# DemiSignal

> Check a domain's DMARC, SPF, DKIM, MX, BIMI and MTA-STS records. Generate SPF and DMARC records.

- name: com.demisignal/mcp
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 82/100 flags: no-repository
- quality: 81/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.demisignal%2Fmcp
- tools: https://api.protogrid.dev/v1/servers/com.demisignal%2Fmcp/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "demisignal": {
      "type": "http",
      "url": "https://demisignal.com/mcp?utm_source=mcp-registry"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 98
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-96% +updated-6d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 81/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 3 of 3 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: check_domain (destructiveHint); generate_spf_record (destructiveHint, openWorldHint); generate_dmarc_record (destructiveHint, openWorldHint)
- pass `tools.token_cost`: about 776 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 5 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 3, about 776 tokens to load them all
- tool set hash: c93c7c8758c7020db350a09dc716fe62
- badge: [![protogrid quality](https://protogrid.dev/badge/com.demisignal/mcp.svg)](https://protogrid.dev/servers/com.demisignal/mcp)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://demisignal.com/mcp?utm_source=mcp-registry (streamable-http, auth none, reachable true, uptime30d 0.95652175)

## Packages

_none_

## Tools (3)

- `check_domain`: Look up a domain's live DNS and grade its email authentication: DMARC, SPF, DKIM (common selectors), MX, BIMI and MTA-STS. Returns each record, its status and the issues found, with a guide link per issue. A domain checked in the last few minutes is answered from that check.
- `generate_dmarc_record`: Build a DMARC TXT record and the host to publish it at, from a policy and the addresses that should receive aggregate reports. Notes what the record does not cover yet. Computes from the arguments only; nothing is looked up or stored.
- `generate_spf_record`: Build an SPF TXT record from the services and servers that send email for a domain, with an estimate of the DNS lookups it uses against SPF's limit of 10. Computes from the arguments only; nothing is looked up or stored.