MCP server for Rubiscout — AI-powered email header analysis for phishing, spoofing, and BEC detection. Exposes Rubiscout's forensic analysis as tools for Claude Code, Claude Desktop, Cursor, and any other MCP-compatible agent.
npx rubiscout-mcpOr install globally:
npm install -g rubiscout-mcpRelated MCP server: mailX tools
Get a free API key at rubiscout.com/dashboard, then add to your MCP client config (e.g. ~/.claude/settings.json or Claude Desktop config):
{
"mcpServers": {
"rubiscout": {
"command": "npx",
"args": ["-y", "rubiscout-mcp"],
"env": {
"RUBISCOUT_API_KEY": "rbs_live_..."
}
}
}
}Alternatively, set RUBISCOUT_API_KEY as a system environment variable and omit the env block.
Tool | Description |
| Submit a raw email string for full forensic analysis. Returns verdict, risk score, authentication results (SPF/DKIM/DMARC/ARC), IP reputation, routing trace, and recommendations. |
| Retrieve a previously stored analysis by UUID. |
| List recent analyses, optionally filtered by risk score. |
Once configured, ask your agent directly:
"Analyze this email for me and tell me if it's a phishing attempt" [paste email]
"Get my last 5 analyses and summarize the threat patterns"
"Analyze all .eml files in this directory and flag any Critical or High risk ones"
npm install
npm run build
npm startdocker build -t rubiscout-mcp .
docker run -i -e RUBISCOUT_API_KEY=rbs_live_... rubiscout-mcpMIT
Analyze an email for phishing, spoofing, and authentication failures. Accepts raw email headers or a full RFC 2822 email (headers + body). Returns a full forensic verdict with SPF/DKIM/DMARC results, IP reputation, routing path, risk score, and recommendations.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | Raw email headers or full RFC 2822 email string |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries the full burden. It discloses the output (forensic verdict with SPF/DKIM/DMARC, IP reputation, etc.) and input format, but does not mention side effects, storage, auth requirements, or statelessness. This leaves some behavioral gaps.
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?
Description is concise (two sentences), front-loads the purpose, and every sentence adds value. 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?
With one parameter, no output schema, and no annotations, the description covers input, process, and output adequately. It lacks prerequisites or error conditions but is complete enough for the tool's complexity.
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 100% with one parameter fully described. The description adds meaning by clarifying that the 'email' parameter accepts raw headers or full RFC 2822 email, which goes beyond the schema's minimal description.
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?
Description clearly states the tool's purpose: analyzing emails for phishing, spoofing, and authentication failures. It specifies acceptable input formats (raw headers or full RFC 2822) and distinguishes from sibling tools (get_analysis, list_analyses) by focusing on performing a new analysis rather than retrieving existing ones.
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 using this tool when you have an email to analyze, but it does not explicitly state when to use it versus alternatives. No exclusions or when-not-to-use guidance is provided, leaving the agent to infer from sibling names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve a previously stored Rubiscout analysis by its UUID. Returns the full analysis result including verdict, risk score, authentication results, IP reputation, and recommendations.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Analysis UUID returned by analyze_email |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description states the tool is read-only and returns specific fields (verdict, risk score, etc.). However, it does not disclose error behavior (e.g., missing UUID), rate limits, or authorization requirements. Without annotations, more detail on limitations would be beneficial.
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, well-formed sentence that front-loads the verb and resource. It covers the purpose, key input, and return value without extraneous 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 simple retrieval tool with one parameter and no output schema, the description fairly covers the return values (verdict, risk score, etc.). It lacks error handling details but is otherwise sufficient.
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 schema covers 100% of parameters with a description. The tool description adds no new meaning beyond restating the UUID origin. Per guidelines, high schema coverage leads to baseline 3.
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 clearly identifies the action (Retrieve), the resource (Rubiscout analysis), and the method (by UUID). It distinguishes itself from sibling tools like analyze_email (which creates) and list_analyses (which lists).
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 when to use the tool (to fetch a specific analysis). However, it does not explicitly state when not to use it or mention prerequisites like needing a UUID from analyze_email, although that context is present in the schema.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List recent Rubiscout analyses, ordered by most recent first. Optionally filter by risk score.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page number (default 1) | |
| per_page | No | Results per page (default 20, max 100) | |
| risk_score | No | Filter by risk score |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description states ordering and filter behavior but omits pagination details (default page, next page handling) and safety (read-only). With no annotations, more behavioral disclosure would be beneficial.
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?
Two concise sentences, front-loaded with action and key ordering detail. No redundant or extraneous 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?
Adequately covers purpose, ordering, and filter for a simple list tool. Missing return format or pagination behavior details, but schema covers parameter constraints. Output schema absent, but completeness is acceptable given tool simplicity.
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 descriptions fully cover all three parameters. Description only repeats risk_score filter, adding no additional meaning beyond schema. Baseline 3 as schema coverage is 100%.
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?
Clear verb 'list' specifies action, resource 'analyses' with ordering 'by most recent first' and optional filter. Distinguishes from sibling tools 'analyze_email' (create) and 'get_analysis' (single retrieval).
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?
No explicit when-to-use or when-not-to-use guidance. Sibling names imply context but description lacks directives on comparing with alternatives or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool targets a distinct operation: analyzing a new email, retrieving a specific analysis by UUID, and listing recent analyses. There is no functional overlap.
All tool names follow a consistent verb_noun pattern with lowercase and underscores (analyze_email, get_analysis, list_analyses), making them predictable.
With 3 tools, the server is scoped tightly to email analysis. While minimal, it covers the primary use cases without unnecessary bloat.
The server provides core CRUD-like operations (create, read, list) for email analyses. Missing update and delete are minor gaps, but the essential workflow for analysis is complete.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Email safety MCP server. Detects phishing, prompt injection, CEO fraud for AI agents.
Email infrastructure for AI agents — send, receive, search, and reply to email over MCP.
Email posture for any domain: can it receive mail, can it be spoofed? MX, SPF and DMARC.
Remote MCP server: 19 domain-hygiene and email-auth tools (DNS, SPF, DMARC, DKIM, TLS).
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/raj-rubicon/rubiscout-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
