MarginGlow AI Signal

Evidence-backed opportunity intelligence for small businesses, built for authorised AI agents.

Should I use this

Quality & Safety

B
Description quality
100%
Schema completeness
53%
Naming quality
80%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Findings (1)

  • LOWTool 'analyse_small_business_opportunities' name length outside 3-30 rangein analyse_small_business_opportunities

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~1,083Tokens (tool definitions)
~3.2 KBTypical response size
Moderate attention impact (0.85% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "signal": {
      "url": "https://www.marginglow.com/mcp"
    }
  }
}

Remote endpoints

https://www.marginglow.com/mcpstreamable-http

What it can do

Tool inventory

Tools (3)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
⚪analyse_small_business_opportunities(businessName, website, country, objective)

Use this when a user wants practical, evidence-based ways for a specific small business to increase revenue, improve margins, reduce costs, strengthen Google visibility, improve conversion or prioritise growth actions. Requires the business name and public website. Returns structured evidence, ranked opportunities, confidence, commercial impact and first actions. Consumes one complimentary or paid MarginGlow AI Signal credit. Do not use for generic business definitions, investment advice, regulated advice or analysis that requires private financial data.

Input Schema

{
  "type": "object",
  "properties": {
    "businessName": {
      "type": "string",
      "minLength": 2,
      "maxLength": 120,
      "description": "The public name of the specific small business to analyse."
    },
    "website": {
      "type": "string",
      "maxLength": 500,
      "description": "The public HTTP or HTTPS website of the business."
    },
    "country": {
      "description": "The business country, when known. Example: Ireland.",
      "type": "string",
      "maxLength": 80
    },
    "objective": {
      "description": "The user's specific commercial goal, such as more weekday bookings, stronger margins or improved Google visibility.",
      "type": "string",
      "maxLength": 500
    }
  },
  "required": [
    "businessName",
    "website"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Output Schema

{
  "type": "object",
  "properties": {
    "transaction": {
      "type": "object",
      "properties": {
        "id": {
          "type": "string"
        },
        "agentId": {
          "type": "string"
        },
        "agentName": {
          "type": "string"
        },
        "replayed": {
          "type": "boolean"
        },
        "allowanceType": {
          "type": "string",
          "enum": [
            "complimentary",
            "paid"
          ]
        },
        "complimentarySignalsRemaining": {
          "type": "number"
        },
        "paidSignalsRemaining": {
          "type": "number"
        }
      },
      "required": [
        "id",
        "agentId",
        "agentName",
        "replayed",
        "allowanceType",
        "complimentarySignalsRemaining",
        "paidSignalsRemaining"
      ],
      "additionalProperties": false
    },
    "signal": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "usage": {
      "type": "object",
      "properties": {
        "totalTokenCount": {
          "type": "number"
        },
        "estimatedAiFootprintKg": {
          "type": "number"
        }
      },
      "required": [
        "totalTokenCount",
        "estimatedAiFootprintKg"
      ],
      "additionalProperties": false
    }
  },
  "required": [
    "transaction",
    "signal"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false
}
🟢check_marginglow_signal_access

Checks the authenticated agent's complimentary and paid MarginGlow AI Signal balances, whether an analysis can run, which allowance will be used next and the latest successfully credited Stripe purchase. This is read-only and does not consume a Signal.

Input Schema

{
  "type": "object",
  "properties": {}
}

Output Schema

{
  "type": "object",
  "properties": {
    "product": {
      "type": "string",
      "const": "MarginGlow AI Signal"
    },
    "agent": {
      "type": "object",
      "properties": {
        "id": {
          "type": "string"
        },
        "name": {
          "type": "string"
        }
      },
      "required": [
        "id",
        "name"
      ],
      "additionalProperties": false
    },
    "access": {
      "type": "object",
      "properties": {
        "status": {
          "type": "string",
          "enum": [
            "ready",
            "credit_required"
          ]
        },
        "canAnalyse": {
          "type": "boolean"
        },
        "nextAllowanceType": {
          "anyOf": [
            {
              "type": "string",
              "enum": [
                "complimentary",
                "paid"
              ]
            },
            {
              "type": "null"
            }
          ]
        }
      },
      "required": [
        "status",
        "canAnalyse",
        "nextAllowanceType"
      ],
      "additionalProperties": false
    },
    "balance": {
      "type": "object",
      "properties": {
        "complimentarySignalsRemaining": {
          "type": "number"
        },
        "paidSignalsRemaining": {
          "type": "number"
        },
        "totalSignalsRemaining": {
          "type": "number"
        }
      },
      "required": [
        "complimentarySignalsRemaining",
        "paidSignalsRemaining",
        "totalSignalsRemaining"
      ],
      "additionalProperties": false
    },
    "latestPurchase": {
      "anyOf": [
        {
          "type": "object",
          "properties": {
            "checkoutSessionId": {
              "type": "string"
            },
            "paymentStatus": {
              "type": "string"
            },
            "amount": {
              "type": "object",
              "properties": {
                "value": {
                  "type": "number"
                },
                "currency": {
                  "type": "string"
                }
              },
              "required": [
                "value",
                "currency"
              ],
              "additionalProperties": false
            },
            "vat": {
              "type": "object",
              "properties": {
                "value": {
                  "type": "number"
                },
                "currency": {
                  "type": "string"
                }
              },
              "required": [
                "value",
                "currency"
              ],
              "additionalProperties": false
            },
            "creditsGranted": {
              "type": "number"
            },
            "appliedAt": {
              "type": "string"
            }
          },
          "required": [
            "checkoutSessionId",
            "paymentStatus",
            "amount",
            "vat",
            "creditsGranted",
            "appliedAt"
          ],
          "additionalProperties": false
        },
        {
          "type": "null"
        }
      ]
    }
  },
  "required": [
    "product",
    "agent",
    "access",
    "balance",
    "latestPurchase"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false
}
⚪purchase_marginglow_signal

Creates a secure Stripe payment link for one MarginGlow AI Signal costing EUR 2, inclusive of applicable tax. Use this when analyse_small_business_opportunities reports that no Signal credits remain. A payment-capable agent may follow the payment instructions automatically when supported. Otherwise, give the secure checkout URL to the user. After payment, retry the original analysis request with the same agent API key and Idempotency-Key.

Input Schema

{
  "type": "object",
  "properties": {}
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded3 tools
verifiedversion not recorded3 tools
verifiedversion not recorded3 tools