# Tools for Agents (remote · api.toolsforagents.tools)

Decision Layer for AI Agents — 58+ tools, Advisor, MCP. Free key: POST /v1/register {}.

- Trust score: 62/100 (medium)
- Change this week: +8
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `api.toolsforagents.tools`: 62/100 (this document), [markdown](https://verifymcp.io/servers/max124vip-dev-tools-for-agents/api.md), [page](https://verifymcp.io/servers/max124vip-dev-tools-for-agents/api)

## Channel facts

- Endpoint: `https://api.toolsforagents.tools/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `0.1.0`

## 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 2026-08-03.

- **Endpoint Security**: 63/100
  - 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 100 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.
  - 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**: 49/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 2899 tokens (~28/item across 100 items; 100 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 76/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 28% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http max124vip-dev-tools-for-agents https://api.toolsforagents.tools/mcp
```

### Codex

```toml
[mcp_servers.max124vip-dev-tools-for-agents]
url = "https://api.toolsforagents.tools/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "max124vip-dev-tools-for-agents": {
      "type": "remote",
      "url": "https://api.toolsforagents.tools/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add max124vip-dev-tools-for-agents --url https://api.toolsforagents.tools/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  max124vip-dev-tools-for-agents:
    url: "https://api.toolsforagents.tools/mcp"
```

### Other

```json
{
  "mcpServers": {
    "max124vip-dev-tools-for-agents": {
      "type": "http",
      "url": "https://api.toolsforagents.tools/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.

### 2026-08-03 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 60, +3)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 57, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 56, +2)

- [functional] Schema quality: poor → fair
- [functional] New tool “crp_feedback”
- [functional] New tool “crp_resolve”

### 2026-07-27 (score 54, +3)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 51)

First indexed and scored.

## MCP tools (100)

### `extract_url` (~30 tokens)

Extract main content from a webpage URL.

Input parameters:

- `format` (string)
- `url` (string, required)

### `extract_pdf` (~22 tokens)

Extract text from a PDF URL.

Input parameters:

- `url` (string, required)

### `embed_text` (~26 tokens)

Generate text embeddings.

Input parameters:

- `model` (string)
- `text` (string, required)

### `ocr_image` (~23 tokens)

OCR text from an image URL.

Input parameters:

- `url` (string, required)

### `validate_email` (~24 tokens)

Validate email (syntax, MX, disposable).

Input parameters:

- `email` (string, required)

### `crypto_invoke` (~37 tokens)

Cryptographic operations (BIP39, wallets, signatures, hashes).

Input parameters:

- `operation` (string, required)
- `params` (object)

### `html_to_markdown` (~22 tokens)

Convert HTML to Markdown.

Input parameters:

- `html` (string, required)

### `x402_info` (~20 tokens)

x402 wallet pricing and setup info (no auth).

### `list_tools` (~15 tokens)

List REST API tools and pricing.

### `web_search` (~30 tokens)

Web search (DuckDuckGo).

Input parameters:

- `max_results` (integer)
- `query` (string, required)

### `page_metadata` (~21 tokens)

OpenGraph / page metadata.

Input parameters:

- `url` (string, required)

### `chunk_text` (~37 tokens)

Split text into RAG chunks.

Input parameters:

- `chunk_size` (integer)
- `overlap` (integer)
- `text` (string, required)

### `text_similarity` (~28 tokens)

Cosine similarity between texts.

Input parameters:

- `model` (string)
- `texts` (array, required)

### `validate_phone` (~27 tokens)

Validate phone number.

Input parameters:

- `default_region` (string)
- `phone` (string, required)

### `youtube_transcript` (~29 tokens)

YouTube captions/transcript.

Input parameters:

- `languages` (array)
- `url` (string, required)

### `extract_query` (~29 tokens)

Answer a question using page content.

Input parameters:

- `query` (string, required)
- `url` (string, required)

### `summarize_text` (~28 tokens)

Extractive summary.

Input parameters:

- `max_sentences` (integer)
- `text` (string, required)

### `rerank_docs` (~31 tokens)

Rerank documents by query relevance.

Input parameters:

- `documents` (array, required)
- `query` (string, required)

### `translate_text` (~34 tokens)

Translate text.

Input parameters:

- `source_lang` (string)
- `target_lang` (string, required)
- `text` (string, required)

### `agent_research` (~32 tokens)

Research: search → extract → summarize.

Input parameters:

- `max_sources` (integer)
- `query` (string, required)

### `browser_interact` (~35 tokens)

Playwright browser automation.

Input parameters:

- `steps` (array, required)
- `timeout` (integer)
- `url` (string, required)

### `read_url` (~33 tokens)

Ingest URL/PDF/YouTube → markdown.

Input parameters:

- `chunk` (boolean)
- `url` (string, required)

### `research_topic` (~29 tokens)

Search + read with citations.

Input parameters:

- `max_results` (integer)
- `query` (string, required)

### `map_site` (~27 tokens)

Discover site URLs.

Input parameters:

- `max_urls` (integer)
- `url` (string, required)

### `estimate_cost` (~35 tokens)

Estimate API units (free).

Input parameters:

- `count` (integer)
- `text` (string)
- `tool` (string, required)

### `memory_store` (~35 tokens)

Store session memory note.

Input parameters:

- `key` (string, required)
- `session_id` (string, required)
- `value` (string, required)

### `memory_search` (~34 tokens)

Search session memory.

Input parameters:

- `limit` (integer)
- `query` (string, required)
- `session_id` (string, required)

### `validate_url` (~20 tokens)

Check URL reachability.

Input parameters:

- `url` (string, required)

### `extract_links` (~28 tokens)

List links from page.

Input parameters:

- `same_host` (boolean)
- `url` (string, required)

### `json_ld` (~21 tokens)

JSON-LD from URL.

Input parameters:

- `url` (string, required)

### `readability` (~18 tokens)

Clean article text.

Input parameters:

- `url` (string, required)

### `extract_schema` (~22 tokens)

Structured fields from JSON-LD.

Input parameters:

- `url` (string, required)

### `extract_json` (~20 tokens)

Structured JSON from URL.

Input parameters:

- `url` (string, required)

### `cache_url` (~23 tokens)

Cached extract (0 units on hit).

Input parameters:

- `url` (string, required)

### `retrieve` (~34 tokens)

Semantic retrieval top-k.

Input parameters:

- `documents` (array, required)
- `query` (string, required)
- `top_k` (integer)

### `screenshot` (~29 tokens)

Webpage screenshot PNG base64.

Input parameters:

- `full_page` (boolean)
- `url` (string, required)

### `batch_extract` (~28 tokens)

Batch extract URLs (async).

Input parameters:

- `urls` (array, required)
- `webhook` (string)

### `crawl` (~27 tokens)

Crawl site (async).

Input parameters:

- `max_pages` (integer)
- `url` (string, required)

### `job_status` (~20 tokens)

Poll async job.

Input parameters:

- `job_id` (string, required)

### `monitor_url` (~34 tokens)

URL change monitor.

Input parameters:

- `interval_hours` (integer)
- `url` (string, required)
- `webhook` (string)

### `compare_texts` (~47 tokens)

Compare two texts or URLs.

Input parameters:

- `text_a` (string)
- `text_b` (string)
- `url_a` (string)
- `url_b` (string)

### `ocr_table` (~22 tokens)

OCR table from image URL.

Input parameters:

- `url` (string, required)

### `image_describe` (~21 tokens)

Describe image (vision).

Input parameters:

- `url` (string, required)

### `transcribe_audio` (~25 tokens)

Transcribe audio from URL (upload endpoint).

Input parameters:

- `url` (string, required)

### `csv_parse` (~48 tokens)

Parse CSV/TSV into rows and records

Input parameters:

- `delimiter` (string): Field delimiter
- `has_header` (boolean)
- `text` (string, required): Raw CSV/TSV text

### `json_parse` (~25 tokens)

Parse and validate JSON text

Input parameters:

- `text` (string, required): JSON text to parse

### `xml_parse` (~37 tokens)

Parse XML and extract tag values

Input parameters:

- `tag` (string): Optional tag to extract values from
- `text` (string, required): XML text

### `markdown_parse` (~26 tokens)

Split Markdown frontmatter, headings, links

Input parameters:

- `text` (string, required): Markdown document

### `regex_extract` (~47 tokens)

Regex capture groups from text

Input parameters:

- `group` (integer)
- `max_matches` (integer)
- `pattern` (string, required): Regular expression
- `text` (string, required): Input text

### `keyword_extract` (~30 tokens)

Top keywords by frequency

Input parameters:

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

### `entity_extract` (~26 tokens)

Extract emails, URLs, phones, dates

Input parameters:

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

### `sentiment_score` (~21 tokens)

Lightweight sentiment polarity

Input parameters:

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

### `language_detect` (~23 tokens)

Detect language (heuristic)

Input parameters:

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

### `readability_score` (~24 tokens)

Flesch reading ease score

Input parameters:

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

### `text_diff` (~42 tokens)

Unified diff between two texts

Input parameters:

- `context_lines` (integer)
- `text_a` (string, required): First text
- `text_b` (string, required): Second text

### `dedupe_text` (~33 tokens)

Remove near-duplicate passages

Input parameters:

- `texts` (array, required): List of text passages
- `threshold` (number)

### `normalize_dates` (~25 tokens)

Find and normalize dates to ISO

Input parameters:

- `text` (string, required): Text containing dates

### `content_hash` (~31 tokens)

Content fingerprint sha256/md5

Input parameters:

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

### `pii_detect` (~31 tokens)

Detect PII; optional redact

Input parameters:

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

### `json_flatten` (~31 tokens)

Flatten nested JSON

Input parameters:

- `data` (required): JSON object or array to flatten
- `prefix` (string)

### `merge_records` (~41 tokens)

Join record lists by key

Input parameters:

- `key` (string, required): Join key field name
- `records_a` (array, required)
- `records_b` (array, required)

### `hash_text` (~24 tokens)

SHA256 and MD5 hash

Input parameters:

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

### `base64_encode` (~26 tokens)

Encode text to base64

Input parameters:

- `text` (string, required): Plain text to encode

### `base64_decode` (~27 tokens)

Decode base64 to text

Input parameters:

- `encoded` (string, required): Base64 string to decode

### `word_stats` (~24 tokens)

Word, char, line counts

Input parameters:

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

### `line_split` (~30 tokens)

Split text into lines

Input parameters:

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

### `extract_emails` (~22 tokens)

Extract email addresses

Input parameters:

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

### `extract_phones` (~22 tokens)

Extract phone numbers

Input parameters:

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

### `url_normalize` (~23 tokens)

Normalize URL form

Input parameters:

- `url` (string, required): URL to normalize

### `pdf_metadata` (~23 tokens)

PDF metadata without full extract

Input parameters:

- `url` (string, required): PDF URL

### `pdf_split` (~43 tokens)

Extract PDF page range text

Input parameters:

- `end_page` (integer): Last page (inclusive)
- `start_page` (integer)
- `url` (string, required): PDF URL

### `robots_parse` (~29 tokens)

Parse robots.txt rules

Input parameters:

- `timeout` (integer)
- `url` (string, required): Site URL

### `redirect_trace` (~37 tokens)

Follow redirect chain

Input parameters:

- `max_hops` (integer)
- `timeout` (integer)
- `url` (string, required): Starting URL

### `dns_lookup` (~49 tokens)

DNS A/MX/TXT lookup

Input parameters:

- `domain` (string, required): Domain name (e.g. example.com)
- `record_type` (string): DNS record type: A, MX, TXT, …

### `ssl_check` (~28 tokens)

TLS certificate check

Input parameters:

- `domain` (string, required): Hostname
- `port` (integer)

### `html_clean` (~23 tokens)

Strip HTML to clean text

Input parameters:

- `html` (string, required): Raw HTML

### `seo_audit` (~32 tokens)

SEO title/meta/H1 checklist

Input parameters:

- `timeout` (integer)
- `url` (string, required): Page URL

### `page_links_external` (~30 tokens)

Internal vs external links

Input parameters:

- `timeout` (integer)
- `url` (string, required): Page URL

### `validate_iban` (~25 tokens)

Validate IBAN checksum

Input parameters:

- `iban` (string, required): IBAN to validate

### `validate_ip` (~28 tokens)

Validate IPv4/IPv6

Input parameters:

- `ip` (string, required): IPv4 or IPv6 address

### `validate_domain` (~23 tokens)

Domain format + DNS check

Input parameters:

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

### `validate_uuid` (~21 tokens)

Validate UUID format

Input parameters:

- `uuid` (string, required): UUID string

### `ocr_url` (~27 tokens)

OCR text from image URL (for chains)

Input parameters:

- `url` (string, required): Image URL

### `ocr_table_url` (~27 tokens)

OCR table from image URL

Input parameters:

- `url` (string, required): Image URL with table

### `list_chains` (~38 tokens)

List tool chain recipes (PDF, web, OCR, video, …).

Input parameters:

- `domain` (string)
- `goal` (string)

### `run_chain` (~30 tokens)

Execute a named tool chain recipe.

Input parameters:

- `chain_id` (string, required)
- `inputs` (object)

### `run_mission` (~40 tokens)

Composite mission — goal in, full result out.

Input parameters:

- `async` (boolean)
- `goal` (string, required)
- `template` (string)

### `table_extract` (~21 tokens)

Extract HTML tables from URL.

Input parameters:

- `url` (string, required)

### `diff_url` (~21 tokens)

Compare cached vs live page.

Input parameters:

- `url` (string, required)

### `sitemap_parse` (~20 tokens)

Parse sitemap.xml URLs.

Input parameters:

- `url` (string, required)

### `feed_parse` (~21 tokens)

Parse RSS/Atom feed.

Input parameters:

- `url` (string, required)

### `verify_fact` (~27 tokens)

Verify a factual claim.

Input parameters:

- `claim` (string, required)
- `mode` (string)

### `plan` (~23 tokens)

Plan workflow steps for a goal (free).

Input parameters:

- `goal` (string, required)

### `dry_run` (~22 tokens)

Probe URL before extract (free).

Input parameters:

- `url` (string, required)

### `advisor` (~31 tokens)

Agent Advisor — workflow + cost estimate (free).

Input parameters:

- `goal` (string, required)
- `optimizer` (string)

### `crp_resolve` (~62 tokens)

Quality Capability Discovery — resolve goal to ranked routes + invocation JSON (free).

Input parameters:

- `capability` (string): Optional explicit capability ID
- `goal` (string, required): Task description
- `inputs` (object): Known inputs (url, text, query, …)

### `crp_feedback` (~70 tokens)

CRP post-execution feedback — improves discovery ranking (free).

Input parameters:

- `capability_id` (string, required)
- `cost_usd` (number)
- `executor_id` (string, required)
- `latency_ms` (integer)
- `outcome` (string, required)
- `resolution_id` (string, required)

### `workflow_stateful` (~25 tokens)

Run multi-step tool chain with $refs.

Input parameters:

- `steps` (array, required)

### `fallback_chain` (~30 tokens)

Try primary tool then fallbacks.

Input parameters:

- `fallbacks` (array)
- `primary` (object, required)

### `source_credibility` (~22 tokens)

Score source URL credibility.

Input parameters:

- `url` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/max124vip-dev-tools-for-agents/api#diagnostics

## Score history

- 2026-08-03: 62
- 2026-08-02: 61
- 2026-08-01: 61
- 2026-07-31: 60
- 2026-07-30: 57
- 2026-07-29: 56
- 2026-07-28: 56
- 2026-07-27: 54
- 2026-07-26: 51

## Links

- Remote endpoint: https://api.toolsforagents.tools/mcp
- Authorisation metadata: https://api.toolsforagents.tools/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/max124vip-dev/tools-for-agents
- Website: https://toolsforagents.tools/
- Changelog RSS feed: https://verifymcp.io/servers/max124vip-dev-tools-for-agents/api/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/max124vip-dev-tools-for-agents/api/changelog.json
- HTML version of this page: https://verifymcp.io/servers/max124vip-dev-tools-for-agents/api