# Tools for Agents

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

- name: io.github.max124vip-dev/tools-for-agents
- version: 0.1.0
- connection class: R1 (autonomous)
- trust: 69/100
- quality: 76/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.max124vip-dev%2Ftools-for-agents
- tools: https://api.protogrid.dev/v1/servers/io.github.max124vip-dev%2Ftools-for-agents/tools

**An agent can connect on its own if it already holds `TOOLS_FOR_AGENTS_TOKEN`.** Remote endpoint behind a static API key or header. The registry never sees the value; the agent fills the placeholder.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "tools-for-agents": {
      "type": "http",
      "url": "https://api.toolsforagents.tools/mcp",
      "headers": {
        "Authorization": "Bearer ${TOOLS_FOR_AGENTS_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${TOOLS_FOR_AGENTS_TOKEN}`.

## Trust

- hygiene: 100
- liveness: 18
- freshness: 85
- provenance: 90
- drivers: +repository +namespace-matches-repo +website -unreachable(2 failures) ~updated-87d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 76/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 64 (weight 30)

- warn `tools.descriptions`: 13 of 107 tools have a description under 20 characters
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: language_detect (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); validate_uuid (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); extract_links (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 4,849 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 107, about 4,849 tokens to load them all
- tool set hash: c7faa39cd67d2b73655353d6164150cf
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.max124vip-dev/tools-for-agents.svg)](https://protogrid.dev/servers/io.github.max124vip-dev/tools-for-agents)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://api.toolsforagents.tools/mcp (streamable-http, auth api_key ${TOOLS_FOR_AGENTS_TOKEN}, reachable false, uptime30d 0.95614034)

## Packages

_none_

## Tools (107)

- `advisor`: Agent Advisor — workflow + cost estimate (free).
- `agent_research`: Research: search → extract → summarize.
- `base64_decode`: Decode base64 to text
- `base64_encode`: Encode text to base64
- `batch_extract`: Batch extract URLs (async).
- `book_ocr`: Book OCR v2: historical scans, ensemble EasyOCR+Tesseract, deskew, columns, Latin normalize, auto DPI retry.
- `browser_interact`: Playwright browser automation.
- `cache_url`: Cached extract (0 units on hit).
- `chunk_text`: Split text into RAG chunks.
- `compare_texts`: Compare two texts or URLs.
- `content_hash`: Content fingerprint sha256/md5
- `crawl`: Crawl site (async).
- `crp_feedback`: CRP post-execution feedback — improves discovery ranking (free).
- `crp_resolve`: Quality Capability Discovery — resolve goal to ranked routes + invocation JSON (free).
- `crypto_invoke`: Cryptographic operations (BIP39, wallets, signatures, hashes).
- `csv_parse`: Parse CSV/TSV into rows and records
- `dedupe_text`: Remove near-duplicate passages
- `diff_url`: Compare cached vs live page.
- `dns_lookup`: DNS A/MX/TXT lookup
- `dry_run`: Probe URL before extract (free).
- `embed_text`: Generate text embeddings.
- `entity_extract`: Extract emails, URLs, phones, dates
- `estimate_cost`: Estimate API units (free).
- `extract_emails`: Extract email addresses
- `extract_json`: Structured JSON from URL.
- `extract_links`: List links from page.
- `extract_outline`: Page outline H1–H3 + word_count.
- `extract_pdf`: Extract text from a PDF URL.
- `extract_phones`: Extract phone numbers
- `extract_query`: Answer a question using page content.
- `extract_schema`: Structured fields from JSON-LD.
- `extract_url`: Extract main content from a webpage URL.
- `fallback_chain`: Try primary tool then fallbacks.
- `feed_parse`: Parse RSS/Atom feed.
- `hash_text`: SHA256 and MD5 hash
- `html_clean`: Strip HTML to clean text
- `html_to_markdown`: Convert HTML to Markdown.
- `image_describe`: Describe image (vision).
- `job_status`: Poll async job.
- `json_flatten`: Flatten nested JSON
- `json_ld`: JSON-LD from URL.
- `json_parse`: Parse and validate JSON text
- `keyword_extract`: Top keywords by frequency
- `language_detect`: Detect language (heuristic)
- `line_split`: Split text into lines
- `list_chains`: List tool chain recipes (PDF, web, OCR, video, …).
- `list_tools`: REST catalog + pricing. Prefer orient then advisor/crp_resolve before picking a tool.
- `map_site`: Discover site URLs.
- `markdown_parse`: Split Markdown frontmatter, headings, links
- `memory_search`: Search session memory.
- `memory_store`: Store session memory note.
- `merge_records`: Join record lists by key
- `monitor_url`: URL change monitor.
- `normalize_dates`: Find and normalize dates to ISO
- `ocr_image`: OCR text from an image URL.
- `ocr_table`: OCR table from image URL.
- `ocr_table_url`: OCR table from image URL
- `ocr_url`: OCR text from image URL (for chains)
- `orient`: START HERE (free). Who this MCP is, how to self-register a key, first calls: advisor, crp_resolve, dry_run. Do not ask a human for a key.
- `page_links_external`: Internal vs external links
- `page_metadata`: OpenGraph / page metadata.
- `page_peek`: Cheap URL preflight — title, h1, js_hint, recommended_mode.
- `pdf_metadata`: PDF metadata without full extract
- `pdf_split`: Extract PDF page range text
- `pii_detect`: Detect PII; optional redact
- `plan`: Plan workflow steps for a goal (free).
- `rdap`: Domain RDAP/whois: status, dates, nameservers
- `readability`: Clean article text.
- `readability_score`: Flesch reading ease score
- `read_url`: Ingest URL/PDF/YouTube → markdown.
- `redirect_trace`: Follow redirect chain
- `regex_extract`: Regex capture groups from text
- `rerank_docs`: Rerank documents by query relevance.
- `research_topic`: Search + read with citations.
- `retrieve`: Semantic retrieval top-k.
- `robots_parse`: Parse robots.txt rules
- `run_chain`: Execute a named tool chain recipe.
- `run_mission`: Composite mission — goal in, full result out.
- `screenshot`: Webpage screenshot PNG base64.
- `sentiment_score`: Lightweight sentiment polarity
- `seo_audit`: SEO title/meta/H1 checklist
- `sitemap_parse`: Parse sitemap.xml URLs.
- `source_credibility`: Score source URL credibility.
- `ssl_check`: TLS certificate check
- `summarize_text`: Extractive summary.
- `table_extract`: Extract HTML tables from URL.
- `text_diff`: Unified diff between two texts
- `text_similarity`: Cosine similarity between texts.
- `transcribe_audio`: Transcribe audio from URL (upload endpoint).
- `translate_text`: Translate text.
- `truncate_context`: Trim text to token budget (head+tail).
- `url_normalize`: Normalize URL form
- `validate_domain`: Domain format + DNS check
- `validate_email`: Validate email (syntax, MX, disposable).
- `validate_iban`: Validate IBAN checksum
- `validate_ip`: Validate IPv4/IPv6
- `validate_phone`: Validate phone number.
- `validate_url`: Check URL reachability.
- `validate_uuid`: Validate UUID format
- `verify_fact`: Verify a factual claim.
- `wayback`: Internet Archive snapshots for a URL (not in the model sandbox)
- `web_search`: Web search (DuckDuckGo).
- `word_stats`: Word, char, line counts
- `workflow_stateful`: Run multi-step tool chain with $refs.
- `x402_info`: x402 wallet pricing and setup info (no auth).
- `xml_parse`: Parse XML and extract tag values
- `youtube_transcript`: YouTube captions/transcript.