Spendline is a hosted AI spend governance proxy. Point your OpenAI or Anthropic SDK at Spendline, keep your own provider key, and every call is priced at the moment it happens, attributed to a customer, agent, workflow and cost centre, and checked against budgets before it is forwarded. A call that would breach a cap is refused with HTTP 402 and never reaches the provider. Ten providers are supported: OpenAI, Anthropic, Google Gemini, xAI, Mistral, DeepSeek, Alibaba Qwen, Together AI, Fireworks AI and Groq. The append-only ledger feeds per-customer gross margin and a month-close workflow that reconciles to the provider invoice. Spendline is not an observability or tracing tool; it sits alongside Langfuse, LangSmith or Helicone. The MCP server lets an agent decide whether Spendline fits (spendline_when_to_use), fetch deterministic integration instructions, and, with a Spendline API key, read spend, list budgets and check that traffic is arriving correctly attributed.

MCP readiness

B · 84/100

Readiness is how fully this listing follows its protocol and how it behaved in our probes over 30 days. It is shown for reference and does not move it in search. Search order and leaderboards use the separate quality grade (here C+, 70.4/100), which weighs availability, conformance, p95 speed and descriptor. How the two differ

Valid MCP handshake	10/10	initialize and tools/list both answered.
Live MCP endpoint	25/25	Endpoint answers the MCP initialize handshake (1976 ms).
Protocol revision	6/10	Speaks MCP 2025-06-18, 2 revision(s) behind 2026-07-28.
Signed descriptor	n/a	No MCP standard defines a signed server descriptor.
Uptime (30 days)	14/15	28/30 probes succeeded over 30 days (93%).
Tool declaration	10/10	Lists 10 tool(s) with descriptions.
Verified identity	5/10	Publisher declared (repository, package or homepage); claim this listing to verify domain control.
Freshness + modern flags	4/5	seen in a source within 7 days.
Auth declaration	2/5	Declares credential scheme: smithery_api_key.

Applicable criteria total 90 points, scaled to 100.

Responsiveness: Responsive (1976 ms; bands ≤2.5 s, ≤5 s, ≤8 s, slower; penalty only).

Measured 2026-11-11.

Nine criteria, the same as the A2A readiness score, read from our daily MCP probe (initialize + tools/list) and 30-day probe history. No MCP standard defines a signed server descriptor, so that criterion is n/a and the other 90 points are scaled to 100. Grades: A>=90, B>=75, C>=60, D>=40, F<40. Display only: search order uses the quality grade.

Compared with peers

Against 53,039 reachable MCP servers in our daily snapshot (2026-11-12 06:46 UTC). Display only; it does not change search order.

Readiness: Higher than 75% of peers; This listing 84 · peer median 81
Latency: Faster than 31% of peers; This listing 495 ms · peer median 326 ms

Where it loses the most points, and how to win them back

Verified identity −5 — Claim the listing and prove control of its domain.
Now: Publisher declared (repository, package or homepage); claim this listing to verify domain control.
Protocol revision −4 — Support the current protocol revision.
Now: Speaks MCP 2025-06-18, 2 revision(s) behind 2026-07-28.
Auth declaration −3 — State how to authenticate (an auth scheme, or that none is needed).
Now: Declares credential scheme: smithery_api_key.

How many agent tools actually work · All statistics

Listed in

Directories this entry was found in.

smithery since 2026-09-07 ↗

How to connect

MCP endpoint (streamable-http)

https://server.smithery.ai/fidafareed12/spendline/mcp

JSON-RPC initialize probe

curl -X POST https://server.smithery.ai/fidafareed12/spendline/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}'

Homepage

https://www.spendline.ai

Listed at (smithery)

https://www.spendline.ai