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.

AIGratis

REMOTE · AIGRATIS.MY.ID · SCANNED SEP 20

Free AI models and per-token prices across API gateways. Search, compare, estimate cost. Read-only.

Available components

74 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 Security80
Transport & Reachability100
Schema Quality & AI Usability78
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1049 tokens (~116/item across 9 items; 9 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 Management7
  • Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage90
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 71% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the AIGratis MCP server?

AIGratis is a hosted endpoint at https://aigratis.my.id/api/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 · aigratis.my.id

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

  • 19 Sept 26 +1
    • Stability: unverified → 0.03 functional
  • 18 Sept 26 73

    First indexed and scored.

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 20 Sept 2026 · Probed https://aigratis.my.id/api/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=aigratis.my.id CN=WE1,O=Google Trust Services,C=US 7 Sept 2026 6 Dec 2026 ECDSA 256 ECDSA-SHA256 bdee0e78e4183df50e2cf89f6fc684d4
SANs: aigratis.my.id, *.aigratis.my.id
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 insecure

Validation of aigratis.my.id. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
id. present 26887 8 Verified
my.id. present 26449 13 Verified
aigratis.my.id. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
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; includeSubDomains
x-content-type-options nosniff
x-frame-options SAMEORIGIN
referrer-policy no-referrer

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://aigratis.my.id/api/mcp Verified 200
http (plaintext) http://aigratis.my.id/api/mcp HTTPS enforced 301 https://aigratis.my.id/api/mcp
MCP tools · 9 exposed · ~911 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
compare_model_prices ~145

Every gateway offering one canonical model, cheapest input price first. Includes context length, cached-input price, isFree, referral link, and when each offer was last synced. Returns the `limit` cheapest offers plus totalOffers. If the exact slug is unknown, falls back to a search and returns candidates.

NameTypeReqDescription
freebooleanWhen searching by partial name: only models with free offers (true) or paid (false)
limitintegerMax offers to return (cheapest first)
modelstringyesCanonical slug (e.g. 'gpt-4o', 'claude-sonnet-4-5') or a partial name

No output schema declared.

No examples provided.

estimate_cost ~114

Monthly bill for a model at every gateway, given expected input and output tokens. Returns the `limit` cheapest gateways in USD and IDR, totalOffers, and the `cheapest` entry. Free offers cost 0.

NameTypeReqDescription
inputTokensnumberInput tokens per month
limitintegerMax gateways to return (cheapest first)
modelstringyesCanonical slug from suggest_models/search_models, or a partial model id
outputTokensnumberOutput tokens per month

No output schema declared.

No examples provided.

get_fx_rates ~28

Exchange rates used to convert USD prices (perUsd = units of currency per 1 USD).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_gateway ~46

One gateway's profile plus its full model list with prices, context length, modalities and isFree, sorted by input price.

NameTypeReqDescription
slugstringyesGateway slug from list_gateways

No output schema declared.

No examples provided.

list_gateways ~90

Active AI gateways (providers) in compact form: slug, name, tagline, website, referral link, model count, likes, last sync. Editor's picks come first by default. Use get_gateway for docs, payment methods, notes, and the model list.

NameTypeReqDescription
limitinteger
offsetinteger
sortstring'likes' ranks by visitor votes

No output schema declared.

No examples provided.

recent_changes ~91

Catalog events, newest first: models added/removed/returned, price up/down, became free/paid, new gateways. Filter by gateway or model. Paginate with cursor.

NameTypeReqDescription
cursorstringnextCursor from the previous page
kindstring
limitinteger
modelstringCanonical model slug
providerstringGateway slug

No output schema declared.

No examples provided.

search_models ~232

Search model offers across all gateways. Each row is one model at one gateway with its input/output price in USD per 1M tokens. Filter by free=true to list only free offers. Returns canonicalSlug for use with compare_model_prices and estimate_cost.

NameTypeReqDescription
freebooleantrue = only free offers, false = only paid
maxInputPricenumberMaximum input price, USD per 1M tokens
minContextintegerMinimum context window in tokens
modalitystringRequired modality, e.g. 'text', 'image', 'audio'
pageinteger
perPageinteger
providerstringGateway slug (see list_gateways)
qstringSubstring match on model id, name, or canonical slug, e.g. 'gpt-4o', 'llama'
sortstring
vendorstringModel maker, lowercase: anthropic, openai, google, meta, deepseek, mistral, qwen, xai, ...

No output schema declared.

No examples provided.

suggest_models ~126

Resolve a loose model name to canonical slugs. Returns up to `limit` canonical models matching the query, with how many gateways sell each, how many for free, and the cheapest monthly bill for the given token usage. Use before compare_model_prices when you only have a rough name.

NameTypeReqDescription
inputTokensnumberMonthly input tokens for the cost preview
limitinteger
outputTokensnumberMonthly output tokens for the cost preview
qstringPartial model name, e.g. 'claude sonnet', 'deepseek'

No output schema declared.

No examples provided.

top_free_gateways ~39

Gateways ranked by how many distinct models they offer for free, with a few well-known example models each.

NameTypeReqDescription
limitinteger

No output schema declared.

No examples provided.

Common questions

What is the AIGratis MCP server?

AIGratis is an MCP server listed in the public MCP registry as id.my.aigratis/aigratis. Free AI models and per-token prices across API gateways. Search, compare, estimate cost. Read-only. This page covers its hosted endpoint (https://aigratis.my.id/api/mcp).

Is the AIGratis MCP server safe to use?

AIGratis scores 74 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 AIGratis MCP server expose?

AIGratis exposes 9 tools: search_models, suggest_models, compare_model_prices, estimate_cost, list_gateways, and 4 more. Their descriptions and schemas cost roughly 911 tokens of context every time the server is loaded.

Does the AIGratis MCP server require authentication?

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

Is the AIGratis MCP server still maintained?

AIGratis is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.