed, and the description does not need to compensate for any schema gaps. The schema is fully covered.
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 'List available automation macros' uses a specific verb and resource, clearly distinguishing itself from sibling tools like run_macro and save_macro. It states exactly what the tool does.
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 ('list' when you need to see available macros) but provides no explicit when/when-not guidance or references to alternatives. It lacks context about when to choose this over sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run a saved macro by name.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| dryRun | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It only states the action without mentioning side effects, safety, reversibility, or what happens when executed. No context about potential impacts is provided.
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 concise sentence with no filler. It efficiently communicates the core purpose without wasting 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?
For a tool with two parameters and no output schema or annotations, the description is far too sparse. It does not explain the effect of running a macro, what 'dryRun' does, or any prerequisites, leaving the agent without enough context for correct invocation.
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 0%, and the description only hints at the 'name' parameter but says nothing about 'dryRun'. The description fails to compensate for the lack of schema-level documentation, leaving param meanings ambiguous.
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 'Run a saved macro by name' uses a specific verb (run) and resource (saved macro), clearly distinguishing it from siblings like list_macros, save_macro, and run_terminal_command. It precisely conveys what the tool does.
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 for executing a previously saved macro, but does not explicitly mention alternatives or provide when-to-use/not-to-use guidance. The context is clear enough from the name and sibling tools, so it meets the 'implied usage' bar.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Execute a terminal command for power-user automation. Disabled by default; set ENABLE_COMMAND_TOOL=true to allow.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | ||
| command | Yes | ||
| timeoutMs | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that the tool is disabled by default and requires an environment variable to enable, which is a meaningful behavioral trait. However, it does not mention safety implications, the fact that arbitrary commands can modify system state, or any execution environment details. The 'power-user' label hints at risk but stops short of explicit disclosure.
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 sentence that is front-loaded with the core purpose. It is concise, with no filler or redundant wording. Every element contributes to understanding the tool's function and an important prerequisite.
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 executes arbitrary terminal commands, a complex and potentially destructive operation, but the description does not mention expected outputs (stdout/stderr, exit codes), error handling, or side effects. No output schema exists to fill this gap. The description only covers the enablement prerequisite, leaving significant behavioral and usage context unspecified.
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 0%, and the description adds no parameter information. The parameter names (command, cwd, timeoutMs) are somewhat self-explanatory but not fully defined (e.g., cwd is not described as current working directory). The description does not compensate for the lack of schema descriptions, leaving the agent to infer meaning from names and types alone.
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 a specific action ('Execute a terminal command') and clearly identifies the resource (terminal command). It is distinct from sibling tools like capture_screen or run_macro, which serve different purposes. The 'power-user automation' qualifier adds context without obscuring the core function.
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 for advanced automation tasks and notes that the tool is disabled by default, providing a prerequisite. However, it does not explicitly state when to use this tool over alternatives or provide exclusions. There are no direct alternatives among siblings, so the context is adequate but not fully explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create or update a macro with steps: sleep, sendKeys, command.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| steps | Yes | ||
| description | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility. It indicates create/update but does not explain update semantics (overwrite vs merge), permissions, side effects, error scenarios, or return behavior. For a mutating tool, this is a significant transparency gap.
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 clauses long and immediately communicates the core action and step types. There is no filler, and the most important information is front-loaded.
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 absence of annotations, output schema, and any schema descriptions, the description is too thin for a tool with a nested steps structure. It leaves the agent without guidance on constructing valid steps or understanding update behavior, making the tool materially incomplete.
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 0%, and the description only hints at step types. It does not explain the meaning of `name`, `steps`, `description`, or the individual step fields (ms, cwd, keys, command, timeoutMs). The description provides minimal value over the raw 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 ('Create or update'), the resource ('macro'), and the supported step types ('sleep, sendKeys, command'). This distinguishes it from sibling tools like list_macros and run_macro, which have different verbs and purposes.
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 saving macros, and the sibling names suggest list/run/capture/diagnose contexts. However, it does not explicitly mention when to use this tool over alternatives or state any exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run a multi-agent nTop diagnosis swarm. Defaults to 20 agents in parallel and returns each finding + synthesis.
| Name | Required | Description | Default |
|---|---|---|---|
| goal | No | ||
| context | No | ||
| errorText | Yes | ||
| agentCount | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the behavioral transparency burden. It discloses the default agent count (20), parallel execution, and the output format (findings + synthesis). However, it omits potential costs, side effects, or failure behavior, which is significant for a tool that spawns 20 parallel agents.
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 primary function and includes key operational details (parallel, default count, output). There is no wasted wording.
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 tool with 4 parameters and no output schema, the description is too sparse. It mentions high-level returns but does not describe the structure of findings or the nature of the synthesis, nor does it explain what the swarm does beyond diagnosis. This leaves the agent guessing about the tool's full behavior.
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%, so the description must compensate for understanding parameters. It only hints at the agentCount parameter by mentioning '20 agents' as a default, but it does not explain the purpose of 'errorText,' 'goal,' or 'context.' This leaves the required parameter and optional ones nearly unexplained.
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 a specific verb and resource: 'Run a multi-agent nTop diagnosis swarm.' It clearly distinguishes from the sibling tool 'diagnose_ntop_error' by emphasizing 'multi-agent' and 'swarm,' which implies a parallel approach versus a likely single-agent diagnostic.
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 nTop error diagnosis but does not explicitly state when to use it over 'diagnose_ntop_error' or other siblings. It provides context (multi-agent diagnosis with parallel agents) but lacks exclusions or alternative recommendations.
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.
v1.0.0capture_screendiagnose_ntop_errorlist_macrosrun_macrorun_terminal_commandsave_macroswarm_diagnose_ntopScored across 7 tools
Most tools have clearly distinct purposes (screen capture, macro management, terminal command). The only overlap is between diagnose_ntop_error and swarm_diagnose_ntop, both for diagnosing nTop errors, but their descriptions clarify different approaches (single vs. multi-agent).
Tool names generally follow a verb_noun pattern (capture_screen, list_macros, save_macro, run_macro, diagnose_ntop_error). The name swarm_diagnose_ntop deviates by using a noun prefix, and run_terminal_command also fits the pattern, but overall the convention is consistent.
With 7 tools, the set is well-scoped for an nTop automation and diagnostics helper. Each tool serves a distinct need without redundancy or bloat, fitting comfortably in the ideal 3-15 range.
Macro lifecycle is well covered (list, save/update, run), and diagnosis has two options. Minor gaps exist, such as no delete macro or ability to stop a running macro, but the core workflows for automation and error handling are present.
Voice-powered bug reporting with 13 MCP tools. Record bugs by talking; let AI find and fix them.
A flock of AI users tests your deployed app and reports where real people get stuck, with fixes.
Debug, build, and manage Power Automate cloud flows with AI agents
Triage failing GitHub Actions jobs and see what self-heal repaired, in natural language.
