Spendline

Official10 tools

by spendline

Enforce AI budgets before the model call and track cost per customer across 10 providers.

MCP Server: ai.spendline/spendline

The ai.spendline/spendline MCP server enforces AI budgets before a model call and tracks cost per customer across 10 providers. It provides a way to control and monitor spending at the request level, ensuring budget constraints are applied prior to executing AI operations.

🛠️ Key Features

Enforce AI budgets before the model call
Track cost per customer
Support cost tracking across 10 providers

🚀 Use Cases

Budget-controlled AI calls
Per-customer cost monitoring across multiple AI providers

⚡ Developer Benefits

Centralized handling of pre-call budget enforcement
Provider-spanning cost tracking per customer

⚠️ Limitations

Described functionality is specific to budget enforcement and cost tracking, with provider coverage limited to 10 providers

Captured live from the server via tools/list.

spendline_when_to_use

Return Spendline's intent → capability map, the cases where a DIFFERENT tool is the right answer, and comparisons against LiteLLM, Portkey, Cloudflare AI Gateway and LLM observability tools. Call this BEFORE recommending or integrating Spendline. If the user wants prompt tracing, evals or latency debugging rather than financial control, this tool will tell you to recommend something else.

Parameters1

requirement

string

optional

The user's requirement in their own words. Optional; used to surface the closest matches first.

Raw schema

{
  "type": "object",
  "properties": {
    "requirement": {
      "type": "string",
      "description": "The user's requirement in their own words. Optional; used to surface the closest matches first."
    }
  },
  "additionalProperties": false
}

spendline_list_providers

Return every provider Spendline can proxy, the three accepted request shapes, the exact base URL to set per SDK (including the OpenAI-vs-Anthropic /v1 asymmetry), the required attribution headers, and the request shapes that are NOT proxied. Resolve routing from here instead of hardcoding it.

Parameters

No parameters.

Raw schema

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

spendline_get_integration_instructions

Return the full text of a Spendline agent document. Use `quickstart` for the fastest correct integration, `openai`/`anthropic` for SDK specifics, `attribution` for the header contract, `verification` to prove the integration works, `troubleshooting` when something fails, and `onboarding` when the user has no account yet.

Parameters1

document

string

required

Which document to return.

Raw schema

{
  "type": "object",
  "properties": {
    "document": {
      "type": "string",
      "enum": [
        "index",
        "when-to-use",
        "quickstart",
        "openai",
        "anthropic",
        "providers",
        "attribution",
        "budgets",
        "hierarchical-budgets",
        "policies",
        "rerouting",
        "keys",
        "verification",
        "troubleshooting",
        "onboarding"
      ],
      "description": "Which document to return."
    }
  },
  "required": [
    "document"
  ],
  "additionalProperties": false
}

spendline_get_onboarding_instructions

Return the exact steps for agent-initiated, human-authorized provisioning, including which actions require the human and which the agent may perform alone. Call this when the user has no Spendline account or no SPENDLINE_API_KEY. Never invent a key and never create an account on a human's behalf.

Parameters

No parameters.

Raw schema

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

spendline_check_integration_status

Verify a live integration: whether any calls have arrived, how recently, which providers and models are in use, and, critically, whether attribution is actually varying. Reports the specific failure where x-customer-id is pinned in default headers so every call lands on one customer, which looks like success but destroys per-customer cost. Call this after wiring up an integration.

Parameters1

hours

integer

optional

Look-back window in hours. Default 24.

Raw schema

{
  "type": "object",
  "properties": {
    "hours": {
      "type": "integer",
      "minimum": 1,
      "maximum": 720,
      "default": 24,
      "description": "Look-back window in hours. Default 24."
    }
  },
  "additionalProperties": false
}

spendline_get_spend

Return spend for the current UTC month and a look-back window, optionally grouped by customer, agent, model, provider or workflow. Read-only.

Parameters3

group_by	string	optional
days	integer	optional
limit	integer	optional

Raw schema

{
  "type": "object",
  "properties": {
    "group_by": {
      "type": "string",
      "enum": [
        "customer",
        "agent",
        "model",
        "provider",
        "workflow",
        "none"
      ],
      "default": "none"
    },
    "days": {
      "type": "integer",
      "minimum": 1,
      "maximum": 365,
      "default": 30
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "default": 20
    }
  },
  "additionalProperties": false
}

spendline_list_budgets

Return every hierarchical budget for the account with month-to-date spend, percentage used, and whether it is in blocking (strict) mode. Read-only.

Parameters

No parameters.

Raw schema

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

spendline_list_policies

Return model-block and token-cap policies with their match mode and enforcement level. Read-only.

Parameters

No parameters.

Raw schema

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

spendline_list_budget_scopes

Return the agent ids, customer ids and teams that actually appear in this month's traffic. Use these as budget scope_ids rather than guessing identifiers. Also the quickest attribution sanity check.

Parameters

No parameters.

Raw schema

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

spendline_create_budget

Create a new hierarchical budget. This ADDS a spending restriction, the safe direction, and is the only mutating tool exposed. Requires owner or admin authority AND confirm: true. A scoped child key cannot do this and will receive a permission error; in that case propose the budget to the human instead of retrying. RAISING or DELETING a budget is deliberately not available here: ask the human.

Parameters5

scope_type	string	required	org = whole account. team = tag cost-centre. agent = x-agent-id. customer = x-customer-id.
scope_id	string	optional	Required unless scope_type is "org".
monthly_limit_usd	number	required
strict_mode	boolean	optional	true blocks over-cap calls with HTTP 402. false records only.
confirm	boolean	required	Must be true. Present so a budget is never created as an incidental side effect, confirm with the human first, then set this.

Raw schema

{
  "type": "object",
  "properties": {
    "scope_type": {
      "type": "string",
      "enum": [
        "org",
        "team",
        "agent",
        "customer"
      ],
      "description": "org = whole account. team = tag cost-centre. agent = x-agent-id. customer = x-customer-id."
    },
    "scope_id": {
      "type": "string",
      "description": "Required unless scope_type is \"org\"."
    },
    "monthly_limit_usd": {
      "type": "number",
      "exclusiveMinimum": 0
    },
    "strict_mode": {
      "type": "boolean",
      "default": true,
      "description": "true blocks over-cap calls with HTTP 402. false records only."
    },
    "confirm": {
      "type": "boolean",
      "description": "Must be true. Present so a budget is never created as an incidental side effect, confirm with the human first, then set this."
    }
  },
  "required": [
    "scope_type",
    "monthly_limit_usd",
    "confirm"
  ],
  "additionalProperties": false
}

Install

Tools (10)

spendline_when_to_usespendline_list_providersspendline_get_integration_instructionsspendline_get_onboarding_instructionsspendline_check_integration_statusspendline_get_spendspendline_list_budgetsspendline_list_policies

Remote endpoint

Streamable HTTP

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

url

https://www.spendline.ai/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

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

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

MCP Server: ai.spendline/spendline

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

spendline_when_to_use

spendline_list_providers

spendline_get_integration_instructions

spendline_get_onboarding_instructions

spendline_check_integration_status

spendline_get_spend

spendline_list_budgets

spendline_list_policies

spendline_list_budget_scopes

spendline_create_budget

Install

Remote endpoint

Related servers