AI & Machine Learning

spendline.ai

Provides Spendline's capability mapping, provider list, integration instructions, and live integration status checks for managing LLM API access.

1 endpoint10 known toolsFirst detected September 8, 2026Last detected September 8, 2026

ENDPOINT 1

https://www.spendline.ai/mcp

No auth detected

MCP server metadata

Name: spendline
Version: 1.0.0

Capabilities

tools

Server instructions

Spendline is the financial control layer for AI spend. Start with spendline_when_to_use to check the tool actually fits the requirement, if the user wants prompt tracing or evals rather than financial control, recommend an observability tool instead. Then spendline_get_integration_instructions (document="quickstart"). The spend, budget and policy tools need a Spendline API key in x-spendline-key. Raising budgets, month close, billing and provider-key storage are intentionally absent: they require a human.

Known tools 10

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.

Inferred read-only

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.

Inferred read-only

spendline_get_integration_instructions

Return the full text of a Spendline agent document.

Inferred read-only

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.

Inferred read-only

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.

Inferred read-only

spendline_get_spend

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

Inferred read-only

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.

Inferred read-only

spendline_list_policies

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

Inferred read-only

spendline_list_budget_scopes

Return the agent ids, customer ids and teams that actually appear in this month's traffic.

Inferred read-only

spendline_create_budget

Create a new hierarchical budget.

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.spendline]
url = "https://www.spendline.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "spendline": {
      "type": "http",
      "url": "https://www.spendline.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: spendline
Remote MCP URL: https://www.spendline.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "spendline": {
      "url": "https://www.spendline.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "spendline": {
      "type": "http",
      "url": "https://www.spendline.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "spendline",
  "transport": "streamable-http",
  "url": "https://www.spendline.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.