mcpbeat Sign in

Tools for Agents MCP Server

by max124vip-dev Your server? Claim it
answering

Tools for Agents is answering right now. Last checked 7 min ago. It exposes 107 tools. Last commit 3 Sep 2026.

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

Uptime history 48 days of history · worst day 64%
48 days agonow
100.0%
Uptime 24h
92 of 92 checks
107
Tools
read from the server
725 ms
Response time
average over 24h
2
Stars
last commit 3 Sep 2026

What changed 5

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 25 August 2026. No other catalogue keeps this.

16 Sep a tool appeared book_ocr
28 Aug 2 tools appeared rdap, wayback
25 Aug a tool appeared orient
25 Aug a tool description was rewritten list_tools

Tools for Agents does not always answer

Over the last week it answered 97.5% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 7 min ago.

run in your terminal
claude mcp add tools-for-agents --transport http https://api.toolsforagents.tools/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "tools-for-agents": {
      "url": "https://api.toolsforagents.tools/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.tools-for-agents]
url = "https://api.toolsforagents.tools/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "tools-for-agents": {
      "url": "https://api.toolsforagents.tools/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "tools-for-agents": {
      "url": "https://api.toolsforagents.tools/mcp"
    }
  }
}

Available tools 107

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

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

Endpoints

URLTransportStateLatencyChecked
https://api.toolsforagents.tools/mcp streamable-http answering 753 ms 7 min ago

Alternatives to Tools for Agents

same job, measured the same way
ToolAPI
by toolapi

Free public MCP for AI agents — 193 tools, 44 workflows. No API key.

193 tools answering
Trusgent MCP
by trusgent

Trusgent MCP — Trust Layer for AI agents. HK registry + Agent Cards. Default: get_merged_profile.

12 tools answering
C
Data
by thinair

PostgreSQL, MySQL, and SQL Server in one session. 26 read-only MCP tools for AI agents.

answering
VedaVisor Vedic Astrology MCP
by dchhill

Professional Vedic astrology tools for AI agents via MCP.

22 tools answering
Neural Memory
by nhadaututtheky

Persistent memory for AI agents — 55 MCP tools, spreading activation recall.

47 installs/wk local only
Frugal
by brainsparker

The open routing layer for AI tools: tool calls routed per policy, decision on every result.

40 installs/wk local only
Kr Groundtruth
by chloepark85

Korean fact-verification tools for AI agents: business registration, address, DART, apt prices, laws

8 tools answering
Agent Conductor
by icohangar-ops

AGENTS.md + skills MCP with CHP R0 gate and adversary decision tools.

24 installs/wk local only

Tools for Agents — questions

Answers built from our own checks of this server.

What can Tools for Agents do?
It exposes 107 tools, read directly from the server on our last check. Among them: advisor, agent_research, base64_decode, base64_encode, batch_extract, book_ocr and 101 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
What is Tools for Agents mostly used for?
Its tools cluster around extract, validate and ocr. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.
Is Tools for Agents working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 725 ms. The bar chart above shows every period we have measured.
How do I connect Tools for Agents?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Tools for Agents need an API key?
No. Tools for Agents completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 107 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Tools for Agents?
It answers our handshake in 725 ms on average, which is faster than 16% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is Tools for Agents open source?
We cannot say either way: written in Python and 2 stars on GitHub, but we could not determine the licence, and without one the code is not open source by default.