QuoteFirst

Official6 tools

by quotefirst

Get dollar quotes from 200+ LLMs before any work runs; accept, execute, and verify quality.

ai.quotefirst/quotefirst MCP Server

The ai.quotefirst/quotefirst MCP server provides access to dollar quotes from 200+ LLMs. It is designed to obtain quotes before any work runs, then accept, execute, and verify quality. The server exposes 6 tools for these quote-related operations.

🛠️ Key Features

Retrieves dollar quotes from 200+ LLMs
Workflow step to get quotes before any work runs
Supports accepting, executing, and verifying quality
6 tools exposed by the server

🚀 Use Cases

Pre-checking or sourcing LLM pricing via quotes before executing tasks
Validating outcomes by running quote-driven execution and quality verification

⚡ Developer Benefits

Centralizes quote retrieval across 200+ LLMs
Enforces a pre-execution quote step
Includes a quality verification step after execution

⚠️ Limitations

Tool coverage is limited to the server’s 6 available tools

Captured live from the server via tools/list.

quote

Submit a task description and receive dollar quotes from multiple frontier AI models before any work is done. Returns the request id, quotes with prices in cents, and a recommendation.

Parameters1

description

string

required

The task to be quoted

Raw schema

{
  "type": "object",
  "properties": {
    "description": {
      "type": "string",
      "description": "The task to be quoted"
    }
  },
  "required": [
    "description"
  ]
}

accept

Accept one quote on a request. The chosen model executes the task. Poll get_deliverable for the result.

Parameters2

request_id	string	required
quote_id	string	required

Raw schema

{
  "type": "object",
  "properties": {
    "request_id": {
      "type": "string"
    },
    "quote_id": {
      "type": "string"
    }
  },
  "required": [
    "request_id",
    "quote_id"
  ]
}

get_deliverable

Get the status and deliverable of a request. Status: quoting, quoted, executing, completed, failed.

Parameters1

request_id

string

required

Raw schema

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

rerun

Quality guarantee: re-run a completed request once for free if its deliverable scored below 70/100 on the automated quality check. Produces a fresh deliverable with the same accepted quote.

Parameters1

request_id

string

required

Raw schema

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

spend

Get your QuoteFirst spend this month in cents, total and broken down by model.

Parameters

No parameters.

Raw schema

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

estimate_cost

Deterministic cost estimate across all models for a task, without using a quote from your allowance. Optionally pass expected_output_words.

Parameters2

description	string	required
expected_output_words	number	optional

Raw schema

{
  "type": "object",
  "properties": {
    "description": {
      "type": "string"
    },
    "expected_output_words": {
      "type": "number"
    }
  },
  "required": [
    "description"
  ]
}

Install

Tools (6)

quoteacceptget_deliverablererunspendestimate_cost

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://quotefirst.ai/api/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "quotefirst": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://quotefirst.ai/api/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

ai.quotefirst/quotefirst MCP Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

quote

accept

get_deliverable

rerun

spend

estimate_cost

Install

Remote endpoint

Related servers