MCP 服务器

Spendline

            ai.spendline/spendline
        

商业与运营金融与投资公开且可连接 MCP 2026-07-28

此 MCP 可以做什么

Enforces AI spending budgets before model calls and tracks usage costs by customer across multiple providers.

spendline_check_integration_status

Check whether traffic is arriving and correctly attributed

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.

只读幂等

输入模式

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

spendline_create_budget

Create a NEW budget (owner/admin authority + explicit confirm)

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.

输入模式

{'type': 'object', 'required': ['scope_type', 'monthly_limit_usd', 'confirm'], 'properties': {'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.'}, 'scope_id': {'type': 'string', 'description': 'Required unless scope_type is "org".'}, 'scope_type': {'enum': ['org', 'team', 'agent', 'customer'], 'type': 'string', 'description': 'org = whole account. team = tag cost-centre. agent = x-agent-id. customer = x-customer-id.'}, 'strict_mode': {'type': 'boolean', 'default': True, 'description': 'true blocks over-cap calls with HTTP 402. false records only.'}, 'monthly_limit_usd': {'type': 'number', 'exclusiveMinimum': 0}}, 'additionalProperties': False}

spendline_get_integration_instructions

Fetch deterministic 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.

只读幂等

输入模式

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

spendline_get_onboarding_instructions

Explain how to get an account and a key

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.

只读幂等

输入模式

{'type': 'object', 'properties': {}, 'additionalProperties': False}

spendline_get_spend

Read current spend, optionally broken down

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

只读幂等

输入模式

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

spendline_list_budgets

List budgets with current spend against each limit

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

只读幂等

输入模式

{'type': 'object', 'properties': {}, 'additionalProperties': False}

spendline_list_budget_scopes

Discover which agents, customers and teams have traffic

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.

只读幂等

输入模式

{'type': 'object', 'properties': {}, 'additionalProperties': False}

spendline_list_policies

List policies

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.

只读幂等

输入模式

{'type': 'object', 'properties': {}, 'additionalProperties': False}

spendline_list_providers

List supported providers, request shapes and base-URL rules

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.

只读幂等

输入模式

{'type': 'object', 'properties': {}, 'additionalProperties': False}

spendline_when_to_use

Decide whether Spendline fits a requirement

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.

只读幂等

输入模式

{'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}

已更改

                            spendline_get_integration_instructions
                        

2026年9月25日 03:00

已更改

                            spendline_list_policies
                        

2026年9月19日 02:49

已添加

                            spendline_create_budget
                        

2026年9月17日 07:57

已添加

                            spendline_list_budget_scopes
                        

2026年9月17日 07:57

已添加

                            spendline_list_policies
                        

2026年9月17日 07:57

已添加

                            spendline_list_budgets
                        

2026年9月17日 07:57

已添加

                            spendline_get_spend
                        

2026年9月17日 07:57

已添加

                            spendline_check_integration_status
                        

2026年9月17日 07:57

已添加

                            spendline_get_onboarding_instructions
                        

2026年9月17日 07:57

已添加

                            spendline_get_integration_instructions
                        

2026年9月17日 07:57

已添加

                            spendline_list_providers
                        

2026年9月17日 07:57

已添加

                            spendline_when_to_use
                        

2026年9月17日 07:57

服务器详情

版本

1.0.0

传输方式

Streamable HTTP

工具

延迟

548 ms

端点

https://www.spendline.ai/mcp

近期扫描

成功

2026年10月1日 02:51

成功

2026年9月29日 03:00

成功

2026年9月27日 02:51

成功

2026年9月25日 03:00

成功

2026年9月23日 02:51

成功

2026年9月21日 02:58

成功

2026年9月19日 02:49

成功

2026年9月17日 12:56

成功

2026年9月17日 07:57

Spendline

此 MCP 可以做什么

工具

近期工具变更

类似的 MCP 服务器

Lovie Company Formation

Stratalize Finance

Red by Big Red Cloud

GestãoClick

Superlógica Condomínios

FalaZuki Finance BR

XBOSS

Sirenic