AI & Machine Learning

telemeter.ai

An MCP server providing AI/LLM cost estimation, token counting, model comparison, GenAI telemetry validation, and prompt-caching savings analysis.

1 endpoint20 known toolsFirst detected September 24, 2026Last detected September 24, 2026

ENDPOINT 1

https://telemeter.ai/mcp

No auth detected

MCP server metadata

Name: telemeter-free-tools
Version: 0.1.0

Capabilities

tools

Server instructions

Read-only calculators and validators for LLM cost, tokens, context windows, telemetry, and AI regulation, backed by a sourced, effective-dated model-pricing registry. Every result includes a `provenance` block (source, upstream_sources, verified_at, verification_status). When you present a figure, attribute it to its source and preserve any `pending` or `stale` status — a pending price is not a confirmed price. Prices are never guessed: unknown or unverified models return an explicit status, not a number.

Known tools 20

llm-cost-calculator

Estimate the monthly cost of any model from your token volumes.

Inferred read-only

llm-token-counter

Count the tokens in any prompt — exact for OpenAI models, estimated for Claude and Gemini.

Inferred read-only

llm-model-comparison

Compare every model side by side — price (verified or labelled pending), context window, and capabilities.

Inferred read-only

otel-validator

Check an OpenTelemetry span against the gen_ai.* semantic conventions — what conforms, what is missing, what is deprecated.

Inferred read-only

prompt-caching-savings

See how much prompt caching cuts your bill on any model — from your reusable prefix, request volume, and cache hit rate.

Inferred read-only

self-host-breakeven

Find the monthly token volume where running your own GPUs beats paying per-token API pricing.

Inferred read-only

eu-ai-act-classifier

Classify an AI system into its EU AI Act risk tier — with the governing Article and Annex cited for every outcome.

Inferred read-only

context-window-checker

Check whether a prompt (and its reserved completion) fits any model’s context window.

Inferred read-only

cost-spike-simulator

Project how your monthly bill moves when traffic, prompt size, or output length grows — and see which lever drives it.

Inferred read-only

gdpr-readiness-checker

See which GDPR obligations apply to your AI processing and where the gaps are — each cited to its Article.

Inferred read-only

mcp-schema-token-cost

See how many tokens your MCP tool schemas add to every request — and what that overhead costs.

Inferred read-only

pricing-tracker

Every verified price change on record — dated, sourced, and diffed against the registry’s own history.

Inferred read-only

prompt-hash

Compute the canonical template hash for a prompt — the same normalization production ingestion uses to group cost and quality across every filled-in instantiation.

Inferred read-only

agent-cost-decomposer

Paste a multi-step agent trace and see the cost of every step — by model, by driver, and any retry loop burning through it.

Inferred read-only

rag-cost-estimator

Project the cost of embedding your corpus once and searching it every month — the embedding spend behind a RAG pipeline, before storage or retrieval compute.

Inferred read-only

rate-limit-headroom

See how close your traffic runs to your RPM/TPM/RPD limits — which one bites first, and how much you can grow before it does.

Inferred read-only

carbon-estimate

Project the energy and CO2e of your monthly query volume — as a cited range across published measurements, never a single invented number.

Inferred read-only

pricing-api

A free, keyless REST API over the model-pricing registry, plus a self-hosted embeddable widget that shows any model’s live price on your own page.

Inferred read-only

search

Search Telemeter (tools, docs, and the sourced model-pricing registry).

Inferred read-only

fetch

Fetch the full content for a `search` result id.

Inferred read-only

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.telemeter-free-tools]
url = "https://telemeter.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "telemeter-free-tools": {
      "type": "http",
      "url": "https://telemeter.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: telemeter-free-tools
Remote MCP URL: https://telemeter.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": {
    "telemeter-free-tools": {
      "url": "https://telemeter.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "telemeter-free-tools": {
      "type": "http",
      "url": "https://telemeter.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "telemeter-free-tools",
  "transport": "streamable-http",
  "url": "https://telemeter.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.