Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "spendline": {
      "type": "http",
      "url": "https://www.spendline.ai/mcp",
      "headers": {
        "x-spendline-key": "${X_SPENDLINE_KEY}"
      }
    }
  }
}

claude mcp add --transport http spendline https://www.spendline.ai/mcp --header "x-spendline-key: ${X_SPENDLINE_KEY}"

[mcp_servers.spendline]
url = "https://www.spendline.ai/mcp"
env_http_headers = { "x-spendline-key" = "X_SPENDLINE_KEY" }

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "spendline": {
      "type": "remote",
      "url": "https://www.spendline.ai/mcp",
      "enabled": true,
      "headers": {
        "x-spendline-key": "{env:X_SPENDLINE_KEY}"
      }
    }
  }
}

{
  "mcpServers": {
    "spendline": {
      "type": "http",
      "url": "https://www.spendline.ai/mcp",
      "headers": {
        "x-spendline-key": "${X_SPENDLINE_KEY}"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=spendline&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vd3d3LnNwZW5kbGluZS5haS9tY3AiLCJoZWFkZXJzIjp7Ingtc3BlbmRsaW5lLWtleSI6IiR7WF9TUEVORExJTkVfS0VZfSJ9fQ%3D%3D"
}

{
  "servers": {
    "spendline": {
      "type": "http",
      "url": "https://www.spendline.ai/mcp",
      "headers": {
        "x-spendline-key": "${X_SPENDLINE_KEY}"
      }
    }
  }
}

{
  "mcpServers": {
    "spendline": {
      "httpUrl": "https://www.spendline.ai/mcp",
      "headers": {
        "x-spendline-key": "${X_SPENDLINE_KEY}"
      }
    }
  }
}

extensions:
  "spendline":
    enabled: true
    name: "spendline"
    type: streamable_http
    uri: "https://www.spendline.ai/mcp"
    headers:
      "x-spendline-key": "${X_SPENDLINE_KEY}"
    timeout: 300

Placeholders to fill from your own secret store: ${X_SPENDLINE_KEY}. The registry never accepts secret values.

Quality 91 / 100strong

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene100 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations10 of 10 tools declare readOnlyHint or destructiveHint
pass
tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
pass
tools.token_costabout 1,711 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability100 · weight 15

pass
stability.changes1 tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

10 tools, about 1,711 tokens to load them all · tool set 482a997fd819 · tools last changed 2026-09-24 · checked 2026-10-19 10:52 UTC

Tool changes

2026-09-24spendline_get_integration_instructionschangedinput schema

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 80 / 100

no-repository

provenance55

liveness100

freshness85

hygiene80

+dns-namespace +website +reachable +uptime-100% ~updated-41d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://www.spendline.ai/mcp` streamable-http	none	yes	100%	387 ms	2025-06-18	2026-10-19

Tools (10)

`spendline_check_integration_status`read-only	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.
`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.
`spendline_get_integration_instructions`read-only	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.
`spendline_get_onboarding_instructions`read-only	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.
`spendline_get_spend`read-only	Return spend for the current UTC month and a look-back window, optionally grouped by customer, agent, model, provider or workflow. Read-only.
`spendline_list_budgets`read-only	Return every hierarchical budget for the account with month-to-date spend, percentage used, and whether it is in blocking (strict) mode. Read-only.
`spendline_list_budget_scopes`read-only	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.
`spendline_list_policies`read-only	Return model-block, model-allow and token-cap policies with their match mode, enforcement level and scope (null = account-wide; otherwise { agent_id / customer_id / agent_name }). Read-only.
`spendline_list_providers`read-only	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.
`spendline_when_to_use`read-only	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.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "ai.spendline/spendline",
  "title": "Spendline",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://www.spendline.ai/mcp",
      "type": "streamable-http",
      "headers": [
        {
          "name": "x-spendline-key",
          "isSecret": true,
          "description": "Spendline API key. Optional: public selection and integration tools work without it; spend, budget and policy tools require it."
        }
      ]
    }
  ],
  "version": "1.0.0",
  "websiteUrl": "https://www.spendline.ai/",
  "description": "Enforce AI budgets before the model call and track cost per customer across 10 providers."
}