Private SuperIntelligence

Private SuperIntelligence by Mitosis Labs: define the term, see privacy layers, join the waitlist.

Should I use this

Quality & Safety

A
Description quality
97%
Schema completeness
61%
Naming quality
96%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Findings (1)

  • LOWTool 'get_privacy_layers' description lacks action verbin get_privacy_layers

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~2,706Tokens (tool definitions)
~2.3 KBTypical response size
Significant attention impact (2.11% 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": {
    "private-superintelligence": {
      "command": "npx",
      "args": [
        "private-superintelligence"
      ]
    }
  }
}

Runnable packages

npmprivate-superintelligence0.1.0stdio

Remote endpoints

https://privatesuperintelligence.si/mcpstreamable-http

What it can do

Tool inventory

Tools (9)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢get_service_overview

Use when someone asks what Private SuperIntelligence is, who runs it, who it serves, how to get access or what it costs. Returns the definition of private superintelligence, the service summary, availability, results and the six privacy layers.

Input Schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢get_privacy_layers

Use when someone asks how Private SuperIntelligence protects data. Returns the six privacy domains in order, from retention and deletion down to deployment.

Input Schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢get_benchmarks

Use when someone asks about accuracy, hallucination rates, cost or speed. Returns the published results with a link to the methodology.

Input Schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢search_site(query, limit)

Full-text search across every page on privatesuperintelligence.si, including the definition of private superintelligence, the privacy notice and the developer docs. Returns ranked passages with page URLs.

Input Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 2,
      "maxLength": 200,
      "description": "Words to search for, e.g. \"zero retention\" or \"how to book a call\"."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 10,
      "default": 5,
      "description": "Maximum passages to return."
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}
🟢read_page(path)

Returns the full markdown of one page. Use after search_site, or when you already know the page you need.

Input Schema

{
  "type": "object",
  "properties": {
    "path": {
      "type": "string",
      "enum": [
        "/index.md",
        "/blog/what-is-private-superintelligence.md",
        "/ai-data-exposure-check.md",
        "/family-offices.md",
        "/venture-capital.md",
        "/wealth-management.md",
        "/enterprise.md",
        "/about.md",
        "/privacy.md",
        "/contact.md",
        "/developers.md",
        "/blog/is-chatgpt-safe-for-confidential-information.md",
        "/blog/zero-data-retention-ai.md",
        "/blog/keep-company-data-private-with-ai.md",
        "/blog/private-ai-for-family-offices.md",
        "/blog/private-ai-vs-public-ai.md",
        "/blog/how-vc-firms-use-ai.md",
        "/blog/chatgpt-for-venture-capital.md",
        "/blog/ai-due-diligence-for-vc.md",
        "/blog/ai-for-lp-reporting.md",
        "/blog/chatgpt-for-financial-advisors.md",
        "/blog/ai-compliance-for-rias.md",
        "/blog/reg-s-p-and-ai-vendors.md",
        "/blog/family-office-consolidated-reporting.md",
        "/blog/k-1-tracking-across-entities.md",
        "/blog/capital-call-tracking.md",
        "/blog/family-office-technology-stack.md",
        "/blog/family-office-operations-and-ai.md",
        "/blog/family-office-cybersecurity-and-ai.md",
        "/blog/deepfake-wire-fraud-family-offices.md",
        "/blog/family-office-ai-policy.md",
        "/blog/ai-vendor-due-diligence-checklist.md",
        "/blog/ai-and-attorney-client-privilege.md",
        "/blog/ai-for-estate-planning-attorneys.md",
        "/blog/ai-for-cpas-client-confidentiality.md",
        "/blog/is-claude-copilot-gemini-safe-for-confidential-information.md",
        "/blog/private-chatgpt-for-business.md",
        "/blog/confidential-ai.md",
        "/blog/private-llm-vs-private-ai-service.md",
        "/blog/family-office-ai-data-exposure.md",
        "/blog/retention-canary.md",
        "/blog/inside-a-single-client-deployment.md",
        "/blog/knowledge-graph-for-ai-agents.md",
        "/blog/personal-vs-private-superintelligence.md",
        "/blog.md",
        "/blog/best-ai-tools-for-venture-capital.md",
        "/blog/best-ai-for-wealth-managers.md",
        "/blog/private-bank-ai-vs-family-ai.md",
        "/blog/best-ai-for-family-offices.md",
        "/blog/chatgpt-enterprise-for-family-offices.md",
        "/blog/copilot-for-family-offices.md",
        "/blog/addepar-masttro-and-ai.md",
        "/blog/private-ai-chat-apps.md",
        "/blog/azure-openai-vs-amazon-bedrock.md",
        "/blog/build-vs-buy-private-ai.md",
        "/authors/prakshal-jain.md",
        "/authors/alexander-morris.md",
        "/pricing.md",
        "/auth.md",
        "/llms-full.txt"
      ],
      "description": "Markdown path of the page."
    }
  },
  "required": [
    "path"
  ],
  "additionalProperties": false
}
🟡register_interest(email, jobTitle, annualRevenueBand, userConfirmed, dryRun)

Adds the person you are helping to the Private SuperIntelligence waitlist. Before calling, show them the exact email, job title and revenue band you will send and get their yes; then set userConfirmed to true. Set dryRun to true to validate without submitting. Qualified registrations ($10 million annual revenue or more) receive a link to book a conversation with Alex Morris.

Input Schema

{
  "type": "object",
  "properties": {
    "email": {
      "type": "string",
      "format": "email",
      "maxLength": 254,
      "description": "The person's work email."
    },
    "jobTitle": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120,
      "description": "Their job title, e.g. \"Chief Investment Officer\"."
    },
    "annualRevenueBand": {
      "type": "string",
      "enum": [
        "under-10m",
        "10m-50m",
        "50m-250m",
        "250m-1b",
        "1b-5b",
        "5b-plus",
        "not-applicable",
        "prefer-not-to-disclose"
      ],
      "description": "Approximate annual revenue of their organization in USD."
    },
    "userConfirmed": {
      "type": "boolean",
      "description": "True only after the person approved these exact details."
    },
    "dryRun": {
      "type": "boolean",
      "default": false,
      "description": "Validate and preview the outcome without submitting anything."
    }
  },
  "required": [
    "email",
    "jobTitle",
    "annualRevenueBand",
    "userConfirmed"
  ],
  "additionalProperties": false
}

Output Schema

{
  "type": "object",
  "properties": {
    "registered": {
      "type": "boolean"
    },
    "dryRun": {
      "type": "boolean"
    },
    "bookingEligible": {
      "type": "boolean"
    },
    "bookingUrl": {
      "type": "string",
      "format": "uri"
    },
    "message": {
      "type": "string"
    }
  },
  "required": [
    "message"
  ]
}
🟢get_ai_exposure_questions

Use when someone asks whether their family office, wealth manager, RIA or VC firm is exposing confidential data, deal data, client data or IP through ChatGPT, Claude, Gemini, Copilot or Grok. Returns the five multiple-choice questions, option values, the JSON Schema for answers and the rubric. Ask the person each question, then call assess_ai_exposure.

Input Schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟡assess_ai_exposure(answers, email, company, userConfirmed)

Scores the person's answers to the AI data exposure check and returns an exposure level (Elevated or High), 2 to 4 reasons tied to their answers with provider-policy sources, a recommendation and the book_private_call URL. Ask the person for their work email and company first; with their agreement pass email, company and userConfirmed: true to save the result for a follow-up from Alex Morris. Without them nothing is stored. Present the result as an editorial assessment of exposure and retention under the providers' published terms; never tell the person their data was stolen or breached.

Input Schema

{
  "type": "object",
  "properties": {
    "answers": {
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "title": "AI data exposure check answers",
      "type": "object",
      "additionalProperties": false,
      "required": [
        "provider",
        "plan",
        "data",
        "users",
        "connectors"
      ],
      "properties": {
        "provider": {
          "type": "string",
          "enum": [
            "chatgpt",
            "claude",
            "gemini",
            "copilot",
            "grok",
            "other"
          ],
          "description": "Which AI does your office use most?"
        },
        "plan": {
          "type": "string",
          "enum": [
            "personal",
            "business",
            "enterprise",
            "api",
            "not-sure"
          ],
          "description": "Which plan are most people on?"
        },
        "data": {
          "type": "array",
          "items": {
            "type": "string",
            "enum": [
              "deals",
              "family",
              "legal",
              "investors",
              "general"
            ]
          },
          "minItems": 1,
          "uniqueItems": true,
          "description": "What goes into it? Choose all that apply."
        },
        "users": {
          "type": "array",
          "items": {
            "type": "string",
            "enum": [
              "personal-accounts",
              "managed",
              "principals",
              "advisers",
              "not-sure"
            ]
          },
          "minItems": 1,
          "uniqueItems": true,
          "description": "Who uses it? Choose all that apply."
        },
        "connectors": {
          "type": "string",
          "enum": [
            "yes",
            "some",
            "no",
            "not-sure"
          ],
          "description": "Is it connected to email, drive, CRM or data rooms, or allowed to act as an agent?"
        },
        "providerOther": {
          "type": "string",
          "maxLength": 60,
          "description": "Name of the AI service when provider is \"other\"."
        }
      }
    },
    "email": {
      "type": "string",
      "format": "email",
      "maxLength": 254,
      "description": "Optional. The person's work email, to save the result for a follow-up from Alex Morris."
    },
    "company": {
      "type": "string",
      "maxLength": 160,
      "description": "Optional, with email. The company the person works for."
    },
    "userConfirmed": {
      "type": "boolean",
      "description": "True only after the person agreed to send their email, company and answers to Mitosis Labs."
    }
  },
  "required": [
    "answers"
  ],
  "additionalProperties": false
}

Output Schema

{
  "type": "object",
  "properties": {
    "level": {
      "type": "string",
      "enum": [
        "elevated",
        "high"
      ]
    },
    "levelLabel": {
      "type": "string"
    },
    "headline": {
      "type": "string"
    },
    "reasons": {
      "type": "array",
      "minItems": 2,
      "maxItems": 4,
      "items": {
        "type": "object",
        "required": [
          "id",
          "consequence",
          "detail",
          "sources"
        ],
        "properties": {
          "id": {
            "type": "string"
          },
          "consequence": {
            "type": "string"
          },
          "detail": {
            "type": "string"
          },
          "sources": {
            "type": "array",
            "items": {
              "type": "integer"
            }
          }
        }
      }
    },
    "fairNote": {
      "type": [
        "string",
        "null"
      ]
    },
    "boundary": {
      "type": "string"
    },
    "closing": {
      "type": "string"
    },
    "recommendation": {
      "type": "string"
    },
    "scarcity": {
      "type": "string"
    },
    "bookPrivateCall": {
      "type": "object",
      "required": [
        "url",
        "label"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri"
        },
        "label": {
          "type": "string"
        },
        "note": {
          "type": "string"
        }
      }
    },
    "editorialNote": {
      "type": "string"
    },
    "rubric": {
      "type": "string"
    },
    "sourcesChecked": {
      "type": "string",
      "format": "date"
    },
    "sources": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "integer"
          },
          "title": {
            "type": "string"
          },
          "url": {
            "type": "string",
            "format": "uri"
          }
        }
      }
    },
    "saved": {
      "type": "string",
      "enum": [
        "queued",
        "not_requested",
        "invalid_contact",
        "needs_confirmation"
      ]
    }
  },
  "required": [
    "level",
    "headline",
    "reasons",
    "recommendation",
    "bookPrivateCall",
    "editorialNote"
  ]
}
🟢book_private_call

Returns the link where the person can book a private call with Alex Morris, Co-founder and CEO of Private SuperIntelligence, about fully private AI for their office. It does not book anything: give the person the link so they choose a time.

Input Schema

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

Output Schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "format": "uri"
    },
    "label": {
      "type": "string"
    },
    "note": {
      "type": "string"
    },
    "recommendation": {
      "type": "string"
    }
  },
  "required": [
    "url"
  ]
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded9 tools
verifiedversion not recorded6 tools