Skip to main content
Glama

Email header analyser

hopi_email_header_analyser
Read-onlyIdempotent

Analyse raw email headers (the full source from Show original or View message source) without any network call: lists every Received hop in delivery order with host, IP, time and delay between hops; extracts From, Reply-To, Return-Path, Subject, Date, Message-ID and mailer; reads SPF, DKIM and DMARC results from Authentication-Results, ARC-Authentication-Results and Received-SPF with the domain each was checked for; and flags warning signs such as Reply-To on a different domain, SPF or DMARC failure, no DKIM, a display name that pretends to be an address or brand, a first hop from a home connection, clock skew and a mismatched Message-ID domain. Returns a verdict (consistent, caution or suspicious). It does not query DNS, so it reports what the receiving servers recorded rather than re-checking it. Source: https://hopi.co.uk/email-header-analyser/

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "headers": "<headers>"
    },
    "name": "hopi_email_header_analyser"
  }
}

Input Schema

NameRequiredDescriptionDefault
headersYesThe raw message headers, pasted as text

Output Schema

NameRequiredDescriptionDefault
toNo
authNo
bulkNo
dateNo
fromNo
hopsNo
mailerNo
dateIsoNo
replyToNo
subjectNo
summaryYes
verdictNo
hopCountNo
warningsNo
messageIdNo
authServerNo
authSourceNo
returnPathNo
source_urlYesThe tool's page on hopi.co.uk (cite or open to check the figure)
headerCountNo
originatingIpNo
dkimSignaturesNo
transitSecondsNo
messageIdDomainNo
returnPathDomainNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed12 schema fields changed
    • changedOutput schema / properties / authServer / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / authSource / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / date / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / dateIso / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / mailer / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / messageId / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / messageIdDomain / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / replyTo / type
      Previous value: -"object"New value: +[
      +  "object",
      +  "null"
      +]
    • changedOutput schema / properties / returnPath / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / returnPathDomain / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / to / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / transitSeconds / type
      Previous value: -"number"New value: +[
      +  "number",
      +  "null"
      +]
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": true,
      +  "properties": {
      +    "auth": {
      +      "type": "object"
      +    },
      +    "authServer": {
      +      "type": "string"
      +    },
      +    "authSource": {
      +      "type": "string"
      +    },
      +    "bulk": {
      +      "type": "boolean"
      +    },
      +    "date": {
      +      "type": "string"
      +    },
      +    "dateIso": {
      +      "type": "string"
      +    },
      +    "dkimSignatures": {
      +      "type": "array"
      +    },
      +    "from": {
      +      "type": "object"
      +    },
      +    "headerCount": {
      +      "type": "number"
      +    },
      +    "hopCount": {
      +      "type": "number"
      +    },
      +    "hops": {
      +      "type": "array"
      +    },
      +    "mailer": {
      +      "type": "string"
      +    },
      +    "messageId": {
      +      "type": "string"
      +    },
      +    "messageIdDomain": {
      +      "type": "string"
      +    },
      +    "originatingIp": {},
      +    "replyTo": {
      +      "type": "object"
      +    },
      +    "returnPath": {
      +      "type": "string"
      +    },
      +    "returnPathDomain": {
      +      "type": "string"
      +    },
      +    "source_url": {
      +      "description": "The tool's page on hopi.co.uk (cite or open to check the figure)",
      +      "type": "string"
      +    },
      +    "subject": {
      +      "type": "string"
      +    },
      +    "summary": {
      +      "type": "string"
      +    },
      +    "to": {
      +      "type": "string"
      +    },
      +    "transitSeconds": {
      +      "type": "number"
      +    },
      +    "verdict": {
      +      "type": "string"
      +    },
      +    "warnings": {
      +      "type": "array"
      +    }
      +  },
      +  "required": [
      +    "source_url",
      +    "summary"
      +  ],
      +  "type": "object"
      +}
  3. Added

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely new behavioural facts: it performs no network access and does not re-verify DNS, so it reports what receiving servers recorded. It also discloses the output verdict vocabulary (consistent, caution, suspicious), which the annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the verb and the no-network guarantee, then enumerates outputs in a single dense sentence. Every clause carries information, though the long serial list of fields and warning signs borders on over-specification given an output schema is present.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers the one risky input requirement (full raw source), the scope limitation (no DNS), and the shape of the result including verdict categories, while the output schema handles return-value detail. A caveat about malformed or partial headers being tolerated would make it complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single required 'headers' string, so the baseline is 3; the description earns one more by clarifying that the expected payload is the *full raw source* rather than a trimmed header block, which the schema's 'pasted as text' wording does not fully pin down.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Analyse raw email headers') and then enumerates exactly what it produces: Received hops with delays, key headers, SPF/DKIM/DMARC results, warning flags, and a verdict. Nothing in the large sibling list does anything comparable, so an agent can distinguish it immediately.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives the concrete precondition for use — you must paste 'the full source from Show original or View message source' — and explicitly bounds the tool's scope ('without any network call', 'does not query DNS'). It never names an alternative or says when not to reach for it, but no plausible sibling alternative exists in this toolset.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources