# FreeTier Agent API (remote · freetier-agent-api.pages.dev)

x402 pay-per-call data for agents: LLM prices, MCP/x402 directories, holidays, FX, page checks

- Trust score: 61/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-22

## Components

- remote · `freetier-agent-api.pages.dev`: 61/100 (this document), [markdown](https://verifymcp.io/servers/dev-pages-freetier-agent-api-freetier-agent-api/freetier-agent-api.md), [page](https://verifymcp.io/servers/dev-pages-freetier-agent-api-freetier-agent-api/freetier-agent-api)

## Channel facts

- Endpoint: `https://freetier-agent-api.pages.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `3.0.0`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-22.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - 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.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2975 tokens (~106/item across 28 items; 28 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 74/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 22% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 28 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 29 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the FreeTier Agent API MCP server?

FreeTier Agent API is a hosted endpoint at https://freetier-agent-api.pages.dev/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.

### Claude

```bash
claude mcp add --transport http dev-pages-freetier-agent-api-freetier-agent-api 'https://freetier-agent-api.pages.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-pages-freetier-agent-api-freetier-agent-api": {
      "url": "https://freetier-agent-api.pages.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-pages-freetier-agent-api-freetier-agent-api": {
      "type": "http",
      "url": "https://freetier-agent-api.pages.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-pages-freetier-agent-api-freetier-agent-api]
url = "https://freetier-agent-api.pages.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-pages-freetier-agent-api-freetier-agent-api": {
      "type": "remote",
      "url": "https://freetier-agent-api.pages.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-pages-freetier-agent-api-freetier-agent-api --url 'https://freetier-agent-api.pages.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-pages-freetier-agent-api-freetier-agent-api:
    url: "https://freetier-agent-api.pages.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-pages-freetier-agent-api-freetier-agent-api": {
      "Transport": "http",
      "Url": "https://freetier-agent-api.pages.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-pages-freetier-agent-api-freetier-agent-api -t streamable-http -u 'https://freetier-agent-api.pages.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "dev-pages-freetier-agent-api-freetier-agent-api": {
      "type": "http",
      "url": "https://freetier-agent-api.pages.dev/mcp"
    }
  }
}
```

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

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-20 (score 61, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “agent_tools” rewrote its description, which is the text the model reads
- [security] Tool “apis_search” rewrote its description, which is the text the model reads
- [security] Tool “base_gas” rewrote its description, which is the text the model reads
- [security] Tool “country” rewrote its description, which is the text the model reads
- [security] Tool “currency” rewrote its description, which is the text the model reads
- [security] Tool “dataset_full” rewrote its description, which is the text the model reads
- [security] Tool “dump_agent_tools” rewrote its description, which is the text the model reads
- [security] Tool “dump_llm_pricing” rewrote its description, which is the text the model reads
- [security] Tool “dump_mcp_servers” rewrote its description, which is the text the model reads
- [security] Tool “dump_world_reference” rewrote its description, which is the text the model reads
- [security] Tool “dump_x402_services” rewrote its description, which is the text the model reads
- [security] Tool “email_verify” rewrote its description, which is the text the model reads
- [security] Tool “extract_json” rewrote its description, which is the text the model reads
- [security] Tool “free_tiers” rewrote its description, which is the text the model reads
- [security] Tool “holidays” rewrote its description, which is the text the model reads
- [security] Tool “link_check” rewrote its description, which is the text the model reads
- [security] Tool “list_endpoints” rewrote its description, which is the text the model reads
- [security] Tool “llm_cost” rewrote its description, which is the text the model reads
- [security] Tool “llm_pricing” rewrote its description, which is the text the model reads
- [security] Tool “mcp_servers” rewrote its description, which is the text the model reads
- [security] Tool “page_check” rewrote its description, which is the text the model reads
- [security] Tool “page_markdown” rewrote its description, which is the text the model reads
- [security] Tool “page_meta” rewrote its description, which is the text the model reads
- [security] Tool “robots_check” rewrote its description, which is the text the model reads
- [security] Tool “x402_services” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail

### 2026-10-19 (score 60, 0)

- [security] Tool “agent_tools” rewrote its description, which is the text the model reads
- [security] Tool “apis_search” rewrote its description, which is the text the model reads
- [security] Tool “base_gas” rewrote its description, which is the text the model reads
- [security] Tool “country” rewrote its description, which is the text the model reads
- [security] Tool “currency” rewrote its description, which is the text the model reads
- [security] Tool “email_verify” rewrote its description, which is the text the model reads
- [security] Tool “extract_json” rewrote its description, which is the text the model reads
- [security] Tool “free_tiers” rewrote its description, which is the text the model reads
- [security] Tool “holidays” rewrote its description, which is the text the model reads
- [security] Tool “link_check” rewrote its description, which is the text the model reads
- [security] Tool “llm_cost” rewrote its description, which is the text the model reads
- [security] Tool “llm_pricing” rewrote its description, which is the text the model reads
- [security] Tool “mcp_servers” rewrote its description, which is the text the model reads
- [security] Tool “page_check” rewrote its description, which is the text the model reads
- [security] Tool “page_markdown” rewrote its description, which is the text the model reads
- [security] Tool “page_meta” rewrote its description, which is the text the model reads
- [security] Tool “robots_check” rewrote its description, which is the text the model reads
- [security] Tool “x402_services” rewrote its description, which is the text the model reads
- [functional improvement] Stability: unverified → 0.03

### 2026-10-18 (score 60)

First indexed and scored.

## MCP tools (28)

### `list_endpoints` (~53 tokens)

Free. List every FreeTier Agent API endpoint with price (25 free calls/day then $0.001 USDC via x402 on pay-per-call routes; dumps $5–$9), description and example query.

### `mcp_servers_sample` (~28 tokens)

Free. Five sample MCP servers from the 4,259-server directory (MIT source).

### `llm_pricing_sample` (~36 tokens)

Free. List prices of five popular LLMs (USD per 1M tokens, LiteLLM table, MIT).

### `api_directory_sample` (~20 tokens)

Free. Five live public APIs that need no key.

### `apis_search` (~158 tokens)

Pay-per-call: 25 free/day then $0.001 USDC via x402. Search 2,230 link-checked public & free-tier APIs (59 categories). Filters: q, category, auth=none, alive=yes, https=yes, kind, limit<=50. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

Input parameters:

- `alive` (string)
- `auth` (string): 'none' = no API key
- `category` (string)
- `https` (string)
- `kind` (string)
- `limit` (string): 1-50, default 10
- `q` (string): free-text search in name/description/category

### `free_tiers` (~99 tokens)

Pay-per-call: 25 free/day then $0.001 USDC via x402. Current free-tier limits for developer services (hosting, DB, auth, email, CI, monitoring) and AI/LLM APIs, with official source URLs. Filter: q, category. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

Input parameters:

- `category` (string)
- `q` (string)

### `robots_check` (~102 tokens)

Pay-per-call: 25 free/day then $0.001 USDC via x402. Check whether a URL may be crawled per the site's robots.txt for a given user-agent. Returns allowed, matched rule, crawl-delay, sitemaps. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

Input parameters:

- `ua` (string): user-agent token, default *
- `url` (string, required): absolute http(s) URL

### `page_meta` (~93 tokens)

Pay-per-call: 25 free/day then $0.001 USDC via x402. Fetch a public web page (robots.txt respected) and return title, meta description, canonical, Open Graph/Twitter tags, language, headings, link counts, HTTP status. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

Input parameters:

- `url` (string, required): absolute http(s) URL

### `dataset_full` (~76 tokens)

Paid dump ($8 USDC via x402, or buy_with_card in the 402 body). Buy the full Verified API Directory dataset (2,230 rows, JSON, CC BY 4.0 + MIT sources) in one call. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

### `llm_pricing` (~220 tokens)

Pay-per-call: 25 free/day then $0.001 USDC via x402. AI model list prices (USD per 1M input/output/cached tokens, context window, vision/tools/reasoning flags) for ~3,000 models across OpenAI, Anthropic, Google, Mistral, Groq, Bedrock, Azure, Together, Fireworks and more, plus verified free tiers/rate limits of AI APIs. Filters: q, provider, free=yes, max_input_per_m, min_context, vision=yes, tools=yes, sort=input|output|context, limit<=100. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

Input parameters:

- `free` (string)
- `limit` (string)
- `max_input_per_m` (string)
- `min_context` (string)
- `provider` (string)
- `q` (string)
- `sort` (string)
- `tools` (string)
- `vision` (string)

### `llm_cost` (~176 tokens)

Pay-per-call: 25 free/day then $0.001 USDC via x402. Token & cost calculator: estimate tokens for a text (or pass input_tokens/output_tokens) and price it across several models using provider list prices (LiteLLM price table, MIT). Params: models (comma list of model ids like gpt-4o-mini, claude-sonnet-4-5, gemini/gemini-2.5-flash or search words, max 15), text or input_tokens, output_tokens, calls. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

Input parameters:

- `calls` (string)
- `input_tokens` (string)
- `models` (string)
- `output_tokens` (string)
- `text` (string)

### `mcp_servers` (~130 tokens)

Pay-per-call: 25 free/day then $0.001 USDC via x402. Search 4,259 MCP (Model Context Protocol) servers by keyword, category, language (python/typescript/go/rust...), scope (cloud/local) and official flag. Returns repo URL and description. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

Input parameters:

- `category` (string)
- `language` (string)
- `limit` (string)
- `official` (string)
- `q` (string)
- `scope` (string)

### `page_check` (~121 tokens)

Pay-per-call: 25 free/day then $0.001 USDC via x402. One-call page audit for agents: HTTP status, redirects, latency, title, meta description, canonical, lang, Open Graph, JSON-LD types, headings, word count, plus agent-friendliness: robots.txt rules for 14 AI crawlers, llms.txt, sitemap, and a 0-100 score with reasons. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

Input parameters:

- `url` (string, required)

### `link_check` (~90 tokens)

Pay-per-call: 25 free/day then $0.001 USDC via x402. Check up to 20 URLs in one call: HTTP status, final URL after redirects, redirect count, latency, content-type, ok flag. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

Input parameters:

- `urls` (string, required): comma-separated absolute URLs, max 20

### `country` (~101 tokens)

Pay-per-call: 25 free/day then $0.001 USDC via x402. Country reference lookup by ISO2/ISO3/name: capital, population, area, continent, currency, phone prefix, TLD, languages, neighbours, time zones with current UTC offset and local time. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

Input parameters:

- `q` (string, required): ISO2, ISO3 or country name

### `holidays` (~97 tokens)

Pay-per-call: 25 free/day then $0.001 USDC via x402. Public holidays for ~490 countries/territories for 2026 and 2027; optional date=YYYY-MM-DD answers is_holiday. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

Input parameters:

- `country` (string, required): ISO2
- `date` (string)
- `year` (string)

### `currency` (~94 tokens)

Pay-per-call: 25 free/day then $0.001 USDC via x402. Currency conversion with official ECB euro reference rates (~30 currencies, daily). Params: from, to, amount. Also returns the rate date. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

Input parameters:

- `amount` (string)
- `from` (string, required)
- `to` (string, required)

### `base_gas` (~84 tokens)

Pay-per-call: 25 free/day then $0.001 USDC via x402. Live Base mainnet gas price (gwei), latest block, and estimated ETH cost of a USDC transfer (~65k gas) and a plain ETH transfer (21k gas). Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

### `page_markdown` (~90 tokens)

Pay-per-call: 25 free/day then $0.001 USDC via x402. Convert a public web page to clean Markdown (title, headings, paragraphs, lists, links, code), scripts/nav/footer removed, max ~60k chars. robots.txt respected. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

Input parameters:

- `url` (string, required)

### `dump_mcp_servers` (~71 tokens)

Paid dump ($9 USDC via x402, or buy_with_card in the 402 body). Full MCP server directory dump (4,259 servers, JSON). Source awesome-mcp-servers (MIT). Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

### `dump_llm_pricing` (~81 tokens)

Paid dump ($5 USDC via x402, or buy_with_card in the 402 body). Full dump: list prices of ~3,000 AI models (LiteLLM table, MIT) + verified AI/dev free tiers with limits (JSON). Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

### `dump_world_reference` (~91 tokens)

Paid dump ($6 USDC via x402, or buy_with_card in the 402 body). Full dump: 252 countries (GeoNames, CC BY 4.0), 418 time zones, ~14,000 public holidays 2026-2027 (python-holidays, MIT). JSON. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

### `email_verify` (~135 tokens)

Pay-per-call: 25 free/day then $0.001 USDC via x402. Email address check WITHOUT sending mail or SMTP probing: RFC-style syntax check, domain MX/A records via DNS-over-HTTPS, disposable-domain flag (CC0 blocklist, ~9,900 domains), role-address flag (info@, support@...), free-mail flag. Verdict: deliverable_domain | risky | invalid. Cannot confirm that the mailbox itself exists. Addresses are not stored or logged. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

Input parameters:

- `email` (string, required): one email address

### `extract_json` (~212 tokens)

Pay-per-call: 25 free/day then $0.001 USDC via x402. Messy text + JSON Schema in, clean JSON out. Uses a small LLM (Cloudflare Workers AI, Llama 3.1 8B, JSON mode) when available, else a deterministic key:value/regex extractor; the result is type-checked against your schema and missing fields are null. Limits: text <= 6,000 chars, schema <= 30 top-level properties (flat objects, arrays of scalars); the model can misread ambiguous text, so check important values. Params: text, schema (JSON string), mode=auto|heuristic. GET query or POST JSON body. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

Input parameters:

- `mode` (string)
- `schema` (string, required): JSON Schema (type object with properties) as a JSON string
- `text` (string, required): input text, max 6000 chars

### `x402_services` (~154 tokens)

Pay-per-call: 25 free/day then $0.001 USDC via x402. Search ~8,900 live x402 pay-per-call APIs (verified/unverified by nohumans.directory probes, CC BY 4.0): name, endpoint URL, category, price, chains, status, score. Filters: q, category, chain, max_price, status=verified, limit<=100. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

Input parameters:

- `category` (string)
- `chain` (string)
- `limit` (string)
- `max_price` (string)
- `q` (string)
- `status` (string)

### `agent_tools` (~131 tokens)

Pay-per-call: 25 free/day then $0.001 USDC via x402. One search across ~13,000 agent tools: 4,259 MCP servers (awesome-mcp-servers, MIT) and ~8,900 x402 pay-per-call APIs (nohumans.directory, CC BY 4.0). Filters: q, type=mcp|x402, limit<=100. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

Input parameters:

- `limit` (string)
- `q` (string, required)
- `type` (string)

### `dump_x402_services` (~91 tokens)

Paid dump ($6 USDC via x402, or buy_with_card in the 402 body). Full dump: ~8,900 x402 pay-per-call APIs with category, price, chains and probe status (JSON). Data from nohumans.directory, CC BY 4.0, attribution required. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

### `dump_agent_tools` (~85 tokens)

Paid dump ($7 USDC via x402, or buy_with_card in the 402 body). Full dump: Agent Tool Directory, ~13,000 MCP servers + x402 APIs in one unified schema (JSON). MIT + CC BY 4.0 sources, attribution included. Calling this tool returns the HTTP request and x402 payment requirements (or use the free quota).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-pages-freetier-agent-api-freetier-agent-api/freetier-agent-api#diagnostics

## Score history

- 2026-10-22: 61
- 2026-10-21: 61
- 2026-10-20: 61
- 2026-10-19: 60
- 2026-10-18: 60

## Common questions

### What is the FreeTier Agent API MCP server?

FreeTier Agent API is an MCP server listed in the public MCP registry as dev.pages.freetier-agent-api/freetier-agent-api. x402 pay-per-call data for agents: LLM prices, MCP/x402 directories, holidays, FX, page checks. This page covers its hosted endpoint (https://freetier-agent-api.pages.dev/mcp).

### Is the FreeTier Agent API MCP server safe to use?

FreeTier Agent API scores 61 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 FreeTier Agent API MCP server expose?

FreeTier Agent API exposes 28 tools: list_endpoints, mcp_servers_sample, llm_pricing_sample, api_directory_sample, apis_search, and 23 more. Their descriptions and schemas cost roughly 2,919 tokens of context every time the server is loaded.

### Does the FreeTier Agent API MCP server require authentication?

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

### Is the FreeTier Agent API MCP server still maintained?

FreeTier Agent API is still listed as active in the MCP registry. We last reached this channel on 22 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://freetier-agent-api.pages.dev/mcp
- Website: https://freetier-agent-api.pages.dev/
- Changelog RSS feed: https://verifymcp.io/servers/dev-pages-freetier-agent-api-freetier-agent-api/freetier-agent-api.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-pages-freetier-agent-api-freetier-agent-api/freetier-agent-api.json
- HTML version of this page: https://verifymcp.io/servers/dev-pages-freetier-agent-api-freetier-agent-api/freetier-agent-api