Go-To Local AI MCP

An official MCP server provided by Go-To Local that allows AI agents to calculate the estimated monthly cost of missed calls for local service businesses and retrieve information about their AI employee services.

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 2026-11-09Operated by Go-To Local

MCP endpoint (Streamable HTTP)

https://gotolocalai.com/mcp

Vendor documentation

What its tools do

2 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

2 of 2 have a description · 2 of 2 declare behavior hints · 1 of 1 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 9, 2026, 3:28 AM UTC
Passed Official MCP Registry namespace is tied to gotolocalai.com · Nov 9, 2026, 3:23 AM UTC
Passed Endpoint is on the registry namespace domain · Nov 9, 2026, 3:23 AM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Calculate the financial impact of missed calls for a local business
Retrieve definitions and details about Go-To Local's AI employee offerings

Source and maintenance

Vendor evidenceRegistry 1.0.0

mcp-registry: com.gotolocalai/missed-call-calculator@1.0.0 Project website

Protocol and capabilities

Server: gotolocal 1.0.0
MCP protocol negotiated in check: 2025-11-25
Tools: 2 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": true
  }
}

Server-provided instructions

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

These tools return a rough missed-call cost estimate worked from the three numbers the caller supplies, and a fixed explainer of the AI employees Go-To Local offers, taken from gotolocalai.com. The estimate is plain arithmetic on the caller's own numbers and is not a forecast; the explainer reflects the site as of its last deploy. Free to use: please cite Go-To Local (gotolocalai.com) and link the source_url in each result.

Tools

2 advertised

missed_call_cost — Missed-call cost estimate

Advertised by the server during the last successful anonymous check.

Advertised read-only

Estimates what missed calls may be costing a local service business each month, using the same formula as the free calculator at https://gotolocalai.com/missed-call-calculator: missed calls a week x 4.33 weeks a month x (share of answered calls that become jobs / 100) x average job value. It is plain arithmetic on the three numbers you give it, so there is no data to go stale, and the result is a rough estimate, not a forecast. Inputs: missed_calls_per_week, avg_job_value (US dollars) and close_rate (a percent: 40 means 40%). Source: Go-To Local, https://gotolocalai.com.

missed_call_cost input schema

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "missed_calls_per_week",
    "avg_job_value",
    "close_rate"
  ],
  "properties": {
    "close_rate": {
      "type": "number",
      "maximum": 100,
      "minimum": 0,
      "description": "Percent of answered calls that become jobs, written as a percent: 40 means 40%. A number from 0 to 100."
    },
    "avg_job_value": {
      "type": "number",
      "maximum": 10000000,
      "minimum": 0,
      "description": "What a typical job pays the business, in US dollars. A number from 0 to 10000000."
    },
    "missed_calls_per_week": {
      "type": "number",
      "maximum": 10000,
      "minimum": 0,
      "description": "Calls the business misses in a typical week, voicemails and unanswered rings included. A number from 0 to 10000."
    }
  }
}

missed_call_cost annotations

{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

what_is_an_ai_employee — What is an AI employee?

Advertised by the server during the last successful anonymous check.

Advertised read-only

Explains what an AI employee is at Go-To Local, a Denver company that builds and runs AI employees for local service businesses: the four employees and where each stands today, the founding pilot price, what the company says it will not do, and that an AI employee says it is an assistant when asked. The text is taken from the Go-To Local website (https://gotolocalai.com/employees) and reflects the site as of its last deploy. No input.

what_is_an_ai_employee input schema

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {}
}

what_is_an_ai_employee annotations

{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

2026-11-09: 1 of 1 checks answered

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: 603 ms
95th percentile latency: 603 ms

Maintenance history

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

Nov 9, 2026, 3:28 AM UTC · probe · passed · 603 ms · metadata changed · 2 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 go-to-local-ai-mcp https://gotolocalai.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 go-to-local-ai-mcp --url https://gotolocalai.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable go-to-local-ai-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "go-to-local-ai-mcp": {
      "url": "https://gotolocalai.com/mcp"
    }
  }
}

Cline

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

Cline configuration

{
  "mcpServers": {
    "go-to-local-ai-mcp": {
      "type": "streamableHttp",
      "url": "https://gotolocalai.com/mcp",
      "disabled": false
    }
  }
}

VS Code

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

VS Code configuration

{
  "servers": {
    "go-to-local-ai-mcp": {
      "type": "http",
      "url": "https://gotolocalai.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 go-to-local-ai-mcp https://gotolocalai.com/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.

Claude Desktop configuration

https://gotolocalai.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": {
    "go-to-local-ai-mcp": {
      "serverUrl": "https://gotolocalai.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Go-To Local AI 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 6,121

Do you run Go-To Local AI 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