Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Tools for Agents

REMOTE · API.TOOLSFORAGENTS.TOOLS · SCANNED SEP 20

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

0 this week 77 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability73
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 3469 tokens (~32/item across 108 items; 107 tools + 1 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage75
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 26% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 4 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "truncate_context" implies "truncate" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 109 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Tools for Agents MCP server?

Tools for Agents is a hosted endpoint at https://api.toolsforagents.tools/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · api.toolsforagents.tools

# add to Claude Code
claude mcp add --transport http max124vip-dev-tools-for-agents 'https://api.toolsforagents.tools/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "max124vip-dev-tools-for-agents": {
      "url": "https://api.toolsforagents.tools/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "max124vip-dev-tools-for-agents": {
      "type": "http",
      "url": "https://api.toolsforagents.tools/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.max124vip-dev-tools-for-agents]
url = "https://api.toolsforagents.tools/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "max124vip-dev-tools-for-agents": {
      "type": "remote",
      "url": "https://api.toolsforagents.tools/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add max124vip-dev-tools-for-agents --url 'https://api.toolsforagents.tools/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  max124vip-dev-tools-for-agents:
    url: "https://api.toolsforagents.tools/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "max124vip-dev-tools-for-agents": {
      "Transport": "http",
      "Url": "https://api.toolsforagents.tools/mcp"
    }
  }
}
# add to Vellum
assistant mcp add max124vip-dev-tools-for-agents -t streamable-http -u 'https://api.toolsforagents.tools/mcp'
// mcp.json
{
  "mcpServers": {
    "max124vip-dev-tools-for-agents": {
      "type": "http",
      "url": "https://api.toolsforagents.tools/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 17 Sept 26 0
    • New tool “book_ocr” functional
  • 10 Sept 26 +54
    • Injection markers: unverified → pass security
    • Stability: unverified → pass security
    • HSTS header: fail → pass security
    • Transport: fail → pass security
    • Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 106 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. security
    • Endpoint reachability: not serving MCP → reachable functional
    • Tool coverage: unverified → 100 functional
    • Schema quality: unverified → 100 functional
    • MCP protocol: unverified → pass functional
  • 9 Sept 26 −54
    • Endpoint reachability: reachable → not serving MCP security
    • Stability: pass → unverified security
    • Tool safety: pass → unverified security
    • Transport: pass → fail security
    • HSTS header: pass → fail security
    • Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the tool list to see what that exposes. security
    • Schema quality: 100 → unverified functional
    • Capabilities: pass → unverified functional
    • Tool coverage: 100 → unverified functional
  • 29 Aug 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • New tool “rdap” functional
    • New tool “wayback” functional
  • 26 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Aug 26 +3
    • Stability: 0.97 → pass security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “list_tools” rewrote its description, which is the text the model reads security
    • The server now declares the “resources” capability functional
    • First check of Schema quality: 100 functional
    • New resource “orient” functional
    • New tool “orient” functional
  • 24 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Probed https://api.toolsforagents.tools/mcp/ · Declared URL https://api.toolsforagents.tools/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=toolsforagents.tools CN=WE1,O=Google Trust Services,C=US 24 Jul 2026 22 Oct 2026 ECDSA 256 ECDSA-SHA256 22aadd89450d7b4b13008121d392d6fa
SANs: toolsforagents.tools, *.toolsforagents.tools
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of api.toolsforagents.tools. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
tools. present 13831 8 Verified
toolsforagents.tools. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 3 probes
Transport URL Outcome Status Location
streamable-http https://api.toolsforagents.tools/mcp Redirected 307 https://api.toolsforagents.tools/mcp/
streamable-http · followed https://api.toolsforagents.tools/mcp/ Verified 200
http (plaintext) http://api.toolsforagents.tools/mcp HTTPS enforced 301 https://api.toolsforagents.tools/mcp
MCP tools · 107 exposed · ~3,303 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
advisor ~31

Agent Advisor — workflow + cost estimate (free).

NameTypeReqDescription
goalstringyes
optimizerstring

No output schema declared.

No examples provided.

agent_research ~32

Research: search → extract → summarize.

NameTypeReqDescription
max_sourcesinteger
querystringyes

No output schema declared.

No examples provided.

base64_decode ~27

Decode base64 to text

NameTypeReqDescription
encodedstringyesBase64 string to decode

No output schema declared.

No examples provided.

base64_encode ~26

Encode text to base64

NameTypeReqDescription
textstringyesPlain text to encode

No output schema declared.

No examples provided.

batch_extract ~28

Batch extract URLs (async).

NameTypeReqDescription
urlsarrayyes
webhookstring

No output schema declared.

No examples provided.

book_ocr ~122

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

NameTypeReqDescription
auto_retry_dpiboolean
dpinumber
end_pageinteger
enginestring
languagesarray
multi_passboolean
preprocessboolean
profilestring
start_pageinteger
urlstringyes
use_text_layerboolean

No output schema declared.

No examples provided.

browser_interact ~35

Playwright browser automation.

NameTypeReqDescription
stepsarrayyes
timeoutinteger
urlstringyes

No output schema declared.

No examples provided.

cache_url ~23

Cached extract (0 units on hit).

NameTypeReqDescription
urlstringyes

No output schema declared.

No examples provided.

chunk_text ~37

Split text into RAG chunks.

NameTypeReqDescription
chunk_sizeinteger
overlapinteger
textstringyes

No output schema declared.

No examples provided.

compare_texts ~47

Compare two texts or URLs.

NameTypeReqDescription
text_astring
text_bstring
url_astring
url_bstring

No output schema declared.

No examples provided.

content_hash ~31

Content fingerprint sha256/md5

NameTypeReqDescription
algorithmstring
textstringyesInput text

No output schema declared.

No examples provided.

crawl ~27

Crawl site (async).

NameTypeReqDescription
max_pagesinteger
urlstringyes

No output schema declared.

No examples provided.

crp_feedback ~70

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

NameTypeReqDescription
capability_idstringyes
cost_usdnumber
executor_idstringyes
latency_msinteger
outcomestringyes
resolution_idstringyes

No output schema declared.

No examples provided.

crp_resolve ~62

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

NameTypeReqDescription
capabilitystringOptional explicit capability ID
goalstringyesTask description
inputsobjectKnown inputs (url, text, query, …)

No output schema declared.

No examples provided.

crypto_invoke ~37

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

NameTypeReqDescription
operationstringyes
paramsobject

No output schema declared.

No examples provided.

csv_parse ~48

Parse CSV/TSV into rows and records

NameTypeReqDescription
delimiterstringField delimiter
has_headerboolean
textstringyesRaw CSV/TSV text

No output schema declared.

No examples provided.

dedupe_text ~33

Remove near-duplicate passages

NameTypeReqDescription
textsarrayyesList of text passages
thresholdnumber

No output schema declared.

No examples provided.

diff_url ~21

Compare cached vs live page.

NameTypeReqDescription
urlstringyes

No output schema declared.

No examples provided.

dns_lookup ~49

DNS A/MX/TXT lookup

NameTypeReqDescription
domainstringyesDomain name (e.g. example.com)
record_typestringDNS record type: A, MX, TXT, …

No output schema declared.

No examples provided.

dry_run ~22

Probe URL before extract (free).

NameTypeReqDescription
urlstringyes

No output schema declared.

No examples provided.

embed_text ~26

Generate text embeddings.

NameTypeReqDescription
modelstring
textstringyes

No output schema declared.

No examples provided.

entity_extract ~26

Extract emails, URLs, phones, dates

NameTypeReqDescription
textstringyesInput text

No output schema declared.

No examples provided.

estimate_cost ~35

Estimate API units (free).

NameTypeReqDescription
countinteger
textstring
toolstringyes

No output schema declared.

No examples provided.

extract_emails ~22

Extract email addresses

NameTypeReqDescription
textstringyesInput text

No output schema declared.

No examples provided.

extract_json ~20

Structured JSON from URL.

NameTypeReqDescription
urlstringyes

No output schema declared.

No examples provided.

extract_links ~28

List links from page.

NameTypeReqDescription
same_hostboolean
urlstringyes

No output schema declared.

No examples provided.

extract_outline ~35

Page outline H1–H3 + word_count.

NameTypeReqDescription
max_headingsinteger
urlstringyes

No output schema declared.

No examples provided.

extract_pdf ~22

Extract text from a PDF URL.

NameTypeReqDescription
urlstringyes

No output schema declared.

No examples provided.

extract_phones ~22

Extract phone numbers

NameTypeReqDescription
textstringyesInput text

No output schema declared.

No examples provided.

extract_query ~29

Answer a question using page content.

NameTypeReqDescription
querystringyes
urlstringyes

No output schema declared.

No examples provided.

extract_schema ~22

Structured fields from JSON-LD.

NameTypeReqDescription
urlstringyes

No output schema declared.

No examples provided.

extract_url ~45

Extract main content from a webpage URL.

NameTypeReqDescription
formatstring
include_linksboolean
modestring
urlstringyes

No output schema declared.

No examples provided.

fallback_chain ~30

Try primary tool then fallbacks.

NameTypeReqDescription
fallbacksarray
primaryobjectyes

No output schema declared.

No examples provided.

feed_parse ~21

Parse RSS/Atom feed.

NameTypeReqDescription
urlstringyes

No output schema declared.

No examples provided.

hash_text ~24

SHA256 and MD5 hash

NameTypeReqDescription
textstringyesInput text

No output schema declared.

No examples provided.

html_clean ~23

Strip HTML to clean text

NameTypeReqDescription
htmlstringyesRaw HTML

No output schema declared.

No examples provided.

html_to_markdown ~22

Convert HTML to Markdown.

NameTypeReqDescription
htmlstringyes

No output schema declared.

No examples provided.

image_describe ~21

Describe image (vision).

NameTypeReqDescription
urlstringyes

No output schema declared.

No examples provided.

job_status ~20

Poll async job.

NameTypeReqDescription
job_idstringyes

No output schema declared.

No examples provided.

json_flatten ~31

Flatten nested JSON

NameTypeReqDescription
datayesJSON object or array to flatten
prefixstring

No output schema declared.

No examples provided.

json_ld ~21

JSON-LD from URL.

NameTypeReqDescription
urlstringyes

No output schema declared.

No examples provided.

json_parse ~25

Parse and validate JSON text

NameTypeReqDescription
textstringyesJSON text to parse

No output schema declared.

No examples provided.

keyword_extract ~30

Top keywords by frequency

NameTypeReqDescription
textstringyesInput text
top_kinteger

No output schema declared.

No examples provided.

language_detect ~23

Detect language (heuristic)

NameTypeReqDescription
textstringyesInput text

No output schema declared.

No examples provided.

line_split ~30

Split text into lines

NameTypeReqDescription
min_lengthinteger
textstringyesInput text

No output schema declared.

No examples provided.

list_chains ~38

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

NameTypeReqDescription
domainstring
goalstring

No output schema declared.

No examples provided.

list_tools ~26

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

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

map_site ~27

Discover site URLs.

NameTypeReqDescription
max_urlsinteger
urlstringyes

No output schema declared.

No examples provided.

markdown_parse ~26

Split Markdown frontmatter, headings, links

NameTypeReqDescription
textstringyesMarkdown document

No output schema declared.

No examples provided.

memory_search ~34

Search session memory.

NameTypeReqDescription
limitinteger
querystringyes
session_idstringyes

No output schema declared.

No examples provided.

Common questions

What is the Tools for Agents MCP server?

Tools for Agents is an MCP server listed in the public MCP registry as io.github.max124vip-dev/tools-for-agents. Decision Layer for AI Agents, 58+ tools, Advisor, MCP. Free key: POST /v1/register {}. This page covers its hosted endpoint (https://api.toolsforagents.tools/mcp).

Is the Tools for Agents MCP server safe to use?

Tools for Agents scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Tools for Agents MCP server expose?

Tools for Agents exposes 107 tools: orient, extract_url, extract_pdf, embed_text, ocr_image, and 102 more. Their descriptions and schemas cost roughly 3,303 tokens of context every time the server is loaded.

Does the Tools for Agents MCP server require authentication?

No. We connected to Tools for Agents without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Tools for Agents MCP server still maintained?

Tools for Agents is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.