Tools for Agents is an MCP server with 106 tools an agent can call, among them advisor, agent_research, base64_decode. It answers at https://api.toolsforagents.tools/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 5 of 7 times since 11 September 2026; the last check, on 10 November 2026, succeeded.
Decision Layer for AI Agents — 58+ tools, Advisor, MCP. Free key: POST /v1/register {}.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
advisor | Agent Advisor — workflow + cost estimate (free). Inputs: goal, optimizer |
agent_research | Research: search → extract → summarize. Inputs: query, max_sources |
base64_decode | Decode base64 to text Inputs: encoded |
base64_encode | Encode text to base64 Inputs: text |
batch_extract | Batch extract URLs (async). Inputs: urls, webhook |
browser_interact | Playwright browser automation. Inputs: url, steps, timeout |
cache_url | Cached extract (0 units on hit). Inputs: url |
chunk_text | Split text into RAG chunks. Inputs: text, chunk_size, overlap |
compare_texts | Compare two texts or URLs. Inputs: text_a, text_b, url_a, url_b |
content_hash | Content fingerprint sha256/md5 Inputs: text, algorithm |
crawl | Crawl site (async). Inputs: url, max_pages |
crp_feedback | CRP post-execution feedback — improves discovery ranking (free). Inputs: resolution_id, capability_id, executor_id, outcome, latency_ms, cost_usd |
crp_resolve | Quality Capability Discovery — resolve goal to ranked routes + invocation JSON (free). Inputs: goal, capability, inputs |
crypto_invoke | Cryptographic operations (BIP39, wallets, signatures, hashes). Inputs: operation, params |
csv_parse | Parse CSV/TSV into rows and records Inputs: text, delimiter, has_header |
dedupe_text | Remove near-duplicate passages Inputs: texts, threshold |
diff_url | Compare cached vs live page. Inputs: url |
dns_lookup | DNS A/MX/TXT lookup Inputs: domain, record_type |
dry_run | Probe URL before extract (free). Inputs: url |
embed_text | Generate text embeddings. Inputs: text, model |
entity_extract | Extract emails, URLs, phones, dates Inputs: text |
estimate_cost | Estimate API units (free). Inputs: tool, text, count |
extract_emails | Extract email addresses Inputs: text |
extract_json | Structured JSON from URL. Inputs: url |
extract_links | List links from page. Inputs: url, same_host |
extract_outline | Page outline H1–H3 + word_count. Inputs: url, max_headings |
extract_pdf | Extract text from a PDF URL. Inputs: url |
extract_phones | Extract phone numbers Inputs: text |
extract_query | Answer a question using page content. Inputs: url, query |
extract_schema | Structured fields from JSON-LD. Inputs: url |
extract_url | Extract main content from a webpage URL. Inputs: url, format, mode, include_links |
fallback_chain | Try primary tool then fallbacks. Inputs: primary, fallbacks |
feed_parse | Parse RSS/Atom feed. Inputs: url |
hash_text | SHA256 and MD5 hash Inputs: text |
html_clean | Strip HTML to clean text Inputs: html |
html_to_markdown | Convert HTML to Markdown. Inputs: html |
image_describe | Describe image (vision). Inputs: url |
job_status | Poll async job. Inputs: job_id |
json_flatten | Flatten nested JSON Inputs: data, prefix |
json_ld | JSON-LD from URL. Inputs: url |
json_parse, keyword_extract, language_detect, line_split, list_chains, list_tools, map_site, markdown_parse, memory_search, memory_store, merge_records, monitor_url, normalize_dates, ocr_image, ocr_table, ocr_table_url, ocr_url, orient, page_links_external, page_metadata, page_peek, pdf_metadata, pdf_split, pii_detect, plan, rdap, read_url, readability, readability_score, redirect_trace, regex_extract, rerank_docs, research_topic, retrieve, robots_parse, run_chain, run_mission, screenshot, sentiment_score, seo_audit, sitemap_parse, source_credibility, ssl_check, summarize_text, table_extract, text_diff, text_similarity, transcribe_audio, translate_text, truncate_context, url_normalize, validate_domain, validate_email, validate_iban, validate_ip, validate_phone, validate_url, validate_uuid, verify_fact, wayback, web_search, word_stats, workflow_stateful, x402_info, xml_parse, youtube_transcript
Every block below points at https://api.toolsforagents.tools/mcp. Pick your client and copy.
claude mcp add --transport http tools-for-agents https://api.toolsforagents.tools/mcp
{
"mcpServers": {
"tools-for-agents": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.toolsforagents.tools/mcp"]
}
}
}{
"mcpServers": {
"tools-for-agents": {
"url": "https://api.toolsforagents.tools/mcp"
}
}
}{
"servers": {
"tools-for-agents": {
"type": "http",
"url": "https://api.toolsforagents.tools/mcp"
}
}
}{
"context_servers": {
"tools-for-agents": {
"url": "https://api.toolsforagents.tools/mcp"
}
}
}{
"mcpServers": {
"tools-for-agents": {
"serverUrl": "https://api.toolsforagents.tools/mcp"
}
}
}{
"mcpServers": {
"tools-for-agents": {
"url": "https://api.toolsforagents.tools/mcp"
}
}
}name: Tools for Agents
version: 0.0.1
schema: v1
mcpServers:
- name: Tools for Agents
type: streamable-http
url: https://api.toolsforagents.tools/mcp{
"mcpServers": {
"tools-for-agents": {
"httpUrl": "https://api.toolsforagents.tools/mcp"
}
}
}{
"mcpServers": {
"tools-for-agents": {
"type": "http",
"url": "https://api.toolsforagents.tools/mcp"
}
}
}{
"mcpServers": {
"tools-for-agents": {
"url": "https://api.toolsforagents.tools/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.toolsforagents.tools%2Fmcp&type=streamable_http&id=tools-for-agents&name=Tools%20for%20Agents
It answered our last check on 10 November 2026 in 527 ms. Over 7 checks since 11 September 2026 it answered 5. Status here comes from Neuronto's own probes, not from the publisher.
106, as returned by the server's own tools/list on 15 September 2026: advisor, agent_research, base64_decode, base64_encode, batch_extract, browser_interact, cache_url, chunk_text, and 98 more.
It answered our last check on 10 November 2026 in 527 ms. Over 7 checks since 11 September 2026 it answered 5.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.toolsforagents.tools/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.max124vip-dev. Endpoint host: api.toolsforagents.tools. ARD identifier: urn:air:io.github.max124vip-dev:mcp:tools-for-agents.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.