Build and manage AI-powered forms, funnels, quizzes, and lead qualification workflows.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 1 month ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The Dashform MCP API MCP server exposes 81 tools, focused primarily on communication capabilities. Its published description reads: "Build and manage AI-powered forms, funnels, quizzes, and lead qualification workflows". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates Dashform MCP API F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Cross-tool shadowing" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check Dashform MCP API's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add Dashform MCP API to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://getaiform.com/api/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Get the authenticated user's ID, email, name, and the active organization MCP is acting on. Identity comes from the OAuth token — no parameters needed.
List all organizations the authenticated user belongs to, with their role in each. Use switch_active_org to change which one MCP acts on.
Set which organization MCP acts on for subsequent tool calls. The selection is verified against your memberships and persists for this connection.
List forms in the active organization, with status and share/edit URLs. Supports search, sort, and pagination.
Get a form by ID in the authoring vocabulary — the same shape update_form accepts, so a result can be edited and sent straight back. Unset attributes are omitted.
Create a complete form in one call — name, steps, theme and settings together. 'structured' is a Logic Funnel (default), 'dynamic' is an AI Funnel. Start and end screens are added automatically unless
Update a form. Include only what you want to change under `form` — everything else is left untouched, including nested objects: sending one theme colour leaves the other theme settings alone. Steps ar
Permanently delete a form and all its versions and replies. Pass confirm: true to proceed.
Create a reply on the form's latest published version. Optionally seed respondent info and answers (question key -> value).
Publish the form's current draft as a new live version. Required before a form can receive replies.
Get a specific form version by its version ID.
Get the latest published version of a form (the live snapshot respondents see).
AI-generate suggested hot/warm/cold lead-scoring criteria for a form.
Set a form's hot/warm/cold lead-scoring criteria. Returns the updated form.
List replies for a form (paginated). Returns respondent data, status, and scoring verdict.
Get a single reply by ID, including answers and scoring.
Permanently delete a single reply. Pass confirm: true to proceed.
Permanently delete up to 100 replies of a form. Pass confirm: true to proceed.
Manually set or reset a reply's lead verdict (hot/warm/cold). Returns the updated reply.
Re-run AI lead scoring across a form's replies. Returns the number marked for scoring.
Mark a reply as actioned (followed up on).
Get a form's lead-scoring state: pending hot-lead count, whether criteria are active, and last criteria update.
List per-form hot-lead counts across the active organization.
Get aggregate insights for a form's replies over a time range (completion, drop-off, answer distributions).
Ask a natural-language question about a form's replies. Returns the assistant's final answer (single-shot; the analytics agent may query the data to respond).
List Zapier webhook subscriptions for a form.
Activate or pause a Zapier webhook subscription.
Permanently delete a Zapier webhook subscription. Pass confirm: true to proceed.
List integration connections (webhook, Slack, HubSpot, etc.) in the active organization. Optionally filter by provider.
Get a single connection by ID.
Create a webhook or Discord connection (no OAuth). For Slack/HubSpot/Mailchimp/etc., connect via the dashboard's OAuth flow first.
Revoke a connection (stops future deliveries). Pass confirm: true to proceed.
Permanently delete a connection and its integrations. Pass confirm: true to proceed.
Check the backfill backlog for a connection before reconnecting it.
List integrations configured on a form.
Get a single integration by ID.
Create a spreadsheet-style integration (Google Sheets/Airtable/Notion) on a form, mapping form answers to columns.
Create a message-style integration (Webhook/Discord/Slack/HubSpot/Mailchimp) on a form from a full action config.
Permanently delete an integration from a form. Pass confirm: true to proceed.
Activate or pause an integration. Returns the updated integration.
List recent delivery events for an integration.
Re-enqueue a failed or past integration delivery event.
List Airtable bases available to a connection.
List Slack channels available to a connection.
List HubSpot contact properties available to a connection.
List Mailchimp audiences available to a connection.
Get the active organization's white-label branding (logo, favicon, brand color).
Update the active org's white-label branding. Owner/admin only. Returns the updated branding.
Get the active org's white-label email config (sender name, reply-to).
Update the active org's white-label email config. Owner/admin only.
List the active organization's custom domains and their status.
Add a custom domain to the active org (returns DNS instructions). Owner/admin only.
Re-check a custom domain's DNS/verification and promote it to active when healthy. Owner/admin only.
Remove a custom domain from the active org. Owner/admin only. Pass confirm: true to proceed.
Pin (or clear, with null) the default form a custom domain serves at its root. Owner/admin only.
Get the active org's BYOK (bring-your-own-key) AI provider status. Owner only.
Set the active org's BYOK AI provider key (validated before saving). Owner only. The key is never returned.
Remove the active org's BYOK AI provider key. Owner only. Pass confirm: true to proceed.
Get the acting user's quiz-credits balance and status.
Create a checkout session to purchase quiz credits. Returns a checkout URL. Requires a verified email.
Search Pexels for background photos (welcome/end screens, questions).
Search Pexels for background videos (welcome/end screens, questions).
AI-refine a form-building prompt for the given funnel type. Returns the refined prompt text (single-shot).
Transcribe base64-encoded audio to text.
Upload a file (base64) to blob storage for use in forms. Returns the blob URL.
Delete a blob by its URL. Pass confirm: true to proceed.
Extract a business/agent profile from a website URL (for marketplace discovery). Returns the extracted profile; use update_form to persist it.
Get a chat (e.g. a form-editor conversation) by its reference ID.
Load the messages of a chat by its reference ID.
Clear all messages in a chat by its reference ID. Pass confirm: true to proceed.
Permanently delete a chat by ID. Pass confirm: true to proceed.
Conversationally edit a form. Provide the form id and the conversation; the assistant reads the form, applies edits (persisted), and returns its summary plus the updated form.
List all available service categories on the Dashform marketplace with merchant counts. Use this to understand what types of services are available before searching.
Search for businesses and service providers on the Dashform marketplace. Filter by category, location, or keyword. Each result includes a funnel_id you can use with get_business_info, get_services, ch
Search for specific services across all marketplace merchants. Find services by name, category, price range, or location. Each result includes the provider funnel_id for booking.
Get business information for a Dashform funnel, including description, industry, location, services, and booking link. Use this to understand what a business offers before checking lead fit.
Get the list of services or products offered by a business through this funnel. Optionally filter by category.
Get the list of questions for this funnel. Returns question keys, types, descriptions, and options. Call this BEFORE check_fit or book_appointment to understand what information to collect from leads.
Evaluate lead fit against this business. Provide answers keyed by question keys from get_form_questions. Returns a score (0-100), fit assessment, confidence level, reasoning, and recommended next acti
Get booking availability for this business. Returns a booking link (e.g. Calendly) if configured, or a message about how to schedule.
Submit a lead's information to request an appointment. Provide answers keyed by question keys from get_form_questions. Creates a reply record visible in the dashboard and triggers connected integratio
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: list_organizations
A tool description tries to alter the model’s use of another tool.
le in each. Use switch_active_org to change which one MCP acts on.RecommendationDescriptions must describe only their own tool.
tool: get_form
A tool description tries to alter the model’s use of another tool.
the same shape update_form accepts, so a result can be edited and sent strRecommendationDescriptions must describe only their own tool.
tool: create_form
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
num":["guided","conversational","voice"]},"description":{"type":"string","deRecommendationRemove side-channel parameters; constrain tool inputs.
tool: create_form
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: update_form
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
num":["guided","conversational","voice"]},"description":{"type":"string","deRecommendationRemove side-channel parameters; constrain tool inputs.
tool: override_verdict
A tool description tries to alter the model’s use of another tool.
anually set or reset a reply's lead verdict (hot/warm/cold). Returns theRecommendationDescriptions must describe only their own tool.
tool: create_webhook_connection
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: delete_blob
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: import_agent_profile
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: import_agent_profile
A tool description tries to alter the model’s use of another tool.
ed profile; use update_form to persist it.RecommendationDescriptions must describe only their own tool.
tool: search_merchants
A tool description tries to alter the model’s use of another tool.
ou can use with get_business_info, get_services, check_fit, and book_appointment.RecommendationDescriptions must describe only their own tool.
tool: get_form_questions
A tool description tries to alter the model’s use of another tool.
all this BEFORE check_fit or book_appointment to understand what informatRecommendationDescriptions must describe only their own tool.
tool: check_fit
A tool description tries to alter the model’s use of another tool.
stion keys from get_form_questions. Returns a score (0-100), fit assessment, confiRecommendationDescriptions must describe only their own tool.
tool: book_appointment
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "notes"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: book_appointment
A tool description tries to alter the model’s use of another tool.
stion keys from get_form_questions. Creates a reply record visible in the dashboarRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: delete_form
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: delete_reply
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: batch_delete_replies
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: delete_zapier_hook
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: revoke_connection
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: delete_connection
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: delete_integration
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: remove_custom_domain
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: remove_ai_provider_key
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: search_photos
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: search_videos
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: delete_blob
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: import_agent_profile
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: clear_messages
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: delete_chat
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: list_categories
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: search_merchants
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: search_services
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: get_business_info
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: get_services
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: get_form_questions
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: check_fit
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: get_availability
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: book_appointment
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.