SPF Grounding Data for AI Agents
The tool
Ground agents in real-time SPF record data so email-security answers reflect live DNS truth and authorized senders, not assumptions.
Once your client is connected to the VerveContext MCP server, this appears in its tool list as SPFGroundingDataforAIAgents. 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": "SPFGroundingDataforAIAgents",
"arguments": {
"domain": "myspace.com"
}
}What that looks like in a conversation
You don't name the tool — the model picks it. Asking about myspace.com in the terms this source covers is enough for it to reach for SPFGroundingDataforAIAgents on its own.
Connecting
One server URL covers every source 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": {
"vervecontext": {
"url": "https://api.vervecontext.com/v1/mcp"
}
}
}https://api.vervecontext.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 |
|---|---|---|---|
domainRequired | string | myspace.com | The domain to validate the SPF record for |
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": {
"host": "myspace.com",
"has_spf_record": true,
"dns_lookups_num": 9,
"spf_record": "v=spf1 mx ip4:63.208.226.34 ip4:204.16.32.0/22 ip4:67.134.143.0/24 ip4:216.205.243.0/24 ip4:34.85.156.5/32 ip4:35.245.108.108/32 ip4:34.86.129.193/32 ip4:34.86.134.94/32 ip4:34.85.222.234/32 ip4:34.86.176.234/32 ip4:34.86.125.212/32 ip4:34.85.224.60/32 ip4:34.86.160.49/32 ip4:35.245.64.166/32 ip4:35.188.226.11/32 ip4:34.86.208.228/32 ip4:34.85.216.144/32 ip4:35.221.22.153/32 ip4:34.86.137.108/32 ip4:34.86.51.35/32 ip4:34.150.221.40/32 ip4:34.85.216.70/32 ip4:34.86.37.191/32 ip4:34.85.214.215/32 ip4:35.236.234.82/32 ip4:34.86.161.241/32 ip4:216.32.181.16 ip4:216.178.32.0/20 ip4:168.235.224.0/24 include:_netblocks.mimecast.com -all",
"spf_records_list": [
{
"origin": "myspace.com",
"record": "v=spf1 mx ip4:63.208.226.34 ip4:204.16.32.0/22 ip4:67.134.143.0/24 ip4:216.205.243.0/24 ip4:34.85.156.5/32 ip4:35.245.108.108/32 ip4:34.86.129.193/32 ip4:34.86.134.94/32 ip4:34.85.222.234/32 ip4:34.86.176.234/32 ip4:34.86.125.212/32 ip4:34.85.224.60/32 ip4:34.86.160.49/32 ip4:35.245.64.166/32 ip4:35.188.226.11/32 ip4:34.86.208.228/32 ip4:34.85.216.144/32 ip4:35.221.22.153/32 ip4:34.86.137.108/32 ip4:34.86.51.35/32 ip4:34.150.221.40/32 ip4:34.85.216.70/32 ip4:34.86.37.191/32 ip4:34.85.214.215/32 ip4:35.236.234.82/32 ip4:34.86.161.241/32 ip4:216.32.181.16 ip4:216.178.32.0/20 ip4:168.235.224.0/24 include:_netblocks.mimecast.com -all",
"chars_num": 637,
"use_macro": false,
"domains": [
"_netblocks.mimecast.com"
],
"authorized_ips": {
"ipv4": [
"63.208.226.34",
"204.16.32.0/22",
"67.134.143.0/24",
"216.205.243.0/24",
"34.85.156.5/32",
"35.245.108.108/32",
"34.86.129.193/32",
"34.86.134.94/32",
"34.85.222.234/32",
"34.86.176.234/32",
"34.86.125.212/32",
"34.85.224.60/32",
"34.86.160.49/32",
"35.245.64.166/32",
"35.188.226.11/32",
"34.86.208.228/32",
"34.85.216.144/32",
"35.221.22.153/32",
"34.86.137.108/32",
"34.86.51.35/32",
"34.150.221.40/32",
"34.85.216.70/32",
"34.86.37.191/32",
"34.85.214.215/32",
"35.236.234.82/32",
"34.86.161.241/32",
"216.32.181.16",
"216.178.32.0/20",
"168.235.224.0/24"
]
}
},
{
"origin": "_netblocks.mimecast.com",
"record": "v=spf1 include:eu._netblocks.mimecast.com include:us._netblocks.mimecast.com include:za._netblocks.mimecast.com include:de._netblocks.mimecast.com include:au._netblocks.mimecast.com include:ca._netblocks.mimecast.com include:usb._netblocks.mimecast.com ~all",
"chars_num": 257,
"use_macro": false,
"domains": [
"eu._netblocks.mimecast.com",
"us._netblocks.mimecast.com",
"za._netblocks.mimecast.com",Fields
| Field | Type | Example | Description |
|---|---|---|---|
host | string | The domain name being validated | |
has_spf_record | boolean | Whether the domain has SPF record | |
dns_lookups_numPremium | number | Total number of DNS lookups performed | |
spf_record | string | The complete SPF record string | |
spf_records_listPremium | array[9] | List of SPF records with detailed parsing | |
└ spf_records_list.0.originPremium | string | Domain origin of SPF record | |
└ spf_records_list.0.recordPremium | string | Full SPF record content | |
└ spf_records_list.0.chars_numPremium | number | Character count of SPF record | |
└ spf_records_list.0.use_macroPremium | boolean | Whether record uses macros | |
└ spf_records_list.0.domainsPremium | array | Domains referenced in SPF record | |
└ spf_records_list.0.authorized_ipsPremium | object | All IP addresses authorized by SPF | |
└ spf_records_list.0.authorized_ips.ipv4Premium | array | IPv4 addresses authorized to send mail | |
domains_extractedPremium | array | All domains found in SPF chain | |
authorized_ipsPremium | object | All IP addresses authorized by SPF | |
└ authorized_ips.ipv4Premium | array | All IPv4 addresses authorized by SPF | |
└ authorized_ips.ipv6Premium | array | All IPv6 addresses authorized by SPF | |
issues_foundPremium | array | List of SPF validation issues | |
spf_valid | boolean | Whether SPF record is valid | |
has_issues | boolean | Whether validation found issues | |
macros_foundPremium | boolean | Whether SPF record uses macros | |
ip_pass | boolean | Whether IP passes SPF check | |
elapsed_msPremium | number | Validation processing time in milliseconds | |
all_qualifier | string | The qualifier on the SPF 'all' mechanism: fail (-all, strict), softfail (~all), neutral (?all) or pass (+all, authorizes any sender). Null when the record has no all mechanism (e.g. defers via redirect) | |
risk_scorePremium | number | Composite 0-100 email-spoofing risk based on the SPF enforcement qualifier and DNS-lookup limit — higher means the domain is more easily spoofed (no SPF or +all scores high; -all scores low) | |
risk_levelPremium | string | Risk band derived from the score: low, medium or high |
Why ground on it
A model can produce something that looks like this answer from its training data, and be confidently out of date or simply wrong. This source returns the current value with a shape you can check, which is the difference between an answer you can cite and one you have to hedge.
Point an evaluation at host: it is the field most worth pinning a claim to, and it is either present and current or absent — never plausibly invented.
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 source isn't part of VerveContext. Check the catalog. |
429 | Brief rate limit. Retrying after a moment succeeds. |
Other ways to use SPF Grounding Data for AI Agents
Set up SPF Grounding Data for AI Agents on VerveContext, or reach the same source a different way. Your VerveContext account and credits work on all of them — one key, one balance.
Frequently asked questions
Do I have to tell the agent to use SPFGroundingDataforAIAgents?
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 VerveContext 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?
5 credits 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.