// SCAN REPORT

Yanifend

18 tools. 10 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 2 Jul 2026

10 can modify or destroy data

8 read-only

18 tools total

Community server · catalogue entry verified 02/07/2026

How to control Yanifend ↓

TOOL MAP

What Yanifend exposes to your agents

Read (8) Write / Execute (8) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Yanifend tools

Destructive · High delete_question The tool performs an irreversible deletion operation on questionary data. Destructive · Medium delete_question_option This tool permanently removes data (an answer option) that cannot be restored without re-creation. Write · Medium create_hosted_form The tool creates a new hosted form resource (/f/{slug}) which is a reversible write operation. Write · High create_personage This tool creates new resources (questionary, personage character, and API key) which are reversible via deletion operations (like delete_question visible on the same server).

10 of Yanifend's 18 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Yanifend

PolicyLayer is an MCP gateway — it sits between your AI agents and Yanifend, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_question": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "clone_questionary": {
    "limits": [
      {
        "counter": "clone_questionary_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_allowed_domains": {
    "limits": [
      {
        "counter": "get_allowed_domains_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Yanifend — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON YANIFEND →

Instant setup, no code required.

FULL CATALOGUE

All 18 Yanifend tools

DESTRUCTIVE 2 tools

Destructive delete_question Delete a question (fails if it is the last one in the form). Destructive delete_question_option Remove an answer option from a choice-style question.

WRITE 8 tools

Write clone_questionary Copy ALL questions + options from one personage Write create_hosted_form Create a shareable hosted form (/f/{slug}) for a personage — an alternative to embedding the widget. Write create_personage Create a NEW personage — a fresh questionary plus its own character and an embeddable API key. This is how you Write create_question Add a new question to a personage Write create_question_option Add an answer option. actionType ∈ CONTINUE, CLOSE, NOTIFY_MANAGER, GOTO_QUESTION (actionPayload = target Write reorder_question_options Reorder a question Write update_question Edit a question. Only the fields you pass are changed. Supports RATE scale (minVal/maxVal) and icon. Write update_question_option Edit an answer option. Only the fields you pass are changed; position moves it without delete/recreate.

READ 8 tools

Read get_allowed_domains Read the client Read get_company_profile Read the client Read get_embed_snippet Get the ready-to-paste embed (api key + widget URL + <script> tag) for ONE personage. Read list_answers Pull the latest collected answers for a personage Read list_integration_keys Get the embed credentials for every personage: id, name, public API key, widget script URL and a ready-to-past Read list_personages List the feedback personages (form characters) on the connected YaniFend site, with id and name. Read list_question_options List the answer options of a choice-style question, in render order. Read list_questions Read the questionary of a personage, ordered by step. Includes each question

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Yanifend

Can an AI agent delete data through the Yanifend MCP server? +

Yes. The Yanifend server exposes 2 destructive tools including delete_question, delete_question_option. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Yanifend? +

The Yanifend server has 8 write tools including clone_questionary, create_hosted_form, create_personage. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Yanifend.

How many tools does the Yanifend MCP server expose? +

18 tools across 3 categories: Destructive, Read, Write. 8 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on Yanifend? +

Register the Yanifend MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Yanifend tool call.

Deterministic rules across all 18 Yanifend tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON YANIFEND →

Instant setup, no code required.

18 Yanifend tools catalogued and risk-classified — across an index of 43,000+ MCP servers.