# Toolbox (remote · toolbox.allthepossibles.com)

Small tools for agent builders: AI-writing tells, tools/list token cost, CLAUDE.md lint, and more.

- Trust score: 70/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-22

## Components

- remote · `toolbox.allthepossibles.com`: 70/100 (this document), [markdown](https://verifymcp.io/servers/com-allthepossibles-toolbox/toolbox.md), [page](https://verifymcp.io/servers/com-allthepossibles-toolbox/toolbox)

## Channel facts

- Endpoint: `https://toolbox.allthepossibles.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - 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**: 72/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1600 tokens (~114/item across 14 items; 14 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 84% 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 14 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 15 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 Toolbox MCP server?

Toolbox is a hosted endpoint at https://toolbox.allthepossibles.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.

### Claude

```bash
claude mcp add --transport http com-allthepossibles-toolbox 'https://toolbox.allthepossibles.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-allthepossibles-toolbox": {
      "url": "https://toolbox.allthepossibles.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-allthepossibles-toolbox": {
      "type": "http",
      "url": "https://toolbox.allthepossibles.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-allthepossibles-toolbox]
url = "https://toolbox.allthepossibles.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-allthepossibles-toolbox": {
      "type": "remote",
      "url": "https://toolbox.allthepossibles.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-allthepossibles-toolbox --url 'https://toolbox.allthepossibles.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-allthepossibles-toolbox:
    url: "https://toolbox.allthepossibles.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-allthepossibles-toolbox": {
      "Transport": "http",
      "Url": "https://toolbox.allthepossibles.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-allthepossibles-toolbox -t streamable-http -u 'https://toolbox.allthepossibles.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-allthepossibles-toolbox": {
      "type": "http",
      "url": "https://toolbox.allthepossibles.com/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.

### 2026-10-22 (score 70, +1)

- [functional] New tool “lint_mcp_tools”

### 2026-10-20 (score 69, +6)

- [security improvement] HTTPS: unverified → pass
- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 64% → 83%
- [functional improvement] Stability: unverified → 0.03
- [functional] New tool “check_headers”
- [functional] New tool “check_page_meta”
- [functional] New tool “check_sitemap”
- [functional] New tool “decode_jwt”
- [functional] New tool “explain_cron”
- [functional] New tool “json_to_schema”
- [functional] New tool “scrub_env”
- [functional] New tool “trace_redirects”

### 2026-10-19 (score 63)

First indexed and scored.

## MCP tools (14)

### `check_tells` (~99 tokens)

Check text for AI-writing tells (em-dashes, 'not just X but Y', rule-of-three lists, stock vocabulary like delve or seamlessly, hedge words, smart quotes, hidden Unicode) and return a score, each tell with its position, and a cleaned copy. Run it on anything you are about to publish on a human's behalf.

Input parameters:

- `text` (string, required): The text to check. Free tier: 3,000 chars.

### `manifest_cost` (~88 tokens)

Estimate what an MCP server's tools/list costs in tokens on every session start, per tool, with the three most expensive tools and flags for oversized descriptions, base64 blobs and echoed schemas. Pass a live Streamable HTTP endpoint or a tools array.

Input parameters:

- `tools` (array): Tool definitions, if the server is not reachable over HTTP
- `url` (string): Streamable HTTP MCP endpoint

### `lint_agent_md` (~91 tokens)

Lint a CLAUDE.md, AGENTS.md or MEMORY.md: line count against Claude Code's 200-line memory index cap, estimated tokens, duplicate lines, contradicting rules, leftover TODO markers, hidden characters, empty headings.

Input parameters:

- `filename` (string): e.g. CLAUDE.md or MEMORY.md; changes the severity of the line cap
- `text` (string, required): File contents

### `mcp_install_snippets` (~92 tokens)

Generate install snippets for an MCP endpoint (Claude Code, Claude Desktop, Cursor, Codex, VS Code, curl) and probe the endpoint once to confirm it answers initialize and tools/list.

Input parameters:

- `headerName` (string)
- `headerValue` (string)
- `name` (string): Server name to use in configs
- `probe` (boolean)
- `url` (string, required)

### `check_ai_crawlers` (~83 tokens)

Read a site's robots.txt and report which AI crawlers (GPTBot, ClaudeBot, Google-Extended, PerplexityBot, CCBot, Bytespider and more) are allowed, blocked or partially blocked; check for llms.txt and draft one from the site's metadata and sitemap.

Input parameters:

- `url` (string, required): Any URL on the site

### `check_headers` (~91 tokens)

Fetch a URL once and grade its response headers: HSTS, Content-Security-Policy, X-Content-Type-Options, frame control, Referrer-Policy, Permissions-Policy, Cache-Control, cookie Secure/HttpOnly/SameSite flags, and server version leaks. Returns a grade, a score and the exact header to add for each gap.

Input parameters:

- `url` (string, required): The page to fetch

### `check_page_meta` (~83 tokens)

Fetch a URL and report what crawlers and link unfurlers see: title and meta description with lengths, canonical, lang, viewport, robots meta, h1s, Open Graph and Twitter card tags, favicon, JSON-LD types, the resulting preview card, and findings for anything missing or too long.

Input parameters:

- `url` (string, required): The page to fetch

### `json_to_schema` (~113 tokens)

Turn a JSON sample (or an array of samples of the same shape) into a JSON Schema draft 2020-12 and a TypeScript type. Infers required vs optional keys across samples, nullable fields, integer vs number, date/email/uri/uuid formats, and small enums. Use it to draft an MCP tool inputSchema from an example payload.

Input parameters:

- `json` (string, required): The JSON text. Free tier: 20,000 chars.
- `name` (string): Type name, default Root

### `explain_cron` (~129 tokens)

Explain a five-field cron expression in plain English, list the next runs in UTC, and warn about the cases Cloudflare Workers, GitHub Actions and crontab handle differently (nicknames, six fields, day-of-month plus day-of-week, sub-5-minute intervals, day 31).

Input parameters:

- `count` (integer): How many next runs to list, 1 to 20, default 5
- `expression` (string, required): e.g. 0 */6 * * 1-5
- `from` (string): ISO date to compute next runs from, default now

### `scrub_env` (~159 tokens)

Scrub a .env file into a safe .env.example: every value is blanked or replaced with a placeholder that keeps its shape (postgres://USER:PASSWORD@HOST/DB). Returns the example, the secrets found (AWS, GitHub, Stripe, Slack, Google, OpenAI, Anthropic, Resend, SendGrid, Twilio, Cloudflare, JWTs, private keys, database URLs, high-entropy strings) by key, kind and line with only the first 4 characters and the length, and findings for duplicate keys, non-UPPER_SNAKE names, unbalanced quotes, export prefixes and trailing spaces.

Input parameters:

- `text` (string, required): The .env file contents. Free tier: 20,000 chars.

### `trace_redirects` (~116 tokens)

Trace a URL's redirect chain hop by hop (up to 10 hops, 8 s each) with status, location, timing and scheme per hop. Flags chains over two redirects, loops, HTTPS-to-HTTP downgrades, 302s used for www or https canonicalisation, dropped paths or query strings, cross-domain moves, meta-refresh or JS redirects on a 200, and a final page that is not 200.

Input parameters:

- `url` (string, required): URL to trace, e.g. http://example.com

### `check_sitemap` (~150 tokens)

Check a site's sitemaps: discovers them from robots.txt, /sitemap.xml and /sitemap_index.xml, reads index files one level deep (20 children max), counts URLs per file and per host, summarises lastmod, and fetches a sample of URLs (HEAD, then GET) to count the ones that are not 200. Flags a missing sitemap, no robots.txt entry, over 50,000 URLs, other hosts, http URLs on https sites and missing lastmod.

Input parameters:

- `sample` (integer): How many sitemap URLs to fetch, default 10, max 25 on free and 100 on Pro
- `url` (string, required): Any URL on the site

### `decode_jwt` (~126 tokens)

Decode a JWT's header and payload without verifying the signature (it never takes a secret). Returns the claims with iat, nbf and exp as ISO times, a plain-text expiresIn, issuer, subject and audience, and findings: alg none, HS* with a URL-like kid, missing or distant exp, expired, nbf or iat in the future, payload over 4 KB, sensitive field names, and jku or x5u pointing off-site.

Input parameters:

- `token` (string, required): The JWT, three dot-separated parts. A leading Bearer is ignored.

### `lint_mcp_tools` (~138 tokens)

Lint the tools an MCP server lists, from the model's side of the wire: names that break Claude's ^[a-zA-Z0-9_-]{1,64}$ rule, duplicate names, missing or near-identical descriptions, instruction-like text in a description, arguments with no description, required arguments missing from properties, destructive-sounding tools with no destructiveHint, and unbounded free-text arguments on them. Pass a live Streamable HTTP endpoint or a tools array.

Input parameters:

- `tools` (array): Tool definitions, if the server is not reachable over HTTP
- `url` (string): Streamable HTTP MCP endpoint

## Diagnostics

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

## Score history

- 2026-10-22: 70
- 2026-10-21: 69
- 2026-10-20: 69
- 2026-10-19: 63

## Common questions

### What is the Toolbox MCP server?

Toolbox is an MCP server listed in the public MCP registry as com.allthepossibles/toolbox. Small tools for agent builders: AI-writing tells, tools/list token cost, CLAUDE.md lint, and more. This page covers its hosted endpoint (https://toolbox.allthepossibles.com/mcp).

### Is the Toolbox MCP server safe to use?

Toolbox scores 70 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 Toolbox MCP server expose?

Toolbox exposes 14 tools: check_tells, manifest_cost, lint_agent_md, mcp_install_snippets, check_ai_crawlers, and 9 more. Their descriptions and schemas cost roughly 1,558 tokens of context every time the server is loaded.

### Does the Toolbox MCP server require authentication?

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

### Is the Toolbox MCP server still maintained?

Toolbox 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://toolbox.allthepossibles.com/mcp
- Website: https://toolbox.allthepossibles.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-allthepossibles-toolbox/toolbox.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-allthepossibles-toolbox/toolbox.json
- HTML version of this page: https://verifymcp.io/servers/com-allthepossibles-toolbox/toolbox