A2A Governance Bridge MCP server. Tools: verify agent compliance, authorize a2a transaction, get trust registry. Built by MEOK AI Labs.
Free
Nothing to run from here
Iteratools is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
Open Installation—
p95 latency
—
call success
local
runs on your machine
—
calls last 7d
What it does
MCP server for IteraTools — AI agent tools API. Image, video, web scraping, search, TTS, WhatsApp and more.
Quickstart
# 1 — run it from where its publisher ships it
npx -y mcp-iteratools
# 2 — ask your agent something
> MCP server for IteraTools — AI agent tools API. Image, video, web scraping, search, TTS, WhatsApp and more.
Iteratools is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
FRAll 1 server
fredpsantos331 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Iteratools as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. It is scanned, signed and pinned to the version you choose — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add iteratools-mcp -- npx -y mcp-iteratoolsReconnect, or start a new session, and the tools appear in the model’s tool list.
Free to install, and it runs from its publisher’s own package: no account, no key, no card.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
74 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Generate an image using Flux 1.1 Pro AI model. Returns image URL.
Takes no parameters.
Example callreturns →
Remove background from an image URL. Returns PNG with transparent background.
Takes no parameters.
Example callreturns →
Generate a 5-second video from a prompt using Kling v1.6 Pro.
Takes no parameters.
Example callreturns →
Scrape any URL and return clean markdown text. Works on JS-rendered pages.
Takes no parameters.
Example callreturns →
Search the web and return real-time results with titles, URLs and snippets.
Takes no parameters.
Example callreturns →
Convert text to natural-sounding speech. Returns audio URL.
Takes no parameters.
Example callreturns →
Take a screenshot of any website URL. Returns image URL.
Takes no parameters.
Example callreturns →
Generate a QR code for any text or URL. Returns image URL.
Takes no parameters.
Example callreturns →
Get current weather and forecast for any location.
Takes no parameters.
Example callreturns →
Get current cryptocurrency price and 24h stats.
Takes no parameters.
Example callreturns →
Validate an email address — checks format, MX records, disposable status.
Takes no parameters.
Example callreturns →
Send a transactional email via SMTP. Specify recipient, subject, and body (plain text or HTML). Price: $0.002/request. Note: currently disabled (503) until enabled.
Takes no parameters.
Example callreturns →
Send a WhatsApp message to a phone number. Initiates with a template. Returns conversation_id for follow-up replies.
Takes no parameters.
Example callreturns →
Send a free-text reply within an active WhatsApp conversation (within 24h window).
Takes no parameters.
Example callreturns →
Translate text from one language to another.
Takes no parameters.
Example callreturns →
Transcribe audio from a public URL using OpenAI Whisper. Returns plain text transcript.
Takes no parameters.
Example callreturns →
Transcribe audio from a URL using Whisper. Returns text transcript.
Takes no parameters.
Example callreturns →
Generate a spreadsheet (XLSX or CSV) from data. Returns file URL.
Takes no parameters.
Example callreturns →
Lookup DNS records for a domain.
Takes no parameters.
Example callreturns →
Get WHOIS registration information for a domain.
Takes no parameters.
Example callreturns →
Get public holidays for a country and year.
Takes no parameters.
Example callreturns →
Extract frames from a video URL. Returns array of image URLs.
Takes no parameters.
Example callreturns →
Transcribe video from URL (YouTube or direct MP4). Downloads audio with yt-dlp, transcribes with OpenAI Whisper. Returns text, language, duration and segments.
Takes no parameters.
Example callreturns →
Get geolocation data for an IP address. Omit ip to use the caller\
Takes no parameters.
Example callreturns →
Convert an amount between currencies using real-time exchange rates.
Takes no parameters.
Example callreturns →
Generate a chart image (bar, line, pie, doughnut). Returns image URL.
Takes no parameters.
Example callreturns →
Extract structured content from a URL using an optional JSON schema.
Takes no parameters.
Example callreturns →
Crawl a website using BFS and extract content (title, markdown, links) from multiple pages. Useful for documentation scraping, site analysis, and content extraction at scale. Price: $0.010 per job.
Takes no parameters.
Example callreturns →
Automate browser actions on a URL (click, fill, navigate, etc.). Optionally returns a screenshot.
Takes no parameters.
Example callreturns →
Execute code in a sandboxed environment. Supports Python, JavaScript, and Bash.
Takes no parameters.
Example callreturns →
Analyze the sentiment of a text (positive, negative, neutral) with confidence score.
Takes no parameters.
Example callreturns →
Summarize a text or URL content into a concise summary.
Takes no parameters.
Example callreturns →
Analyze text statistics: word count, character count, sentences, paragraphs, reading time, unique words. $0.001 per request.
Takes no parameters.
Example callreturns →
Shorten a URL, optionally with a custom code. Returns shortened URL.
Takes no parameters.
Example callreturns →
Generate a PDF from HTML content or a URL. Returns PDF file URL.
Takes no parameters.
Example callreturns →
Extract text content from a PDF URL.
Takes no parameters.
Example callreturns →
Resize or convert an image from a URL. Returns new image URL.
Takes no parameters.
Example callreturns →
Compress an image with quality control. Supports JPEG, PNG, WebP, and AVIF formats. Optionally resize if wider than max_width. Returns compressed image as base64 data URL with original_size, compressed_size, reduction_pct, format, width, height.
Takes no parameters.
Example callreturns →
Validate and format a phone number. Returns validity, type (MOBILE/FIXED_LINE/etc), country, country name, and E.164/international/national formats. Uses libphonenumber-js — no external API, instant response.
Takes no parameters.
Example callreturns →
Generate vector embeddings for text using OpenAI text-embedding-3-small (default, 1536 dims) or text-embedding-3-large (3072 dims). Supports single string or batch of up to 100 strings. Returns float arrays ready for semantic search, RAG pipelines, and clustering.
Takes no parameters.
Example callreturns →
Generate a fast, low-cost image from a prompt. Returns image URL.
Takes no parameters.
Example callreturns →
Extract text from an image URL using OCR.
Takes no parameters.
Example callreturns →
Read data from a Google Spreadsheet. Returns headers (first row) and all rows as key-value objects. Supports optional range parameter (e.g. Sheet1!A1:Z100). Price: $0.002/request.
Takes no parameters.
Example callreturns →
Write or append rows to an existing Google Spreadsheet. Supports overwrite (default) and append modes. Price: $0.003/request.
Takes no parameters.
Example callreturns →
Create a new Google Spreadsheet with optional title and column headers. The sheet is automatically made publicly viewable. Returns spreadsheet_id and shareable URL. Price: $0.005/request.
Takes no parameters.
Example callreturns →
Fetch details for any GitHub repository: stars, forks, primary language, topics, open issues, default branch, and last commit (SHA, message, author, date). Works on public repos without a token. Provide a GitHub PAT via the token param to increase rate limits to 5,000 req/h. Price: $0.001/request.
Takes no parameters.
Example callreturns →
Create a new GitHub issue on any repository you have write access to. Supports title (required), markdown body, and labels. Requires a GitHub Personal Access Token (PAT) with repo scope for private repos or public_repo scope for public repos. Returns the issue number and URL. Price: $0.002/request.
Takes no parameters.
Example callreturns →
Read and decode the text content of any file in a GitHub repository. Automatically decodes GitHub\
Takes no parameters.
Example callreturns →
Convert documents between formats using LibreOffice and Pandoc. Supports DOCX→PDF, PPTX→PDF, HTML→PDF, PDF→DOCX, MD→HTML, MD→PDF, HTML→MD. Supply document via URL or inline content (text or base64 for binary formats). Returns a public URL to the converted file. Price: $0.003/conversion.
Takes no parameters.
Example callreturns →
Generate a cryptographic hash of any text. Supports MD5, SHA-1, SHA-256, SHA-384, SHA-512. Returns both hex and base64 encodings. Uses Node.js native crypto — no external API, instant response. Perfect for fingerprinting content, integrity checks, or generating unique identifiers.
Takes no parameters.
Example callreturns →
Generate barcodes (Code128, Code39, EAN-13, EAN-8, UPC-A, ITF14, DataMatrix) — returns PNG as base64. Price: $0.001
Takes no parameters.
Example callreturns →
Chat with an LLM (GPT-4o-mini, Claude Haiku, or Gemini Flash) via a single API. Returns text response and token usage.
Takes no parameters.
Example callreturns →
Store or update a text document with vector embedding in a namespace (RAG store). Uses OpenAI text-embedding-3-small (1536 dims). Namespace is automatically isolated per API key — different users cannot access each other\
Takes no parameters.
Example callreturns →
Delete all stored vector embeddings in a namespace. This action is irreversible — all documents in the namespace are permanently deleted. Returns the count of deleted documents. Use this to reset agent memory between sessions, clear outdated knowledge bases, or comply with data deletion requests.
Takes no parameters.
Example callreturns →
Store a key-value pair in persistent memory, isolated per API key. Value can be any JSON-serializable data. Automatically generates embedding for semantic search via /memory/kv/search. Namespace is optional (default:
Takes no parameters.
Example callreturns →
Retrieve a previously stored key-value pair by key and namespace. Returns 404 if the key does not exist. Use to read back agent state, user preferences, or any persisted data.
Takes no parameters.
Example callreturns →
Delete a specific key from persistent KV memory. Returns whether the key existed before deletion. Use to clean up stale data, remove expired session data, or delete specific entries.
Takes no parameters.
Example callreturns →
Search your stored key-value pairs by semantic similarity using OpenAI embeddings + cosine similarity. Finds the most relevant entries for a natural language query. Great for finding related memories, facts, or data points without knowing the exact key.
Takes no parameters.
Example callreturns →
Validate, format, minify, or analyze JSON. Modes: validate (syntax check with error position), format (pretty-print with configurable indent), minify (compact), stats (key count, depth, type map), get (extract value by dot-bracket path like
Takes no parameters.
Example callreturns →
Create a new event in Google Calendar. User must provide a valid OAuth2 access token with Google Calendar scope (https://www.googleapis.com/auth/calendar). Returns event_id, html_link, and status.
Takes no parameters.
Example callreturns →
List events from a Google Calendar for a date range. Returns events with id, summary, start, end, location, and attendee count.
Takes no parameters.
Example callreturns →
Check free/busy status of a Google Calendar using the Freebusy API. Returns list of busy time slots and whether the calendar is completely free.
Takes no parameters.
Example callreturns →
Delete an event from Google Calendar by event_id. This action is irreversible. Requires OAuth2 access token with write scope.
Takes no parameters.
Example callreturns →
Fetch and parse RSS/Atom feed URLs into structured JSON. Perfect for monitoring news, blogs, podcasts, and content feeds.
Takes no parameters.
Example callreturns →
Start a WhatsApp market research session. Send a questionnaire to multiple contacts and collect structured responses automatically. Sends first question immediately after greeting. Returns research_id to track progress.
Takes no parameters.
Example callreturns →
Get status of a WhatsApp research session (FREE, no auth required). Returns total contacts, how many have responded, and per-contact status.
Takes no parameters.
Example callreturns →
Get the structured report for a WhatsApp research session (FREE, no auth required). Returns all answers per contact with question-answer pairs and completion statistics.
Takes no parameters.
Example callreturns →
Generate professional PPTX presentations from JSON data with customizable themes (minimal/dark/corporate). Returns base64-encoded PPTX file ready to download.
Takes no parameters.
Example callreturns →
Agentic WhatsApp market research: pass a natural language task → agent discovers contacts on Google Maps, extracts questions via LLM (GPT-4o-mini), and runs full WhatsApp survey automatically. Returns research_id immediately (fully async). $0.050/contact, minimum $0.50/job.
Takes no parameters.
Example callreturns →
Check the status of a WhatsApp Research Agent job started with whatsapp_research_agent. Returns current phase (discovering/searching/researching/in_progress/error), contacts found, city, niche, questions, and inner research_id for polling with whatsapp_research_status.
Takes no parameters.
Example callreturns →
Send a Slack message via Incoming Webhook URL (simple, no OAuth scopes needed) or Bot Token (xoxb-..., requires channel). Supports plain text and Block Kit blocks. No credentials are stored. $0.001 per request.
Takes no parameters.
Example callreturns →
Read the latest messages from a Slack channel using a Bot Token with channels:history (public) or groups:history (private) scope. Returns messages with timestamp, user ID, and text. $0.002 per request.
Takes no parameters.
Example callreturns →
Create a new public or private Slack channel using a Bot Token with channels:manage (public) or groups:write (private) scope. Channel name is auto-sanitized to lowercase alphanumeric + hyphens. $0.002 per request.
Takes no parameters.
Example callreturns →
Pay-per-use AI agent tools API. 41+ tools: web scraping, image gen, video gen, TTS, WhatsApp, code execution, browser automation, and more. Pay per call from $0.001.
Takes no parameters.
Example callreturns →
Freeyour plan
$0 forever
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Iteratools costs nothing to install and nothing to call, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: $8.42
$16.58 left
ATrust score 99 / 100
Release 1.0.41 · scanned 26 Aug 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score99
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationrepo
Surface digestdfb31ca2703d3d9d6acaad71dfe98edd8b1a9d1c7e4c4cf8e02a961ffddfdbcf
Score vectorthreat 100 → client 99
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (3 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| iteratools | no tags | |
| IteraTools | no tags | |
| IteraTools MCP Server | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestdfb31ca2703d3d9d
Scanned2026-08-26
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Pinned to 1.0.41 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
1.0.41
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Iteratools in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes an account with 50 real tool calls against it.