Moltbound MCP

An official MCP server providing AI agents with access to Moltbound's sandbox environment for generating simulated insurance and utility quotes across 20 US services. It supports session management, requirement gathering, quote retrieval, and simulated consent flows using fictitious data.

Visit Moltbound

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by Moltbound

MCP endpoint (Streamable HTTP)

https://moltbound.dev/kapi/mcp

Vendor documentation

What you can do with it

Generate simulated quotes for car, pet, or home insurance
Retrieve required underwriting fields for specific services
Simulate the consent and checkout approval flow
List available services in the sandbox catalog

Source and maintenance

Vendor evidenceRegistry 1.0.1

mcp-registry: dev.moltbound/sandbox@1.0.1 Project website

Protocol and capabilities

Server: moltbound-sandbox 1.0.0
MCP protocol: 2025-03-26
Tools: 17 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

TEST ONLY. Moltbound is a sandbox. Every partner is fictional and every quote is simulated: these are not real quotes, not financial advice, and nothing will be bought for real. Moltbound is not an insurer or broker. United States only. SANDBOX: use fictitious data only. Do not enter real personal details.

Tools

17 advertised

moltbound_list_services

Advertised by the server during the last successful anonymous check.

List all 20 services across 9 categories with partner counts, descriptions, and required fields. Answers 'What sort of quotes can you provide?'. SANDBOX: use fictitious data only. Do not enter real personal details.

moltbound_list_services input schema

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

moltbound_start_session

Advertised by the server during the last successful anonymous check.

Start an anonymous TEST-ONLY quote session. TEST ONLY. Moltbound is a sandbox. Every partner is fictional and every quote is simulated: these are not real quotes, not financial advice, and nothing will be bought for real. Moltbound is not an insurer or broker. United States only. SANDBOX: use fictitious data only. Do not enter real personal details. Relay the notice to your human, then continue. SANDBOX: use fictitious data only. Do not enter real personal details.

moltbound_start_session input schema

{
  "type": "object",
  "required": [
    "jurisdiction"
  ],
  "properties": {
    "agent_name": {
      "type": "string"
    },
    "service_id": {
      "type": "string",
      "default": "car_insurance",
      "description": "Any of the 20 service IDs, or '*' for all 20 services"
    },
    "jurisdiction": {
      "enum": [
        "US"
      ],
      "default": "US"
    }
  }
}

moltbound_requirements

Advertised by the server during the last successful anonymous check.

Fields to ask the human for a service. SANDBOX: use fictitious data only. Do not enter real personal details. Pass service_id to inspect any of the 20 services.

moltbound_requirements input schema

{
  "type": "object",
  "required": [
    "session_token"
  ],
  "properties": {
    "service_id": {
      "type": "string",
      "description": "Optional service_id override (e.g. home_building, electricity)"
    },
    "session_token": {
      "type": "string",
      "description": "From moltbound_start_session or moltbound_human_sim_verify"
    }
  }
}

moltbound_get_quotes

Advertised by the server during the last successful anonymous check.

Request simulated quotes (cheapest first) with the human's answers. Pass parameters directly for any of the 20 services. SANDBOX: use fictitious data only. Do not enter real personal details.

moltbound_get_quotes input schema

{
  "type": "object",
  "required": [
    "session_token",
    "service_id"
  ],
  "properties": {
    "service_id": {
      "enum": [
        "car_insurance",
        "dog_pet_insurance",
        "home_building",
        "contents",
        "travel",
        "life_quote_only",
        "gas_energy",
        "electricity",
        "broadband_internet",
        "mobile_plan",
        "roadside",
        "pet_boarding",
        "health_insurance",
        "motorcycle_insurance",
        "sme_business_insurance",
        "cyber_insurance",
        "dental_vision",
        "water_utility",
        "home_security",
        "gym_membership"
      ],
      "type": "string",
      "description": "Which of the 20 US services to quote, e.g. car_insurance, home_building, dog_pet_insurance, travel, electricity."
    },
    "auto_default": {
      "type": "boolean",
      "default": false,
      "description": "Set true to fill missing fields with safe sandbox defaults. Car insurance driver fields (numberOfDrivers, driverAges) are filled only when both are missing; rejected if only one is missing."
    },
    "risk_profile": {
      "type": "object",
      "description": "The service's fields as key/value pairs (see moltbound_requirements). They may also be passed at the top level.",
      "additionalProperties": true
    },
    "session_token": {
      "type": "string",
      "description": "Session token from moltbound_start_session"
    }
  },
  "description": "Request simulated quotes with the human's answers for one service. SANDBOX: use fictitious data only. Do not enter real personal details.",
  "additionalProperties": true
}

moltbound_quote_status

Advertised by the server during the last successful anonymous check.

Poll a quote job until complete, then show the human the quotes. Optional sort/filter: sort (price_asc|price_desc|deductible_asc|deductible_desc|cover_desc|partner), partner, cover (basic|standard|comprehensive, comma list), max_deductible, max_price, limit. The human picks which quote to continue with. SANDBOX: use fictitious data only. Do not enter real personal details.

moltbound_quote_status input schema

{
  "type": "object",
  "required": [
    "session_token",
    "job_id"
  ],
  "properties": {
    "sort": {
      "type": "string"
    },
    "cover": {
      "type": "string"
    },
    "limit": {
      "type": "integer"
    },
    "job_id": {
      "type": "string"
    },
    "partner": {
      "type": "string"
    },
    "max_price": {
      "type": "number"
    },
    "session_token": {
      "type": "string",
      "description": "From moltbound_start_session or moltbound_human_sim_verify"
    },
    "max_deductible": {
      "type": "number"
    }
  }
}

moltbound_consent_link

Advertised by the server during the last successful anonymous check.

Give the human a code to link you so they can approve a (fictional) purchase with their passkey. SANDBOX: use fictitious data only. Do not enter real personal details.

moltbound_consent_link input schema

{
  "type": "object",
  "required": [
    "session_token"
  ],
  "properties": {
    "max_price": {
      "type": "number"
    },
    "service_id": {
      "type": "string"
    },
    "jurisdiction": {
      "enum": [
        "US"
      ],
      "default": "US"
    },
    "session_token": {
      "type": "string",
      "description": "From moltbound_start_session or moltbound_human_sim_verify"
    }
  }
}

moltbound_complete_purchase

Advertised by the server during the last successful anonymous check.

After the human approved on Moltbound's website (or via moltbound_human_sim_approve): complete the fictional purchase within 15 minutes. Bound to that exact quote and agent: repeating the call for the same approved quote is idempotent (returns the existing purchase_id), while reusing an approval for any other quote returns consent_used (another agent or session gets not_found, as it cannot see that approval) and an expired approval returns consent_expired. SANDBOX: use fictitious data only. Do not enter real personal details.

moltbound_complete_purchase input schema

{
  "type": "object",
  "required": [
    "session_token",
    "consent_request_id"
  ],
  "properties": {
    "session_token": {
      "type": "string",
      "description": "From moltbound_start_session or moltbound_human_sim_verify"
    },
    "consent_request_id": {
      "type": "string"
    }
  }
}

moltbound_purchase_status

Advertised by the server during the last successful anonymous check.

Poll the status of a fictional purchase by purchase_id until 'bound'. Returns partner's policy_number. SANDBOX: use fictitious data only. Do not enter real personal details.

moltbound_purchase_status input schema

{
  "type": "object",
  "required": [
    "session_token",
    "purchase_id"
  ],
  "properties": {
    "purchase_id": {
      "type": "string"
    },
    "session_token": {
      "type": "string",
      "description": "From moltbound_start_session or moltbound_human_sim_verify"
    }
  }
}

moltbound_approval_request

Advertised by the server during the last successful anonymous check.

After the human linked you and you quoted: ask them to approve one quote. SANDBOX: use fictitious data only. Do not enter real personal details.

moltbound_approval_request input schema

{
  "type": "object",
  "required": [
    "session_token",
    "job_id",
    "bid_id"
  ],
  "properties": {
    "bid_id": {
      "type": "string"
    },
    "job_id": {
      "type": "string"
    },
    "session_token": {
      "type": "string",
      "description": "From moltbound_start_session or moltbound_human_sim_verify"
    }
  }
}

moltbound_quick_quote

Advertised by the server during the last successful anonymous check.

One-shot quotes across any service. Accepts a natural language prompt, partial fields, or a full risk profile. When auto_default is true, missing fields are populated with safe sandbox defaults (car insurance driver fields numberOfDrivers and driverAges are filled only when both are missing; rejected if only one is missing). Pass grant_token for Protected Mode. SANDBOX: use fictitious data only. Do not enter real personal details.

moltbound_quick_quote input schema

{
  "type": "object",
  "properties": {
    "state": {
      "type": "string",
      "description": "Two-letter US state code, e.g. TX"
    },
    "prompt": {
      "type": "string",
      "description": "Plain-language request, e.g. 'car insurance for a 2019 Honda Civic in Austin TX 78701'. No names or ID numbers."
    },
    "service_id": {
      "enum": [
        "car_insurance",
        "dog_pet_insurance",
        "home_building",
        "contents",
        "travel",
        "life_quote_only",
        "gas_energy",
        "electricity",
        "broadband_internet",
        "mobile_plan",
        "roadside",
        "pet_boarding",
        "health_insurance",
        "motorcycle_insurance",
        "sme_business_insurance",
        "cyber_insurance",
        "dental_vision",
        "water_utility",
        "home_security",
        "gym_membership"
      ],
      "type": "string",
      "description": "Which of the 20 US services to quote, e.g. car_insurance, home_building, dog_pet_insurance, travel, electricity."
    },
    "grant_token": {
      "type": "string",
      "description": "Optional grant token for Protected Mode"
    },
    "auto_default": {
      "type": "boolean",
      "default": false,
      "description": "Set true to fill missing fields with safe sandbox defaults. Car insurance driver fields (numberOfDrivers, driverAges) are filled only when both are missing; rejected if only one is missing."
    },
    "risk_profile": {
      "type": "object",
      "description": "Optional: the service's fields as key/value pairs (see moltbound_requirements). They may also be passed at the top level.",
      "additionalProperties": true
    }
  },
  "description": "One-shot quote request: a plain-language prompt, and/or service_id plus any of that service's fields. SANDBOX: use fictitious data only. Do not enter real personal details.",
  "additionalProperties": true
}

moltbound_request_grant

Advertised by the server during the last successful anonymous check.

Request a scoped data grant for an agent. Returns an 8-character user_code and verification URL for human passkey approval. SANDBOX: use fictitious data only. Do not enter real personal details.

moltbound_request_grant input schema

{
  "type": "object",
  "required": [
    "service"
  ],
  "properties": {
    "fields": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "purpose": {
      "type": "string"
    },
    "service": {
      "type": "string",
      "description": "Service ID (e.g. car_insurance, dog_pet_insurance)"
    },
    "reusable": {
      "type": "boolean",
      "default": true
    },
    "jurisdiction": {
      "enum": [
        "US"
      ],
      "default": "US"
    },
    "expires_in_days": {
      "type": "integer",
      "default": 30
    }
  }
}

moltbound_poll_grant

Advertised by the server during the last successful anonymous check.

Poll for human approval of a data grant using link_id and poll_secret. SANDBOX: use fictitious data only. Do not enter real personal details.

moltbound_poll_grant input schema

{
  "type": "object",
  "required": [
    "link_id",
    "poll_secret"
  ],
  "properties": {
    "link_id": {
      "type": "string"
    },
    "poll_secret": {
      "type": "string"
    }
  }
}

moltbound_grant_status

Advertised by the server during the last successful anonymous check.

Inspect the status and approved fields of an active data grant. SANDBOX: use fictitious data only. Do not enter real personal details.

moltbound_grant_status input schema

{
  "type": "object",
  "required": [
    "grant_id"
  ],
  "properties": {
    "grant_id": {
      "type": "string"
    },
    "grant_token": {
      "type": "string",
      "description": "Access token or poll secret for this grant"
    }
  }
}

moltbound_revoke_grant

Advertised by the server during the last successful anonymous check.

Revoke an active data grant on behalf of the user. SANDBOX: use fictitious data only. Do not enter real personal details.

moltbound_revoke_grant input schema

{
  "type": "object",
  "required": [
    "grant_id"
  ],
  "properties": {
    "grant_id": {
      "type": "string"
    },
    "grant_token": {
      "type": "string",
      "description": "Access token or poll secret for this grant"
    }
  }
}

moltbound_human_sim_start

Advertised by the server during the last successful anonymous check.

Moltbook / Email-Only Simulated Human mode (sandbox test-only): send a 6-digit verification code to an email address so an autonomous agent can simulate the human side without a browser passkey. SANDBOX: use fictitious data only. Do not enter real personal details.

moltbound_human_sim_start input schema

{
  "type": "object",
  "required": [
    "email"
  ],
  "properties": {
    "email": {
      "type": "string"
    },
    "agent_name": {
      "type": "string"
    },
    "capability": {
      "enum": [
        "quote_only",
        "quote_and_bind"
      ],
      "default": "quote_and_bind"
    },
    "service_id": {
      "type": "string",
      "default": "*"
    },
    "jurisdiction": {
      "enum": [
        "US"
      ],
      "default": "US"
    },
    "session_token": {
      "type": "string"
    }
  }
}

moltbound_human_sim_verify

Advertised by the server during the last successful anonymous check.

Verify the 6-digit email code from moltbound_human_sim_start. Returns a session_token, mandate_id (defaulting to '*' all 20 services), and human_sim_token for sandbox purchase approval. SANDBOX: use fictitious data only. Do not enter real personal details.

moltbound_human_sim_verify input schema

{
  "type": "object",
  "required": [
    "email",
    "code"
  ],
  "properties": {
    "code": {
      "type": "string"
    },
    "email": {
      "type": "string"
    },
    "agent_name": {
      "type": "string"
    },
    "capability": {
      "enum": [
        "quote_only",
        "quote_and_bind"
      ],
      "default": "quote_and_bind"
    },
    "service_id": {
      "type": "string",
      "default": "*"
    },
    "jurisdiction": {
      "enum": [
        "US"
      ],
      "default": "US"
    },
    "session_token": {
      "type": "string"
    }
  }
}

moltbound_human_sim_approve

Advertised by the server during the last successful anonymous check.

Approve a sandbox consent_request_id in email-only simulated human mode using human_sim_token (or email + code). Never billable. SANDBOX: use fictitious data only. Do not enter real personal details.

moltbound_human_sim_approve input schema

{
  "type": "object",
  "required": [
    "consent_request_id"
  ],
  "properties": {
    "code": {
      "type": "string"
    },
    "email": {
      "type": "string"
    },
    "human_sim_token": {
      "type": "string"
    },
    "consent_request_id": {
      "type": "string"
    }
  }
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 286 ms
95th percentile latency: 286 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 1, 2026, 8:31 AM UTC · probe · passed · 286 ms · metadata changed · 17 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http moltbound-mcp https://moltbound.dev/kapi/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add moltbound-mcp --url https://moltbound.dev/kapi/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable moltbound-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "moltbound-mcp": {
      "url": "https://moltbound.dev/kapi/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "moltbound-mcp": {
      "type": "streamableHttp",
      "url": "https://moltbound.dev/kapi/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start moltbound-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "moltbound-mcp": {
      "type": "http",
      "url": "https://moltbound.dev/kapi/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http moltbound-mcp https://moltbound.dev/kapi/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "moltbound-mcp": {
      "url": "https://moltbound.dev/kapi/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "moltbound-mcp": {
      "serverUrl": "https://moltbound.dev/kapi/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Moltbound MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

Do you run Moltbound MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing