Tools for Agents
Decision Layer for AI Agents — 58+ tools, Advisor, MCP.
Community: Submitted by a user or imported; check the owner before granting accessDegradedAPI key requiredGlobalFreeCan modify data
What it can do
What data it sees
Do you need an account
An API key from the service settings is required
Decision Layer for AI Agents — 58+ tools, Advisor, MCP. Free key: POST /v1/register {}.
Server tool list (107)
Raw names from tools/list. Only developers need these.
| 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. |
| extract_url | Extract main content from a webpage URL. |
| extract_pdf | Extract text from a PDF URL. |
| embed_text | Generate text embeddings. |
| ocr_image | OCR text from an image URL. |
| book_ocr | Book OCR v2: historical scans, ensemble EasyOCR+Tesseract, deskew, columns, Latin normalize, auto DPI retry. |
| validate_email | Validate email (syntax, MX, disposable). |
| crypto_invoke | Cryptographic operations (BIP39, wallets, signatures, hashes). |
| html_to_markdown | Convert HTML to Markdown. |
| x402_info | x402 wallet pricing and setup info (no auth). |
| list_tools | REST catalog + pricing. Prefer orient then advisor/crp_resolve before picking a tool. |
| web_search | Web search (DuckDuckGo). |
| page_metadata | OpenGraph / page metadata. |
| page_peek | Cheap URL preflight — title, h1, js_hint, recommended_mode. |
| extract_outline | Page outline H1–H3 + word_count. |
| truncate_context | Trim text to token budget (head+tail). |
| chunk_text | Split text into RAG chunks. |
| text_similarity | Cosine similarity between texts. |
| validate_phone | Validate phone number. |
| youtube_transcript | YouTube captions/transcript. |
| extract_query | Answer a question using page content. |
| summarize_text | Extractive summary. |
| rerank_docs | Rerank documents by query relevance. |
| translate_text | Translate text. |
| agent_research | Research: search → extract → summarize. |
| browser_interact | Playwright browser automation. |
| read_url | Ingest URL/PDF/YouTube → markdown. |
| research_topic | Search + read with citations. |
| map_site | Discover site URLs. |
| estimate_cost | Estimate API units (free). |
| memory_store | Store session memory note. |
| memory_search | Search session memory. |
| validate_url | Check URL reachability. |
| extract_links | List links from page. |
| json_ld | JSON-LD from URL. |
| readability | Clean article text. |
| extract_schema | Structured fields from JSON-LD. |
| extract_json | Structured JSON from URL. |
| cache_url | Cached extract (0 units on hit). |
| retrieve | Semantic retrieval top-k. |
| screenshot | Webpage screenshot PNG base64. |
| batch_extract | Batch extract URLs (async). |
| crawl | Crawl site (async). |
| job_status | Poll async job. |
| monitor_url | URL change monitor. |
| compare_texts | Compare two texts or URLs. |
| ocr_table | OCR table from image URL. |
| image_describe | Describe image (vision). |
| transcribe_audio | Transcribe audio from URL (upload endpoint). |
| csv_parse | Parse CSV/TSV into rows and records |
| json_parse | Parse and validate JSON text |
| xml_parse | Parse XML and extract tag values |
| markdown_parse | Split Markdown frontmatter, headings, links |
| regex_extract | Regex capture groups from text |
| keyword_extract | Top keywords by frequency |
| entity_extract | Extract emails, URLs, phones, dates |
| sentiment_score | Lightweight sentiment polarity |
| language_detect | Detect language (heuristic) |
| readability_score | Flesch reading ease score |
| text_diff | Unified diff between two texts |
| dedupe_text | Remove near-duplicate passages |
| normalize_dates | Find and normalize dates to ISO |
| content_hash | Content fingerprint sha256/md5 |
| pii_detect | Detect PII; optional redact |
| json_flatten | Flatten nested JSON |
| merge_records | Join record lists by key |
| hash_text | SHA256 and MD5 hash |
| base64_encode | Encode text to base64 |
| base64_decode | Decode base64 to text |
| word_stats | Word, char, line counts |
| line_split | Split text into lines |
| extract_emails | Extract email addresses |
| extract_phones | Extract phone numbers |
| url_normalize | Normalize URL form |
| pdf_metadata | PDF metadata without full extract |
| pdf_split | Extract PDF page range text |
| robots_parse | Parse robots.txt rules |
| redirect_trace | Follow redirect chain |
| dns_lookup | DNS A/MX/TXT lookup |
| ssl_check | TLS certificate check |
| wayback | Internet Archive snapshots for a URL (not in the model sandbox) |
| rdap | Domain RDAP/whois: status, dates, nameservers |
| html_clean | Strip HTML to clean text |
| seo_audit | SEO title/meta/H1 checklist |
| page_links_external | Internal vs external links |
| validate_iban | Validate IBAN checksum |
| validate_ip | Validate IPv4/IPv6 |
| validate_domain | Domain format + DNS check |
| validate_uuid | Validate UUID format |
| ocr_url | OCR text from image URL (for chains) |
| ocr_table_url | OCR table from image URL |
| list_chains | List tool chain recipes (PDF, web, OCR, video, …). |
| run_chain | Execute a named tool chain recipe. |
| run_mission | Composite mission — goal in, full result out. |
| table_extract | Extract HTML tables from URL. |
| diff_url | Compare cached vs live page. |
| sitemap_parse | Parse sitemap.xml URLs. |
| feed_parse | Parse RSS/Atom feed. |
| verify_fact | Verify a factual claim. |
| plan | Plan workflow steps for a goal (free). |
| dry_run | Probe URL before extract (free). |
| advisor | Agent Advisor — workflow + cost estimate (free). |
| crp_resolve | Quality Capability Discovery — resolve goal to ranked routes + invocation JSON (free). |
| crp_feedback | CRP post-execution feedback — improves discovery ranking (free). |
| workflow_stateful | Run multi-step tool chain with $refs. |
| fallback_chain | Try primary tool then fallbacks. |
| source_credibility | Score source URL credibility. |