Koskamo

Spam I Am MCP

An official MCP server that allows AI agents to verify if a phone number displays spam warnings (like 'Spam Risk' or 'Scam Likely') on major US carriers. The agent initiates a check, the number calls a test line, and the server returns the label, caller name, and screenshot from a real device.

Visit Spam I Am

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.

Spam I Am MCP logo, by Spam I AmVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by Spam I Am
You need:the first check on any number works without a keysign up, add funds and make a key on the Balance page
MCP endpoint (Streamable HTTP)
https://ismynumberspam.com/mcp
Vendor documentation

What you can do with it

  • Check if a phone number shows spam labels on AT&T, Verizon, or T-Mobile
  • Retrieve detailed results including caller name and screenshots
  • Request human approval for spending limits to perform paid checks

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: com.ismynumberspam/spam-i-am@1.0.0Project website

Protocol and capabilities

Server
spam-i-am 1.0.0
MCP protocol
2025-06-18
Tools
6 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

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

Spam I Am checks whether a phone number shows a spam label (such as 'Spam Risk' or 'Scam Likely') on AT&T, Verizon and T-Mobile, using real phones on each carrier. Use it when calls go unanswered or someone says a number came up as spam. Flow: start_check with the number; then the number being checked must call each 'dial' number in the answer (you can't place calls with these tools; use your own calling tools or ask your human); then get_check with wait_seconds until status is 'complete'. Report each carrier separately. The first check on a number is free without a key. Later checks cost money: never pay yourself. Use request_approval to get a link for your human, then get_approval to pick up your key. Only check numbers your human controls, and never use results to rotate numbers to evade labels.

Tools

6 advertised

start_check — Start a spam label check
Advertised by the server during the last successful anonymous check.
Open-world

Start a check of what AT&T, Verizon and T-Mobile phones show when a number calls. Returns the test line to call ('dial') for each carrier and a check id (and a token for a keyless check: keep it). The number being checked must then call each test line within the window. The first check on a number is free; later ones need a key with funds.

start_check input schema
{
  "type": "object",
  "required": [
    "number"
  ],
  "properties": {
    "number": {
      "type": "string",
      "description": "US 10-digit phone number, any format, e.g. '2145550100' or '(214) 555-0100'"
    },
    "api_key": {
      "type": "string",
      "description": "Optional API key (sia_...), if your connection has none and you got one from get_approval"
    },
    "carriers": {
      "type": "array",
      "items": {
        "enum": [
          "AT&T",
          "Verizon",
          "T-Mobile"
        ],
        "type": "string"
      },
      "description": "Leave out to check every carrier that's online"
    },
    "webhook_url": {
      "type": "string",
      "description": "Optional https address to POST the finished result to"
    }
  }
}
start_check annotations
{
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}
get_check — Get a check's results
Advertised by the server during the last successful anonymous check.
Advertised read-only

The check and each carrier's result: status waiting, complete or incomplete; the label shown and caller name; flagged true/false; a screenshot link. Set wait_seconds (up to 25) to wait for results to arrive before answering.

get_check input schema
{
  "type": "object",
  "required": [
    "check_id"
  ],
  "properties": {
    "token": {
      "type": "string",
      "description": "The token from start_check, for a check started without a key"
    },
    "api_key": {
      "type": "string",
      "description": "Optional API key (sia_...), if your connection has none and you got one from get_approval"
    },
    "check_id": {
      "type": "string"
    },
    "wait_seconds": {
      "type": "integer",
      "maximum": 25,
      "minimum": 0
    }
  }
}
get_check annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
get_coverage — Carriers and prices
Advertised by the server during the last successful anonymous check.
Advertised read-only

Which carriers are online now, prices in cents, and the dialing window.

get_coverage input schema
{
  "type": "object",
  "properties": {}
}
get_coverage annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
get_balance — Balance
Advertised by the server during the last successful anonymous check.
Advertised read-only

Needs a key. The account balance, holds, and this key's spending limit.

get_balance input schema
{
  "type": "object",
  "properties": {
    "api_key": {
      "type": "string",
      "description": "Optional API key (sia_...), if your connection has none and you got one from get_approval"
    }
  }
}
get_balance annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
request_approval — Ask your human to approve spending
Advertised by the server during the last successful anonymous check.
Open-world

Get a link (approve_url) for your human to open: they sign in, add funds if needed, set a spending limit and approve. Show them the link, then call get_approval. Use this when a check is refused with free_check_used, insufficient_funds or key_limit.

request_approval input schema
{
  "type": "object",
  "properties": {
    "number": {
      "type": "string",
      "description": "US 10-digit phone number, any format, e.g. '2145550100' or '(214) 555-0100'"
    },
    "reason": {
      "type": "string",
      "maxLength": 300,
      "description": "Shown to your human, e.g. 'Check our sales line before Monday's campaign'"
    },
    "api_key": {
      "type": "string",
      "description": "Optional API key (sia_...), if your connection has none and you got one from get_approval"
    },
    "amount_cents": {
      "type": "integer",
      "maximum": 100000,
      "minimum": 1,
      "description": "How much you're asking for"
    }
  }
}
request_approval annotations
{
  "readOnlyHint": false,
  "openWorldHint": true,
  "destructiveHint": false
}
get_approval — Check whether your human approved
Advertised by the server during the last successful anonymous check.
Advertised read-only

Status of an approval request: pending, approved, declined or expired. Once approved, a keyless request returns api_key (shown once): pass it as api_key to the other tools. Set wait_seconds (up to 25) to wait for a decision.

get_approval input schema
{
  "type": "object",
  "required": [
    "approval_id"
  ],
  "properties": {
    "token": {
      "type": "string",
      "description": "The token from request_approval"
    },
    "api_key": {
      "type": "string",
      "description": "Optional API key (sia_...), if your connection has none and you got one from get_approval"
    },
    "approval_id": {
      "type": "string"
    },
    "wait_seconds": {
      "type": "integer",
      "maximum": 25,
      "minimum": 0
    }
  }
}
get_approval annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}

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
403 ms
95th percentile latency
403 ms

Maintenance history

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

  • · probe · passed · 403 ms · metadata changed · 6 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 spam-i-am-mcp https://ismynumberspam.com/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 spam-i-am-mcp --url https://ismynumberspam.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable spam-i-am-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "spam-i-am-mcp": {
      "url": "https://ismynumberspam.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "spam-i-am-mcp": {
      "type": "streamableHttp",
      "url": "https://ismynumberspam.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start spam-i-am-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "spam-i-am-mcp": {
      "type": "http",
      "url": "https://ismynumberspam.com/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 spam-i-am-mcp https://ismynumberspam.com/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": {
    "spam-i-am-mcp": {
      "url": "https://ismynumberspam.com/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": {
    "spam-i-am-mcp": {
      "serverUrl": "https://ismynumberspam.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Spam I Am 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
See all 4,513

Do you run Spam I Am 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