# ThirdMade Shelf (remote · shelf.thirdmade.net)

26 pay-per-call tools for agents: scrape, verify, guards, crypto. x402 USDC on Base.

- Trust score: 71/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `shelf.thirdmade.net`: 71/100 (this document), [markdown](https://verifymcp.io/servers/net-thirdmade-shelf/shelf.md), [page](https://verifymcp.io/servers/net-thirdmade-shelf/shelf)

## Channel facts

- Endpoint: `https://shelf.thirdmade.net/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `3.1.0`

## 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 2026-09-20.

- **Endpoint Security**: 51/100
  - 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 26 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 check failed: the endpoint is reachable over plaintext HTTP.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 85/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1541 tokens (~57/item across 27 items; 26 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 60/100
  - Stability check failed: schema churn in the 21 days we've observed: 0 tool removals, 5 breaking changes, 0 auth/transport breaks, 0 additions.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "captcha_eval" implies "eval" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 28 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the ThirdMade Shelf MCP server?

ThirdMade Shelf is a hosted endpoint at https://shelf.thirdmade.net/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 net-thirdmade-shelf 'https://shelf.thirdmade.net/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "net-thirdmade-shelf": {
      "url": "https://shelf.thirdmade.net/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "net-thirdmade-shelf": {
      "type": "http",
      "url": "https://shelf.thirdmade.net/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.net-thirdmade-shelf]
url = "https://shelf.thirdmade.net/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "net-thirdmade-shelf": {
      "type": "remote",
      "url": "https://shelf.thirdmade.net/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add net-thirdmade-shelf --url 'https://shelf.thirdmade.net/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  net-thirdmade-shelf:
    url: "https://shelf.thirdmade.net/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "net-thirdmade-shelf": {
      "Transport": "http",
      "Url": "https://shelf.thirdmade.net/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add net-thirdmade-shelf -t streamable-http -u 'https://shelf.thirdmade.net/mcp'
```

### Other

```json
{
  "mcpServers": {
    "net-thirdmade-shelf": {
      "type": "http",
      "url": "https://shelf.thirdmade.net/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.

### 2026-09-20 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60.

### 2026-09-18 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 54.

### 2026-09-16 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 44 to 47.

### 2026-09-14 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40.

### 2026-09-12 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 34.

### 2026-09-09 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 24.

### 2026-09-07 (score 65, +1)

- [functional] Server version: 4.0.0 → 4.6.0

### 2026-09-05 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10.

## MCP tools (26)

### `robots` (~55 tokens)

Parses robots.txt for any domain — shows crawl rules, disallowed paths, sitemaps. Agents use this to check if they're allowed to scrape a site before doing it. [free]

Input parameters:

- `url` (string, required): Target webpage URL

### `llms_txt` (~50 tokens)

llms txt

Fetches and normalizes llms.txt / llms-full.txt from any site — the emerging standard for making websites readable to AI agents. [free]

Input parameters:

- `url` (string, required): Target webpage URL

### `page_meta` (~63 tokens)

page meta

Extracts OG tags, canonical URL, title, and meta description from any web page. Useful for link previews, SEO audits, and content enrichment. [price: $0.001/call USDC via x402]

Input parameters:

- `url` (string, required): Target webpage URL

### `domain_facts` (~61 tokens)

domain facts

Live-checks a domain: is it up, does it have TLS, what's the title? Quick domain health check for agents evaluating links. [price: $0.001/call USDC via x402]

Input parameters:

- `domain` (string, required): Domain name

### `link_graph` (~57 tokens)

link graph

Extracts all outbound links from a page, classified by domain. Shows where a page links to and which domains dominate. [price: $0.001/call USDC via x402]

Input parameters:

- `url` (string, required): Target webpage URL

### `scrape` (~62 tokens)

Scrapes any public web page and returns clean structured JSON (title, text, length). The workhorse — agents use this for real data extraction. [price: $0.01/call USDC via x402]

Input parameters:

- `url` (string, required): Target webpage URL

### `captcha_eval` (~78 tokens)

captcha eval

Classifies captcha type (reCAPTCHA, hCaptcha, Turnstile) and difficulty. Eval only — we do NOT solve captchas. [price: $0.01/call USDC via x402]

Input parameters:

- `type` (string): Captcha type: recaptcha, hcaptcha, turnstile, image, slider, puzzle

### `geo_time` (~44 tokens)

geo time

Geocode + timezone + currency context for any location string. [price: $0.001/call USDC via x402]

Input parameters:

- `q` (string, required): Location string

### `entity_find` (~52 tokens)

entity find

Extracts named entities (people, companies, places) from text. Wikidata resolution next iteration. [price: $0.001/call USDC via x402]

Input parameters:

- `text` (string, required): Input text

### `search_verify` (~62 tokens)

search verify

Checks if a URL supports a claim. Returns confidence score. Research agents use this to verify sources. [price: $0.01/call USDC via x402]

Input parameters:

- `claim` (string, required): Claim to verify
- `url` (string, required): Source URL

### `similar_domains` (~53 tokens)

similar domains

Finds similar/competitor domains by name-similarity. Lead-gen agents use this for prospecting. [price: $0.001/call USDC via x402]

Input parameters:

- `domain` (string, required): Domain name

### `gas_now` (~46 tokens)

gas now

Current gas prices in Gwei for Base, Ethereum, or Arbitrum via public RPC. [free]

Input parameters:

- `chain` (string): base (default), ethereum, or arbitrum

### `chain_stats` (~49 tokens)

chain stats

Block height + chain stats for Base or Ethereum. [price: $0.001/call USDC via x402]

Input parameters:

- `chain` (string): base (default), ethereum, or arbitrum

### `nonce` (~65 tokens)

Current transaction nonce for any address on Base or Ethereum. Agent tx bots need this before sending transactions. [price: $0.001/call USDC via x402]

Input parameters:

- `address` (string, required): EVM address
- `chain` (string): base (default) or ethereum

### `token_security` (~67 tokens)

token security

Token security heuristics: honeypot signals, proxy detection, LP data. Trading agents use this to avoid rugs. [price: $0.01/call USDC via x402]

Input parameters:

- `address` (string, required): Token contract address
- `chain` (string): base (default)

### `ens_lookup` (~45 tokens)

ens lookup

ENS name resolution + reverse lookup via public Ethereum RPC. [price: $0.001/call USDC via x402]

Input parameters:

- `name` (string, required): ENS name or address

### `summarize` (~47 tokens)

Extractive summary (3 sentences) + top-5 keywords from any text. [price: $0.001/call USDC via x402]

Input parameters:

- `text` (string, required): Input text

### `jsonify` (~50 tokens)

Coerces messy text (key=value lines, CSV-ish, sentences) into clean JSON. [price: $0.001/call USDC via x402]

Input parameters:

- `text` (string, required): Input text

### `sentiment` (~46 tokens)

Sentiment classification (positive/negative/neutral) + emotion keyword hits. [price: $0.001/call USDC via x402]

Input parameters:

- `text` (string, required): Input text

### `image_gen` (~73 tokens)

image gen

Generates 1 PNG from a text prompt (FLUX.1-dev, 512px). Async: returns job ID + poll URL. GPU-backed via RunPod ComfyUI, scale-to-zero. [price: $0.02/call USDC via x402]

Input parameters:

- `prompt` (string, required): Image prompt

### `image_status` (~41 tokens)

image status

Poll image-gen job status by job ID. Returns image base64 PNG when COMPLETED. [free]

Input parameters:

- `job` (string, required): Job ID from image_gen

### `pii_guard` (~63 tokens)

pii guard

Detects PII (emails, phones, SSNs, credit cards) in any text with character spans. Compliance agents use this before processing user data. [price: $0.001/call USDC via x402]

Input parameters:

- `text` (string, required): Input text

### `prompt_guard` (~58 tokens)

prompt guard

Scores prompt-injection / jailbreak risk for LLM inputs. Agent builders use this to sanitize user inputs before hitting their LLM. [price: $0.01/call USDC via x402]

Input parameters:

- `text` (string, required): Input text

### `hallucination_check` (~66 tokens)

hallucination check

Entailment scoring: does the provided context support this claim? Research agents use this to self-check outputs. [price: $0.001/call USDC via x402]

Input parameters:

- `claim` (string, required): Claim to check
- `context` (string, required): Evidence/context text

### `json_guard` (~58 tokens)

json guard

Validates JSON, detects PII inside values, reports schema stats. Pipeline agents use this as a data-quality gate. [price: $0.001/call USDC via x402]

Input parameters:

- `json` (string, required): JSON text to validate

### `sweep` (~64 tokens)

One verify-loop lane: confidence-labeled findings on any topic. The flagship teaser — full sweeps at $0.50-5 ship when this crosses BUILD. [price: $0.05/call USDC via x402]

Input parameters:

- `topic` (string, required): Research topic

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/net-thirdmade-shelf/shelf#diagnostics

## Score history

- 2026-09-20: 71
- 2026-09-19: 70
- 2026-09-18: 70
- 2026-09-17: 69
- 2026-09-16: 69
- 2026-09-15: 68
- 2026-09-14: 68
- 2026-09-13: 67
- 2026-09-12: 67
- 2026-09-11: 66
- 2026-09-10: 66
- 2026-09-09: 66
- 2026-09-08: 65
- 2026-09-07: 65
- 2026-09-06: 64
- 2026-09-05: 64
- 2026-09-04: 63
- 2026-09-03: 63
- 2026-09-02: 62
- 2026-09-01: 62
- 2026-08-31: 62
- 2026-08-30: 62

## Common questions

### What is the ThirdMade Shelf MCP server?

ThirdMade Shelf is an MCP server listed in the public MCP registry as net.thirdmade/shelf. 26 pay-per-call tools for agents: scrape, verify, guards, crypto. x402 USDC on Base. This page covers its hosted endpoint (https://shelf.thirdmade.net/mcp).

### Is the ThirdMade Shelf MCP server safe to use?

ThirdMade Shelf scores 71 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 ThirdMade Shelf MCP server expose?

ThirdMade Shelf exposes 26 tools: robots, llms_txt, page_meta, domain_facts, link_graph, and 21 more. Their descriptions and schemas cost roughly 1,475 tokens of context every time the server is loaded.

### Does the ThirdMade Shelf MCP server require authentication?

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

### Is the ThirdMade Shelf MCP server still maintained?

ThirdMade Shelf 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.

## Links

- Remote endpoint: https://shelf.thirdmade.net/mcp
- Website: https://thirdmade.net/
- Changelog RSS feed: https://verifymcp.io/servers/net-thirdmade-shelf/shelf.xml
- Changelog JSON feed: https://verifymcp.io/servers/net-thirdmade-shelf/shelf.json
- HTML version of this page: https://verifymcp.io/servers/net-thirdmade-shelf/shelf