AI Business System Advisor

by tenkai2018 · remote · local (npm) · no sign-in to list tools · v0.1.10 · published by GitHub user tenkai2018

Find the safest first AI workflow before investing in AI agents or automation.

Changes · 8

Compare Registry entry

9 tools: 8 change things and 1 only read.

Scanned Oct 21, 2026

Deletes or cancels0Claude Code: deny
Can't be undone0Claude Code: ask
Changes things8Claude Code: ask: see these tools
Only reads1Claude Code: allow: see these tools

3 checks matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http ai-business-system-advisor https://mcp.prodxsolution.com/ai-business-system-advisor/mcp

Findings

Matches of fixed checks, with the text they matched.

3 warn

Warnevaluate_ai_opportunities
The server marks "evaluate_ai_opportunities" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "evaluate_ai_opportunities" says "evaluate": a word for a change.
What this check looks for
Warngenerate_mini_report
The server marks "generate_mini_report" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "generate_mini_report" says "generate": a word for a change.
What this check looks for
Warnexport_intake_packet
The server marks "export_intake_packet" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "create": a word for a change.
What this check looks for

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

9 tools

Changes things 8Creates or changes something that can be changed back.Claude Code: ask

assess_trust_control_risksReviews a proposed AI workflow for human review needs, data boundaries, quality controls, escalation triggers, unsafe automation risks, and confidence.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
Reviews a proposed AI workflow for human review needs, data boundaries, quality controls, escalation triggers, unsafe automation risks, and confidence.
Annotations the server declares
- title: Assess Trust And Control Risks
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
evaluate_ai_opportunitiesEvaluates candidate AI workflow ideas for business value, implementation readiness, repeatability, trust/control risk, warnings, and missing information.1 finding
Why it is in this group
- The name "evaluate_ai_opportunities" says "evaluate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "evaluate_ai_opportunities" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "evaluate_ai_opportunities" says "evaluate": a word for a change.
  What this check looks for
Description, as the server wrote it
Evaluates candidate AI workflow ideas for business value, implementation readiness, repeatability, trust/control risk, warnings, and missing information.
Annotations the server declares
- title: Evaluate AI Opportunities
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
export_intake_packetCreates a structured public-safe markdown and JSON intake packet with business context, findings, risks, recommended workflow, missing information, and confidence.1 finding
Why it is in this group
- The description's first verb is "create": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "export_intake_packet" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "create": a word for a change.
  What this check looks for
Description, as the server wrote it
Creates a structured public-safe markdown and JSON intake packet with business context, findings, risks, recommended workflow, missing information, and confidence.
Annotations the server declares
- title: Export Intake Packet
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
generate_mini_reportGenerates a public-safe mini business system review with snapshot, bottlenecks, opportunities, risks, first workflow, next step, missing information, and confidence.1 finding
Why it is in this group
- The name "generate_mini_report" says "generate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "generate_mini_report" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "generate_mini_report" says "generate": a word for a change.
  What this check looks for
Description, as the server wrote it
Generates a public-safe mini business system review with snapshot, bottlenecks, opportunities, risks, first workflow, next step, missing information, and confidence.
Annotations the server declares
- title: Generate Mini Report
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
identify_bottlenecksIdentifies likely revenue, operations, customer experience, and trust/control bottlenecks from the supplied business context and returns a public-safe summary.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
Identifies likely revenue, operations, customer experience, and trust/control bottlenecks from the supplied business context and returns a public-safe summary.
Annotations the server declares
- title: Identify Bottlenecks
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
map_customer_touchpointsMaps customer-facing workflow stages, trust-sensitive moments, automation-safe areas, human-critical areas, missing information, and confidence.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
Maps customer-facing workflow stages, trust-sensitive moments, automation-safe areas, human-critical areas, missing information, and confidence.
Annotations the server declares
- title: Map Customer Touchpoints
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
recommend_first_workflowRecommends the safest narrow AI-human workflow to implement first, including roles, review rules, escalation rules, success metrics, and missing information.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
Recommends the safest narrow AI-human workflow to implement first, including roles, review rules, escalation rules, success metrics, and missing information.
Annotations the server declares
- title: Recommend First Workflow
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
recommend_next_stepRecommends a practical next-step category based on business goal, workflow complexity, implementation readiness, risk level, preferences, and missing information.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
Recommends a practical next-step category based on business goal, workflow complexity, implementation readiness, risk level, preferences, and missing information.
Annotations the server declares
- title: Recommend Next Step
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false

Only reads 1Looks things up and changes nothing.Claude Code: allow

analyze_business_contextSummarizes the supplied business context, including customer, offer, workflow, goals, constraints, readiness signals, missing information, and confidence.No findings
Why it is in this group
- The name "analyze_business_context" says "analyze": a word for reading.
Description, as the server wrote it
Summarizes the supplied business context, including customer, offer, workflow, goals, constraints, readiness signals, missing information, and confidence.
Annotations the server declares
- title: Analyze Business Context
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 0.1.10. Values in angle brackets are yours to fill in.

claude mcp add --transport http ai-business-system-advisor https://mcp.prodxsolution.com/ai-business-system-advisor/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__ai-business-system-advisor__analyze_business_context"
    ],
    "ask": [
      "mcp__ai-business-system-advisor__map_customer_touchpoints",
      "mcp__ai-business-system-advisor__identify_bottlenecks",
      "mcp__ai-business-system-advisor__evaluate_ai_opportunities",
      "mcp__ai-business-system-advisor__assess_trust_control_risks",
      "mcp__ai-business-system-advisor__recommend_first_workflow",
      "mcp__ai-business-system-advisor__generate_mini_report",
      "mcp__ai-business-system-advisor__recommend_next_step",
      "mcp__ai-business-system-advisor__export_intake_packet"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as ai-business-system-advisor. Review it before you use it.

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/io.github.tenkai2018/ai-business-system-advisor-mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Anlyon alternative

8 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Compare with other servers for the same product.

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:50 UTC.

For agents: Markdown · JSON · report this listing