SRV Record Parser Skill
The tool
The API parses SRV record strings in various formats and provides structured output with service identification, protocol information, and load balancing parameters.
Once your client is connected to the VerveKit MCP server, this appears in its tool list as SRVRecordParserSkill. It is read-only and open-world: it fetches, it never mutates anything on your side, so most clients will call it without asking you to confirm.
{
"name": "SRVRecordParserSkill",
"arguments": {
"record": "_http._tcp.example.com. 3600 IN SRV 10 60 80 server.example.com."
}
}What that looks like in a conversation
You don't name the tool — the model picks it. Asking about _http._tcp.example.com. 3600 IN SRV 10 60 80 server.example.com. in the terms this source covers is enough for it to reach for SRVRecordParserSkill on its own.
Connecting
One server URL covers every skill in the catalog, including this one. Authorization is OAuth — the client opens a browser once and there is no key to paste into a config file.
{
"mcpServers": {
"vervekit": {
"url": "https://api.vervekit.com/v1/mcp"
}
}
}https://api.vervekit.com/v1/mcpPer-client setup — Claude Desktop, Cursor, VS Code, ChatGPT — is on the MCP setup page.
Arguments
These are the properties on the tool's inputSchema, so a well-behaved client validates them before the call is made.
| Argument | Type | Example | Description |
|---|---|---|---|
recordRequired | string | _http._tcp.example.com. 3600 IN SRV 10 60 80 server.example.com. | The SRV record string to parse |
What the model gets back
The result carries a structuredContent object matching the tool's declared outputSchema, so a client can read fields without parsing prose. status is "ok" on success and error is null; a null field means the value wasn't available for that input, not that the call failed.
{
"status": "ok",
"error": null,
"data": {
"raw_record": "_http._tcp.example.com. 86400 IN SRV 10 60 80 server.example.com.",
"parsed": {
"name": "_http._tcp.example.com.",
"service": "_http",
"protocol": "tcp",
"domain": "example.com.",
"ttl": 86400,
"class": "IN",
"priority": 10,
"weight": 60,
"port": 80,
"target": "server.example.com"
},
"service_info": {
"name": "HTTP",
"description": "Web service",
"default_port": 80
},
"interpretation": {
"priority_explanation": "Priority level 10 (lower is better)",
"weight_explanation": "Weight 60 for load balancing",
"target_explanation": "Connect to server.example.com:80"
},
"is_valid": true
}
}Fields
| Field | Type | Example | Description |
|---|---|---|---|
raw_record | string | _http._tcp.example.com. 86400 IN SRV 10 60 80 server.example.com. | Original SRV record string provided for parsing |
parsed | object | {…} | |
parsed.name | string | _http._tcp.example.com. | Full SRV record name with trailing dot |
parsed.service | string | _http | Service identifier (e.g., _http, _xmpp, _sip) |
parsed.protocol | string | tcp | Protocol type (e.g., tcp, udp, tls) |
parsed.domain | string | example.com. | Domain name with trailing dot |
parsed.ttl | number | 86400 | Time-to-live value in seconds |
parsed.class | string | IN | DNS class (typically IN for Internet) |
parsed.priorityPremium | number | 10 | Priority value (lower values preferred) |
parsed.weightPremium | number | 60 | Weight for load balancing among same priority |
parsed.portPremium | number | 80 | Port number for service connection |
parsed.targetPremium | string | server.example.com | Target hostname without trailing dot |
service_infoPremium | object | {…} | Information about the recognized service type |
service_info.name | string | HTTP | Human-readable service name (e.g., HTTP, XMPP) |
service_info.description | string | Web service | Service description and use case |
service_info.default_port | number | 80 | Default port for identified service |
interpretationPremium | object | {…} | Human-readable interpretation of SRV record values |
interpretation.priority_explanation | string | Priority level 10 (lower is better) | Human-readable explanation of priority level |
interpretation.weight_explanation | string | Weight 60 for load balancing | Human-readable explanation of weight value |
interpretation.target_explanation | string | Connect to server.example.com:80 | How to connect to target with port |
is_valid | boolean | true | Whether record is validly formatted and parsed |
Failure modes
Errors come back as tool errors with a sentence the model can act on, not a bare status code.
| Status | What it means |
|---|---|
400 / 422 | The arguments didn't validate. The message names the offending one. |
401 | The OAuth session is invalid or expired — reconnect the server. |
403 | Out of credits. Not a bad key — the month's allowance is spent. |
404 | This skill isn't part of VerveKit. Check the catalog. |
429 | Brief rate limit. Retrying after a moment succeeds. |
Other ways to use SRV Record Parser Skill
Set up SRV Record Parser Skill on VerveKit, or reach the same source a different way. Your VerveKit account and credits work on all of them — one key, one balance.
Frequently asked questions
Do I have to tell the agent to use SRVRecordParserSkill?
No. The tool's name and description are in the model's context once the server is connected, so it selects the tool when the question calls for it. Naming it explicitly works too and is useful when you want to force the call.
Does connecting the server expose every tool at once?
Yes — one connection lists the whole VerveKit catalog. Clients with a tool budget can usually filter the list; the credit cost is per call, so an unused tool costs nothing.
What does a call cost?
1 credit each time the tool actually runs. A model that reasons about the tool without calling it costs nothing.
Is there a REST version of this?
Yes — the same source is available as a plain HTTPS endpoint on APIVerve, linked above. Same data, same credits, same account.