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 {}.
How to connect
How to connect Tools for Agents to Claude
The server address to paste into Claude settings:
https://api.toolsforagents.tools/mcp
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect Tools for Agents to ChatGPT
The server address to paste into ChatGPT settings:
https://api.toolsforagents.tools/mcp
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect Tools for Agents to Cursor
The server address to paste into Cursor settings:
https://api.toolsforagents.tools/mcp
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
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. |