Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

com.modelpricewatch/mcp

REMOTE · MODELPRICEWATCH.COM · 2 COMPONENTS · SCANNED SEP 25

Live LLM API pricing: token prices, comparisons, cheapest-model lookups. No key required.

Available components

remote · modelpricewatch.com 77 npm · @modelpricewatch/mcp 34
0 this week 77 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security66
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • Authorisation not fully verified: no authorisation is required to call this server, and 4 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
  • DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
Schema Quality & AI Usability75
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 566 tokens (~141/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management78
  • Stability check failed: schema churn in the 30 days we've observed: 1 tool removals, 0 breaking changes, 0 auth/transport breaks, 0 additions. See how to fix → Fail
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
Install

How do I install the com.modelpricewatch/mcp server?

com.modelpricewatch/mcp is a hosted endpoint at https://modelpricewatch.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · modelpricewatch.com

# add to Claude Code
claude mcp add --transport http com-modelpricewatch-mcp 'https://modelpricewatch.com/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "com-modelpricewatch-mcp": {
      "url": "https://modelpricewatch.com/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "com-modelpricewatch-mcp": {
      "type": "http",
      "url": "https://modelpricewatch.com/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.com-modelpricewatch-mcp]
url = "https://modelpricewatch.com/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-modelpricewatch-mcp": {
      "type": "remote",
      "url": "https://modelpricewatch.com/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add com-modelpricewatch-mcp --url 'https://modelpricewatch.com/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  com-modelpricewatch-mcp:
    url: "https://modelpricewatch.com/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "com-modelpricewatch-mcp": {
      "Transport": "http",
      "Url": "https://modelpricewatch.com/mcp"
    }
  }
}
# add to Vellum
assistant mcp add com-modelpricewatch-mcp -t streamable-http -u 'https://modelpricewatch.com/mcp'
// mcp.json
{
  "mcpServers": {
    "com-modelpricewatch-mcp": {
      "type": "http",
      "url": "https://modelpricewatch.com/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 15 Sept 26 −4
    • Stability: pass → fail ▼ security
    • A breaking change shipped without a version bump: still 1.0.0 ▼ security
    • Tool “compare_models” was removed ▼ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: 127 → 141 ▼ functional
  • 26 Aug 26 81
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Aug 26 0
    • Stability: 0.97 → pass security
  • 11 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 2 Aug 26 0
    • “get_model_pricing” reworded the description of “model_id” cosmetic

    1 cosmetic change on this day. Switch on “Show cosmetic changes” to see it.

  • 31 Jul 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 27 Jul 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 24 Sept 2026 · Probed https://modelpricewatch.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=modelpricewatch.com CN=WE1,O=Google Trust Services,C=US 22 Aug 2026 20 Nov 2026 ECDSA 256 ECDSA-SHA256 ecd157bb42a137db0e2d873fa60b92e3
SANs: modelpricewatch.com, *.modelpricewatch.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC secure

Validation of modelpricewatch.com. — Secure

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
modelpricewatch.com. present 2371 13 Verified
modelpricewatch.com. Verified address RRset verified with the apex keys
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=15552000

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://modelpricewatch.com/mcp Verified 200
http (plaintext) http://modelpricewatch.com/mcp HTTPS enforced 301 https://modelpricewatch.com/mcp
MCP tools · 4 exposed · ~483 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
cheapest_models ~164

Find the cheapest current models, ranked by input price, output price, or a blended cost. The generic ranking covers generative text models (embeddings, OCR and realtime models are excluded — they price different work); pass category to rank a specific pool instead, e.g. 'embedding'. Use to answer 'what is the cheapest model for <use case>'.

NameTypeReqDescription
categorystring–Filter by category, e.g. flagship, reasoning, budget, coding, embedding.
limitnumber–How many to return (default 10, max 50).
open_sourceboolean–If true, only open-source models.
sort_bystring–Ranking metric: 'input', 'output', or 'blended' (default 'blended').

No output schema declared.

No examples provided.

get_model_pricing ~103

Get full pricing and capability details for one model by its id (from search_models). Returns input/output/cached price per 1M tokens, blended cost, context window, modality, release date, and the modelpricewatch.com page URL.

NameTypeReqDescription
model_idstringyesThe model id, e.g. 'anthropic-claude-opus-4-8' or 'openai-gpt-5-5'. Get ids from search_models.

No output schema declared.

No examples provided.

list_providers ~35

List all tracked AI model providers (OpenAI, Anthropic, Google, etc.) with a short description and their pricing page.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

search_models ~181

Search the live LLM pricing database by model name, provider, or id. Returns matching models with current input/output prices (USD per 1M tokens), context window, modality, and category. Use this to answer 'how much does <model> cost' or 'what models does <provider> offer'.

NameTypeReqDescription
categorystring–Filter by category, e.g. flagship, reasoning, budget, coding, embedding, fast, mid-tier.
limitnumber–Max results (default 20, max 50).
open_sourceboolean–If true, only open-source/open-weight models; if false, only proprietary.
querystring–Free-text match against model name, provider, or id (e.g. 'claude', 'gpt-5', 'gemini flash'). Omit to list all.

No output schema declared.

No examples provided.

Common questions

What is the com.modelpricewatch/mcp server?

com.modelpricewatch/mcp is listed in the public MCP registry as com.modelpricewatch/mcp. Live LLM API pricing: token prices, comparisons, cheapest-model lookups. No key required. This page covers its hosted endpoint (https://modelpricewatch.com/mcp).

Is the com.modelpricewatch/mcp server safe to use?

com.modelpricewatch/mcp scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the com.modelpricewatch/mcp server expose?

com.modelpricewatch/mcp exposes 4 tools: search_models, get_model_pricing, cheapest_models, list_providers. Their descriptions and schemas cost roughly 483 tokens of context every time the server is loaded.

Does the com.modelpricewatch/mcp server require authentication?

No. We connected to com.modelpricewatch/mcp without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the com.modelpricewatch/mcp server still maintained?

com.modelpricewatch/mcp is still listed as active in the MCP registry. We last reached this channel on 24 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.