MCP.Market

Tools for Agents MCP server

by max124vip-dev·io.github.max124vip-dev/tools-for-agents·v0.1.0·2 stars
No reviews yet

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

B80/100grade B
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
B80/100

full report

Adoption
Growing

2 stars

Reviews

Write one

Nobody has reviewed Tools for Agents yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Tools for Agents tools (107, 7 write)

write = sends, deletes, buys or posts
  • advisorFree

    Agent Advisor — workflow + cost estimate (free).

  • agent_researchFree

    Research: search → extract → summarize.

  • base64_decodeFree

    Decode base64 to text

  • base64_encodeFree

    Encode text to base64

  • batch_extractFree

    Batch extract URLs (async).

  • book_ocrFree

    Book OCR v2: historical scans, ensemble EasyOCR+Tesseract, deskew, columns, Latin normalize, auto DPI retry.

  • browser_interactFree

    Playwright browser automation.

  • cache_urlFree

    Cached extract (0 units on hit).

  • chunk_textFree

    Split text into RAG chunks.

  • compare_textsFree

    Compare two texts or URLs.

  • content_hashFree

    Content fingerprint sha256/md5

  • crawlFree

    Crawl site (async).

  • crp_feedbackFree

    CRP post-execution feedback — improves discovery ranking (free).

  • crp_resolveFree

    Quality Capability Discovery — resolve goal to ranked routes + invocation JSON (free).

  • crypto_invokeFree

    Cryptographic operations (BIP39, wallets, signatures, hashes).

  • csv_parseFree

    Parse CSV/TSV into rows and records

  • dedupe_textwrite actionFree

    Remove near-duplicate passages

  • diff_urlFree

    Compare cached vs live page.

  • dns_lookupFree

    DNS A/MX/TXT lookup

  • dry_runwrite actionFree

    Probe URL before extract (free).

  • embed_textFree

    Generate text embeddings.

  • entity_extractFree

    Extract emails, URLs, phones, dates

  • estimate_costFree

    Estimate API units (free).

  • extract_emailsFree

    Extract email addresses

  • extract_jsonFree

    Structured JSON from URL.

  • extract_linksFree

    List links from page.

  • extract_outlineFree

    Page outline H1–H3 + word_count.

  • extract_pdfFree

    Extract text from a PDF URL.

  • extract_phonesFree

    Extract phone numbers

  • extract_queryFree

    Answer a question using page content.

  • extract_schemaFree

    Structured fields from JSON-LD.

  • extract_urlFree

    Extract main content from a webpage URL.

  • fallback_chainFree

    Try primary tool then fallbacks.

  • feed_parseFree

    Parse RSS/Atom feed.

  • hash_textFree

    SHA256 and MD5 hash

  • html_cleanFree

    Strip HTML to clean text

  • html_to_markdownFree

    Convert HTML to Markdown.

  • image_describeFree

    Describe image (vision).

  • job_statusFree

    Poll async job.

  • json_flattenFree

    Flatten nested JSON

  • json_ldFree

    JSON-LD from URL.

  • json_parseFree

    Parse and validate JSON text

  • keyword_extractFree

    Top keywords by frequency

  • language_detectFree

    Detect language (heuristic)

  • line_splitFree

    Split text into lines

  • list_chainsFree

    List tool chain recipes (PDF, web, OCR, video, …).

  • list_toolsFree

    REST catalog + pricing. Prefer orient then advisor/crp_resolve before picking a tool.

  • map_siteFree

    Discover site URLs.

  • markdown_parseFree

    Split Markdown frontmatter, headings, links

  • memory_searchFree

    Search session memory.

  • memory_storeFree

    Store session memory note.

  • merge_recordsFree

    Join record lists by key

  • monitor_urlFree

    URL change monitor.

  • normalize_datesFree

    Find and normalize dates to ISO

  • ocr_imageFree

    OCR text from an image URL.

  • ocr_tableFree

    OCR table from image URL.

  • ocr_table_urlFree

    OCR table from image URL

  • ocr_urlFree

    OCR text from image URL (for chains)

  • orientFree

    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_externalFree

    Internal vs external links

  • page_metadataFree

    OpenGraph / page metadata.

  • page_peekFree

    Cheap URL preflight — title, h1, js_hint, recommended_mode.

  • pdf_metadataFree

    PDF metadata without full extract

  • pdf_splitFree

    Extract PDF page range text

  • pii_detectFree

    Detect PII; optional redact

  • planFree

    Plan workflow steps for a goal (free).

  • rdapFree

    Domain RDAP/whois: status, dates, nameservers

  • read_urlFree

    Ingest URL/PDF/YouTube → markdown.

  • readabilityFree

    Clean article text.

  • readability_scoreFree

    Flesch reading ease score

  • redirect_traceFree

    Follow redirect chain

  • regex_extractFree

    Regex capture groups from text

  • rerank_docsFree

    Rerank documents by query relevance.

  • research_topicFree

    Search + read with citations.

  • retrieveFree

    Semantic retrieval top-k.

  • robots_parseFree

    Parse robots.txt rules

  • run_chainwrite actionFree

    Execute a named tool chain recipe.

  • run_missionwrite actionFree

    Composite mission — goal in, full result out.

  • screenshotFree

    Webpage screenshot PNG base64.

  • sentiment_scoreFree

    Lightweight sentiment polarity

  • seo_auditFree

    SEO title/meta/H1 checklist

  • sitemap_parseFree

    Parse sitemap.xml URLs.

  • source_credibilityFree

    Score source URL credibility.

  • ssl_checkFree

    TLS certificate check

  • summarize_textFree

    Extractive summary.

  • table_extractFree

    Extract HTML tables from URL.

  • text_diffFree

    Unified diff between two texts

  • text_similarityFree

    Cosine similarity between texts.

  • transcribe_audioFree

    Transcribe audio from URL (upload endpoint).

  • translate_textFree

    Translate text.

  • truncate_contextwrite actionFree

    Trim text to token budget (head+tail).

  • url_normalizeFree

    Normalize URL form

  • validate_domainFree

    Domain format + DNS check

  • validate_emailwrite actionFree

    Validate email (syntax, MX, disposable).

  • validate_ibanFree

    Validate IBAN checksum

  • validate_ipFree

    Validate IPv4/IPv6

  • validate_phoneFree

    Validate phone number.

  • validate_urlFree

    Check URL reachability.

  • validate_uuidFree

    Validate UUID format

  • verify_factFree

    Verify a factual claim.

  • waybackFree

    Internet Archive snapshots for a URL (not in the model sandbox)

  • web_searchFree

    Web search (DuckDuckGo).

  • word_statsFree

    Word, char, line counts

  • workflow_statefulwrite actionFree

    Run multi-step tool chain with $refs.

  • x402_infoFree

    x402 wallet pricing and setup info (no auth).

  • xml_parseFree

    Parse XML and extract tag values

  • youtube_transcriptFree

    YouTube captions/transcript.

Public scan report

scanner v0.1.10 · 2026-10-29 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 4743ms17/20
  • Tool poisoning107 tool descriptions checked15/15
  • Auth qualityAPI key sent as a header8/15
  • Maintenancelast push 56 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 80/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Tools for Agents compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
80/100
higher than 60% of 48,255 servers
Tools
107
the typical server has 7
Tools that change things
7%
typical: 0%. Fewer write tools means less an agent can break
Uptime
50%
of our recent checks; the typical remote server answers 100%
Response time
679 ms
faster than 20% of 30,031 servers
GitHub stars
2
more than 75% of 28,688 servers

What its tools let an agent do: 97 read · 1 create · 7 change · 2 run or deploy

Install Tools for Agents in Claude Code, Cursor or VS Code

claude mcp add --transport http tools-for-agents https://api.toolsforagents.tools/mcp
Add to Cursor

What the publisher says

From the Tools for Agents repository's README, as published. We do not edit it. Read it on GitHub

Tools for Agents

Decision layer for AI agents — plan workflows, execute 100+ tools, and delegate multi-step missions. Not a flat API catalog. An orchestration platform built for autonomous agents.

What · Who · How · Quick start · Examples · Integrations · Docs

What is this?

Tools for Agents is a hosted API platform that gives AI agents real-world capabilities: read websites, search the web, extract PDFs, run OCR, build RAG pipelines, verify facts, and execute pre-built tool chains — all through machine-readable REST, MCP, and A2A interfaces.

Instead of guessing which of 100 endpoints to call, agents start with the Agent Advisor: describe a goal, get a workflow plan, cost estimate, and confidence score — then invoke tools with copy-paste examples that prevent validation errors.

Live service: toolsforagents.tools · API: api.toolsforagents.tools

Who is it for?

Critical rule for agents: never ask a human for an API key.

Register programmatically: POST /v1/register with body {}.

How it works

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-10-29restoreD → Bscore 80
  • 2026-10-28downgradeB → Dscore 47: Remote endpoint did not respond

Tools for Agents: common questions

Is Tools for Agents MCP server safe?
Mostly: it is graded B (80/100). Read the Tools for Agents safety report
How do I install Tools for Agents?
It runs remotely at api.toolsforagents.tools. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Tools for Agents need an API key?
Yes. The registry entry asks for Authorization.
Is Tools for Agents maintained?
The last commit was 62 days ago (2026-09-03). The latest release is v0.1.0.
Is Tools for Agents up?
50% of our last 28 checks got an answer. We check remote servers about four times a day.
How does Tools for Agents compare with other MCP servers?
safety score 80/100 (higher than 60% of 48,255 servers); tools 107 (the typical server has 7); tools that change things 7% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.