TR Try tools
← Whole catalogue

AI Infrastructure

Part of the catalogue. The same key, envelope and billing cover every other endpoint too.

MCP Tool Surface Index · LLM Price & Lifecycle Archive · LLM Endpoint Drift

  • No account needed to try any endpoint on this page.
  • Deterministic endpoints answer from cache in single-digit milliseconds.
  • Every response carries a receipt: credits charged, cache status, duration.

Free try on this page → when you need a key, Proceed to pay · API access.

POST/v1/mcp/index
Request
{
  "view": "search",
  "q": "invoice"
}
no request sent yet
Response
Press Run to try free — no key needed.
3endpoints
data points banked
time series
median response

Why this exists

Built for hostile input

A Turkish address arrives as "Cd." or "Cad." or "Caddesi", with the flat number glued to the building number. Generic parsers drop half of it silently. This one tells you what it could not place.

Every number carries its provenance

Each archived point stores the source URL and a content hash of the page it came from, and the archive is committed to a Merkle root anchored in Bitcoin. Every commitment — with its cutoff, leaf count and anchors — is published at /proof, so you can check for yourself how current the latest one is. The bulletins themselves are public and anyone can read them; what this adds is that a number you quote can be shown to be the number we held on that date, and that it has not been edited since.

You only pay for work

Repeated inputs come from cache and cost zero credits. If a response ever fails its own schema, the call is refunded automatically.

Endpointsexpand any row to see the parameters and call it live

AI Infrastructure3

/v1/mcp/index MCP Tool Surface Index 1 credit

Searchable, dated archive of what every public MCP server actually exposes — tool definitions, daily change feed, and rug-pull detection.

The official MCP registry publishes a server’s name and address but not its tool surface; the only way to learn what a server exposes is to connect and call `tools/list`. This endpoint does that daily across every public remote server and keeps the result. Three things become answerable that the source cannot answer: tool-level search (the registry has none), uptime, and — the one that matters for security — what a tool’s description said yesterday. In MCP a tool description is part of the context handed to the model, so it is prompt text; if it changes after the user approved the server, the server has silently injected new instructions. Each indexed tool also carries a review score with the matched evidence, so the claim can be checked rather than trusted. Measurement boundary: only `initialize` and `tools/list` are ever called — never `tools/call`.

Parameters

view "search" | "changes" | "server" | "tool" | "stats" `search`: search tool name/description · `changes`: change feed (the actual product) · `server`: per-day measurement history for one server · `tool`: definition history for one tool · `stats`: index-level totals. default "search"
q string Search term (only `search`), e.g. `invoice`, `calendar`, `sql`.
server string Registry server name, e.g. `com.temsor/api`. Required for `server`/`tool` views.
tool string Tool name (only `tool` view).
minRisk integer Only tools whose review score is at or above this (only `search`).
severity "high" | "medium" | "low" | "info" Only `changes`.
type string Event type filter (only `changes`), e.g. `tool_description_changed`.
days integer Window in days (`changes` and `server`). default 30
limit integer default 50
POST/v1/mcp/index
Request
{
  "view": "search",
  "q": "invoice"
}
no request sent yet
Response
Press Run to try free — no key needed.
/v1/model/archive LLM Price & Lifecycle Archive 1 credit

Dated archive of LLM prices, context windows, announced retirement dates and quiet delistings across 400+ models and 50+ providers.

Providers overwrite their pricing pages and drop models from their catalogs without publishing what changed. This endpoint keeps a daily record, so three otherwise unanswerable questions become answerable: what a model cost on a given date (a contract and budget question), which models were quietly removed (a dependency-audit question), and when a retirement date was first announced and whether it later moved (a migration-planning question). Price points land in the shared time series, so a full range query is available through `series/history` under `model.price.<provider>/<model>.<input|output|cache_read>`. The archive can only accumulate forward — it cannot be reconstructed after the fact.

Parameters

view "catalog" | "expiring" | "delisted" | "events" | "stats" `catalog`: tracked models · `expiring`: retirement announced · `delisted`: dropped from the catalogue · `events`: lifecycle events · `stats`: archive totals. default "catalog"
provider string Provider prefix, e.g. `anthropic`, `openai`, `google`.
slug string Full model id, e.g. `anthropic/claude-opus-5` (only `events`).
q string Search in model id/name (only `catalog`).
type "listed" | "delisted" | "relisted" | "price_up" | "price_down" | "context_changed" | "expiration_announced" | "expiration_changed" Event type (only `events`).
severity "high" | "medium" | "low" | "info"
withinDays integer `expiring`: retire within this many days. default 180
days integer `events`: window in days. default 90
includeDelisted boolean `catalog`: include delisted models. default false
limit integer default 100
POST/v1/model/archive
Request
{
  "view": "expiring",
  "withinDays": 180
}
no request sent yet
Response
Press Run to try free — no key needed.
/v1/model/drift LLM Endpoint Drift 1 credit

Independent daily record of what changed behind a provider endpoint: which alias resolved to which model, and when behaviour shifted.

Providers update models behind stable endpoint names. This endpoint publishes an independent measurement: a fixed probe suite is sent daily at temperature 0, three repeats per probe, and the identity a provider declares in its own response (`modelVersion`, `system_fingerprint`, region) is recorded alongside. A change is only reported as drift when the repeats agree with each other and disagree with the previous run — same-day disagreement is noise, not drift. `aliases` answers "what was actually behind `gemini-flash-latest` on that day"; a question that cannot be answered retroactively.

Parameters

view "aliases" | "events" | "probes" `aliases`: alias → the real model behind it · `events`: drift events · `probes`: probe status from the last run. default "aliases"
provider string Filter by provider (gemini, groq, cerebras, mistral).
severity "high" | "medium" | "low" | "info" Only for the `events` view.
days integer History window in days (only `events`). default 90
limit integer default 100
POST/v1/model/drift
Request
{
  "view": "aliases"
}
no request sent yet
Response
Press Run to try free — no key needed.

Pricingone key covers every endpoint

Free try on this page → when you need a key, Proceed to pay · API access.

Credits are consumed per call and cache hits are free. Requests without a key run on a narrow per-IP demo quota so you can evaluate before signing up.

The API key is e-mailed the moment payment clears. Upgrades keep the same key, so your integration is never broken.

Want to finish the integration before paying?

Use it from an AI assistantthe same catalogue, exposed as MCP tools

Every endpoint is also published over the Model Context Protocol, so Claude, ChatGPT or your own agent can call it directly — no glue code, no wrapper functions. The assistant sees the same input schemas and the same metering.

Currently 68 tools. New endpoints appear automatically; nothing to update on your side.

claude_desktop_config.json

{
  "mcpServers": {
    "temsor": {
      "url": "https://api.temsor.com/mcp",
      "headers": { "x-api-key": "fk_live_…" }
    }
  }
}

Quickstart

Official client: npm install temsor-api · npmjs.com/package/temsor-api

Node.js

import Client from "temsor-api";

const api = new Client({ apiKey: KEY });
const r = await api.${(() => {
  const first = apis[0];
  return first.slug.split(/[/-]/).map((p, i) => (i === 0 ? p : p[0].toUpperCase() + p.slice(1))).join('');
})()}(${esc(JSON.stringify(apis[0].examples[0]?.input ?? {}))});
console.log(r, r.$meta);

cURL

curl -s https://api.temsor.com/v1/mcp/index \
  -H "content-type: application/json" \
  -H "x-api-key: fk_live_…" \
  -d '{"view":"search","q":"invoice"}'

JavaScript

const res = await fetch("https://api.temsor.com/v1/mcp/index", {
  method: "POST",
  headers: { "content-type": "application/json", "x-api-key": KEY },
  body: JSON.stringify({"view":"search","q":"invoice"})
});
const { data } = await res.json();

Python

import httpx
r = httpx.post("https://api.temsor.com/v1/mcp/index",
    headers={"x-api-key": KEY},
    json={"view":"search","q":"invoice"})
data = r.json()["data"]
temsor API

Small, precise APIs behind one key and one response envelope. New endpoints ship on the same key.

References OpenAPI 3.1MCP manifestService health
Response contract

{ ok, data, meta }

{ ok:false, error }

Tell us what broke

Wrong answer, missing field, an endpoint you wish existed — it reaches a person, not a queue.