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., "@NetOps MCP Server My Wi-Fi keeps disconnecting—run diagnostics and suggest fixes."
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.
A Model Context Protocol (MCP) server providing structured, bottom-up network diagnostics (OSI Layers 1–3) for LLM clients like Claude Desktop.
WSL2 Host Boundary Traversal: WSL2 runs inside a virtualized Hyper-V switch. Standard Linux utilities cannot see host Wi-Fi or physical adapters. This server bridges across the boundary into Windows host binaries (netsh.exe, route.exe) to collect physical Wi-Fi signal, link rates, and default gateway status.
Complete MCP Primitive Coverage:
Tools: Active diagnostic probes (run_ping, get_gateway_telemetry, get_wifi_telemetry, resolve_dns, lookup_remediation, create_incident_ticket).
Resources: Exposes standard-backed runbooks (netops://runbooks/network-triage) directly into the agent's context window.
Prompts: triage_network guides the LLM through a disciplined, bottom-up diagnostic sequence rather than jumping to conclusions.
Defensive Engineering:
Strict input validation against command chaining (;, |, &, etc.) and option-injection flags (-).
Hard timeouts on all subprocess network calls (ping, netsh, route).
SQLite persistence for tracking triage incidents locally without crashing server responses on I/O failures.
Related MCP server: connectivity-diagnostics
Python >= 3.10
uv (recommended) or standard python3 -m venv
git clone https://github.com/drew-1618/netops-mcp.git
cd netops-mcp
# Using uv (fast, deterministic sync from uv.lock)
uv syncTest the server in stdio mode:
uv run python -m src.serverOr test interactively using the official MCP Inspector:
npx @modelcontextprotocol/inspector uv run python -m src.serverAdd the server to your Claude Desktop configuration file (%APPDATA%\Claude\claude_desktop_config.json):
{
"mcpServers": {
"netops": {
"command": "wsl.exe",
"args": [
"-e",
"/<your-absolute-path>/netops-mcp/.venv/bin/python",
"-m",
"src.server"
]
}
}
}Note: Claude Desktop will automatically launch and manage the background WSL process over
stdio. No terminal or WSL window needs to remain open.
Tool | Arguments | Description |
|
| Measures reachability, packet loss %, and average RTT latency. |
| None | Queries host routing table for default gateway and tests first-hop reachability. |
| None | Extracts host Wi-Fi interface state, SSID, signal %, and link rates via |
|
| Resolves hostnames via local resolver and measures DNS resolution latency in ms. |
|
| Extracts specific runbook remediation sections ( |
|
| Generates a unique incident ID ( |
|
| Queries past incident records to check for recurring failures or open tickets. |
URI | Description |
| Full operational SLA thresholds and bottom-up triage guidelines from |
Prompt | Arguments | Description |
|
| Guides the LLM step-by-step through Layer 1 to Layer 3 diagnostic checks and incident escalation. |
Creates a structured operational incident ticket payload for escalation
| Name | Required | Description | Default |
|---|---|---|---|
| target | Yes | ||
| summary | Yes | ||
| severity | No | medium | |
| failing_layer | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says 'Creates a structured operational incident ticket payload', which is ambiguous about whether it actually creates a ticket or just a payload, and doesn't mention side effects, permissions, reversibility, or any constraints.
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 (one sentence), but it's under-specified. It doesn't front-load critical usage information and is too short to be adequately informative for a tool with 4 parameters and no other documentation.
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?
Even though an output schema exists, the description doesn't explain what the tool returns or how the payload is used. With no parameter details, no usage context, and no behavioral notes, the agent lacks essential information to call this tool correctly.
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 provides no information about any of the four parameters (target, summary, severity, failing_layer). The agent has no guidance on their meaning, format, or constraints, making correct invocation guesswork.
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 'Creates' and a resource 'operational incident ticket payload', which clearly differentiates it from sibling tools like query_incident_history. However, it lacks specificity about what 'payload' entails and doesn't mention the target system, so it's clear but not fully detailed.
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?
There is no explicit guidance on when to use this tool versus alternatives. The phrase 'for escalation' hints at a use case, but it doesn't specify conditions, prerequisites, or when not to use it. No exclusions or alternative tool references are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Discover the local default gateway and check first-hop reachability.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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 discloses the operation (discover gateway, check first-hop reachability) but does not mention whether this is a read-only operation, whether it requires special permissions, what the output looks like, or whether it performs any active network probes that could have side effects.
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 that front-loads the primary action ('Discover the local default gateway') and adds the secondary purpose ('check first-hop reachability'). 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?
For a zero-parameter tool with no output schema, the description is reasonably complete for basic invocation. However, it lacks information about the return format, whether the check is active or passive, and how it relates to run_ping. An agent could call it correctly but may not know what to expect from the result.
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 schema provides no parameter semantics. The description appropriately explains what the tool does without needing to document parameters. Baseline 4 is appropriate for a zero-parameter tool.
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 ('Discover') and resource ('local default gateway'), and adds 'check first-hop reachability' to clarify the telemetry aspect. It is clear enough to distinguish from siblings like get_wifi_telemetry, though it does not explicitly name a sibling.
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 a diagnostic/network-checking use case, and the sibling list includes run_ping and resolve_dns, so an agent can infer this is for gateway-level reachability rather than general connectivity. However, it does not explicitly state when to use this tool versus run_ping or get_wifi_telemetry.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Gathers local WiFi interface telemetry such as SSID, signal strength percentage, radio type, and link rates.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the behavioral burden. The verb 'Gathers' suggests a read-only operation slash, and the listed fields indicate what data will be returned. However, it does not explicitly confirm there are no state changes, possible permission requirements, or behavior when no WiFi interface is available.
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, focused sentence that front-loads the action and resource, then adds three concrete examples of the telemetry gathered. Every word earns its place; there is no filler or repetition.
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 zero-parameter, read-only telemetry tool, the description is largely complete: it names the primary output fields, which is especially important without an output schema. The only gaps are minor edge-case disclosures, such as behavior when the WiFi interface is absent or unavailable.
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 is empty (zero parameters), so there is no parameter coverage to worry about. The description compensates by listing the telemetry fields returned (SSID, signal strength, radio type, link rates), which gives the agent a clear expectation of output despite the lack of an output 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 uses the specific verb 'Gathers' and names a clear resource: 'local WiFi interface telemetry.' It provides concrete examples (SSID, signal strength, radio type, link rates) that make the tool's purpose unambiguous and distinguish it from sibling tools like get_gateway_telemetry, which targets a different network scope.
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 intended use is implied by the description: use it when WiFi interface telemetry is needed. However, there is no explicit 'when to use' or 'when not to use' guidance, and no mention of alternatives such as get_gateway_telemetry, leaving the agent to infer the scope from the tool name and description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Look up specific remediation advice and thresholds from the triage runbook.
Valid categories: 'physical' (or 'signal', 'L1'), 'packet_loss' (or 'loss'), 'latency' (or 'RTT', 'bufferbload').
| Name | Required | Description | Default |
|---|---|---|---|
| category | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not state whether this is a read-only lookup, what the return format is, whether it can fail for invalid categories, or any side effects. The description is purely about input validation, not behavior.
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 with no filler. The purpose is stated first, and the parameter guidance is compactly listed. Every sentence 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?
For a single-parameter lookup tool with no output schema, the description covers the input domain well but omits return value details and error behavior. An agent could call it correctly with a valid category, but would not know what to expect in the response or how to handle an invalid category.
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%, so the description must compensate. It does so by enumerating valid values and aliases for the single parameter, which is genuinely useful beyond the bare schema. However, it does not explain what each category returns or how the aliases map to canonical values.
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 ('look up') and resource ('remediation advice and thresholds from the triage runbook'), which clearly distinguishes it from sibling tools like run_ping or get_gateway_telemetry. It does not explicitly name a sibling alternative, but the resource and action are specific enough to make the tool's purpose clear.
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 explicit valid categories and aliases, which tells the agent exactly what input values are acceptable. It does not explicitly state when to use this tool versus alternatives, but the domain ('triage runbook') and the category list imply the intended use case clearly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Queries past incident tickets to identify recurring failures, historical context, or open issues
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| status | No | ||
| target | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the behavioral burden. 'Queries' implies a read-only operation and 'past incident tickets' conveys scope, but the description does not explicitly state that no tickets are modified, nor mention permissions, rate limits, or retention. It is adequate but not rich behavioral 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 front-loaded sentence with no filler; it names the action, resource, and intended use cases immediately. There is no wasted text.
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 optional-parameter query with an output schema, the description supplies the core purpose. However, the unresolved semantics of status/target and the lack of explicit read-only confirmation leave gaps, making it a minimum-viable but not fully complete description.
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 never addresses the three parameters. 'limit' is inferable from its name, but 'status' and especially 'target' are ambiguous—target of an incident, a host, or a service?—and no allowed values or examples are given.
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 opens with the specific verb 'Queries' and resource 'past incident tickets', then states concrete goals: recurring failures, historical context, and open issues. This clearly distinguishes it from sibling tools like create_incident_ticket, which writes, and network diagnostic tools such as run_ping and resolve_dns.
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 gives clear use cases: identifying recurring failures, historical context, or open issues. It does not explicitly name alternatives or exclusions, but none of the sibling tools performs incident-history lookup, so the usage context is reasonably clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Resolves a hostname using the local system resolver & measures resolution latency
| Name | Required | Description | Default |
|---|---|---|---|
| hostname | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full transparency burden. It does disclose the mechanism ('local system resolver') and the latency measurement, which is useful. However, it does not mention failure behavior, timeouts, or whether the operation is purely read-only.
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, tightly written sentence that front-loads the action and adds the latency detail without waste. 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?
The tool is simple, has only one required parameter, and an output schema exists, so return-value details are not necessary. The description covers the core action and metric, though it could better address when to prefer this over run_ping.
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%, so the description needed to clarify what 'hostname' should look like (e.g., FQDN, IP address, port inclusion). It does not add any semantics beyond the schema's field title, merely echoing the parameter name.
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 ('Resolves'), a specific resource ('a hostname'), and the additional behavior of measuring resolution latency. It clearly distinguishes itself from sibling tools like run_ping or telemetry queries.
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 gives no explicit guidance on when to use resolve_dns versus alternatives such as run_ping, even though the distinction between DNS resolution and network reachability is important. Usage context is only implied by the tool name and description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Pings an IP address or hostname to check reachability, average latency, and packet loss.
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | ||
| target | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the behavioral disclosure burden. It states the operation and the metrics returned, implying a read-only diagnostic, but it does not mention permissions, timeouts, packet size, or whether any state changes occur. For a simple ping this is adequate but not rich.
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?
One sentence with no filler; the key facts (action, target type, result metrics) are front-loaded. Every phrase contributes 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 is sufficient to understand what the tool does, and the stated metrics hint at the response contents despite the absence of an output schema. However, the count parameter is unspecified and no usage exclusions or operational caveats are provided, so an agent must still guess at edge cases.
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. It defines 'target' as an IP address or hostname, but it does not describe 'count', leaving the agent to infer that it controls the number of probes. This is only partial compensation for the schema gap.
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 uses the verb 'Pings' and specifies the resource ('an IP address or hostname') and the outcome ('reachability, average latency, and packet loss'). It is clear and distinct from sibling tools in practice, but it never explicitly contrasts with resolve_dns or the telemetry tools, so it stops short of the top score.
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 purpose clause 'to check reachability, average latency, and packet loss' implies when the tool is useful, but there is no explicit when-to-use or when-not-to-use guidance. Sibling tools like resolve_dns and get_gateway_telemetry exist, yet the description does not route the agent among them.
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.
v0.1.0create_incident_ticketget_gateway_telemetryget_wifi_telemetrylookup_remediationquery_incident_historyresolve_dnsrun_pingScored across 7 tools
Each tool targets a distinct diagnostic or operational action: gateway telemetry, WiFi telemetry, ping, DNS, runbook lookup, and incident creation/history. The only possible overlap is reachability checks between get_gateway_telemetry and run_ping, but their scopes are explicitly separated by first-hop vs arbitrary target.
All tools follow a verb_noun snake_case pattern such as get_*, run_*, resolve_*, create_*, query_*, and lookup_*. There is no mix of casing or grammatical styles, and each verb clearly signals the tool's intended action.
Seven tools is a focused, appropriately scoped set for a NetOps assistant: four network diagnostics, one remediation reference, and two incident-management tools. Each tool adds a distinct capability without unnecessary bloat.
The set covers the core diagnostic loop with gateway/WiFi/ping/DNS checks, remediation lookup, and incident creation/history. It lacks some obvious extras like traceroute or incident update/close, but these are workable gaps rather than blocking omissions.
Network, domain and website diagnostics for AI clients via MCP.
Provides capabilities that let LLM agents perform a range of infrastructure management tasks.
Protocol-native energy infrastructure orchestration for AI data centers. Provides 46 MCP tools across 8 grid protocols (IEC-61850, DNP3, Modbus, OCPP, OpenADR, IEEE 2030.5, IEC 60870-5-104, ICCP) with 5 core API primitives: connect, dispatch, settle, comply, and intel. Enables AI agents to programmatically interact with substations, grid interfaces, and energy assets for real-time workload-grid coordination.
Agent-readiness scanner (0-5 score), robots.txt + llms.txt generators, managed agent enablement.
