// SCAN REPORT

FlowDot MCP Server

207 tools. 117 can modify or destroy data without limits.

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

Last updated:

117 can modify or destroy data
90 read-only
207 tools total

Community server · catalogue entry checked 22/07/2026

How to control FlowDot MCP Server ↓

TOOL MAP

What FlowDot MCP Server exposes to your agents

Read (90) Write / Execute (91) Destructive / Financial (26)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS
Critical Risk

The most dangerous FlowDot MCP Server tools

Destructive · High cancel_execution Cancelling a running execution irreversibly terminates it — the in-progress work is lost and cannot be resumed. Destructive · High delete_agent_character The tool irreversibly deletes an agent character and causes active sessions to fail. Destructive · High delete_app This tool irreversibly removes data (the app and all associated metadata) from the system. Destructive · High delete_app_file This tool irreversibly deletes data (app files) with no undo mechanism.

117 of FlowDot MCP Server's 207 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control FlowDot MCP Server

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

Deny destructive operations
{
  "browser_act": {
    "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
{
  "abandon_goal": {
    "limits": [
      {
        "counter": "abandon_goal_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "agent_chat": {
    "limits": [
      {
        "counter": "agent_chat_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register FlowDot MCP Server — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON FLOWDOT →

Instant setup, no code required.

FULL CATALOGUE

All 207 FlowDot MCP Server tools

DESTRUCTIVE 26 tools
Destructive browser_act Perform one UI action. action ∈ click | double_click | right_click | type | clear | press_key | scroll | hover Destructive cancel_execution Cancel a running workflow execution. Only works on executions with status Destructive delete_agent_character Permanently delete an agent character. Requires confirm: true. This is irreversible — any voice-call session i Destructive delete_app Permanently delete an app. This action cannot be undone. The app and all its associated data (comments, votes Destructive delete_app_file Delete a file from a multi-file FlowDot app. Permanently removes the file from the app. This action cannot be Destructive delete_connection Remove a connection between two nodes in a workflow. Destructive delete_custom_node Delete a custom node. This action cannot be undone. Destructive delete_goal Permanently delete a goal and all its tasks and milestones. Destructive delete_goal_milestone Delete a milestone from a goal. Destructive delete_goal_task Delete a task from a goal. Destructive delete_image Delete one of your uploaded images by id. Removes the stored file and frees the storage it used. Only your own Destructive delete_input_preset Delete an input preset. You can only delete presets you created. Destructive delete_knowledge_category Delete a knowledge base category. Documents in the category will become uncategorized (not deleted). Destructive delete_knowledge_document Permanently delete a document from your knowledge base. This removes the file and all associated chunks/embedd Destructive delete_node Delete a node from a workflow. This also removes all connections to/from the node. Destructive delete_recipe Permanently delete an agent recipe. This action cannot be undone. Destructive delete_recipe_step Delete a step from a recipe. References to this step will need to be updated. Destructive delete_recipe_store Delete a store from a recipe. Steps using this store will need to be updated. Destructive delete_workflow Permanently delete a workflow. This action cannot be undone. Only the workflow owner can delete it. Destructive email_delete Move an email message to trash. Subject to mailbox grant permissions. This is a soft delete (trash), not perma Destructive mcp__flowdot__delete_agent_toolkit Delete a toolkit permanently. WARNING: This cannot be undone. All tools, installations, and related data will Destructive mcp__flowdot__delete_toolkit_tool Delete a tool from a toolkit. WARNING: This cannot be undone. The tool will be permanently removed. Destructive mcp__flowdot__uninstall_toolkit Uninstall a toolkit from your account. Removes the installation and credential mapping (toolkit itself remain Destructive panic_clear Clear an active emergency stop for your account. Requires Destructive revoke_kb_access Revoke one of YOUR Knowledge-Base grants by its grant id (get it from \ Destructive unlink_property_kb_source Remove a Knowledge-Base source link from a property you own, by its link id (get the id from \
EXECUTE 14 tools
Execute browser_launch Open a web page in a real browser, OR launch an Electron app to QA it. Returns a session_id used by every othe Execute browser_navigate Navigate a browser session to a new URL. Blocked from reaching the internal FlowDot node server (hub-mode). Execute browser_sequence Run several actions in one call (fast, fewer round-trips). Each item is { action, target?, value? }. Execute browser_wait_for Wait until a selector or text appears (up to a timeout). Execute convert_document Convert a document to another format; the output extension sets the target. Supported: Execute email_send Send an email through a connected mailbox. Subject to mailbox grant permissions — Execute execute_workflow Execute a FlowDot workflow by ID. Use list_workflows first to get available workflow IDs. Execute mcp__flowdot__invoke_toolkit_tool Execute a tool from an installed toolkit. Runs the tool with provided inputs using your configured credential Execute mcp__flowdot__test_toolkit_installation Run a Test Connection diagnostic against an installed toolkit. Resolves the toolkit Execute panic_stop EMERGENCY STOP: Activates a sticky emergency stop for your account. Execute retry_execution Retry a failed workflow execution using the same inputs. Creates a new execution. Execute send_notification Send a notification message to the user via their configured COMMS channels (Telegram, Discord, Slack, Signal) Execute unlink_app_recipe Unlink a recipe from an app. The app can no longer trigger that recipe. Execute unlink_app_toolkit Unlink a toolkit from an app. After unlinking, the app will no longer be able to invoke that toolkit
WRITE 77 tools
Write abandon_goal Abandon a goal. Use this when a goal is no longer relevant but you want to keep it for record-keeping rather t Write add_connection Create a connection between two nodes in a workflow. Connects an output socket to an input socket. Write add_custom_node_comment Add a comment to a custom node. Can also be used to reply to existing comments. Write add_goal_milestone Add a milestone to a goal. Milestones are progress markers with optional target dates. Write add_goal_task Add a task to a goal. Task types: - research — gather information - draft — write content - code — write or m Write add_shared_result_comment Add a comment to a shared execution result. Write add_workflow_comment Add a comment to a workflow. You can only comment on public workflows or your own workflows. Write browser_close Close one browser/Electron session and free its resources. Write browser_fill_form Fill many form fields in one call, each with the correct interaction for its type (react-select, autocomplete, Write checkpoint_recipe Create a manual checkpoint snapshot of a recipe. Unlike auto-snapshots (which coalesce within 60 seconds), a c Write clone_app Clone a public app to your library. Creates a private copy that you can customize. The cloned app will: - Be Write complete_goal Mark a goal as completed. Write complete_goal_milestone Mark a goal milestone as completed. Write copy_custom_node Copy a public custom node to your library. The copy will be private by default. Write create_agent_character Create a new agent character (voice-call persona). All voice/STT/LLM/persona fields are required — the Hub rej Write create_app_file Create a new file in a multi-file FlowDot app. Creates a new file with the specified path and content. File Write create_document Create a new document at a local path; the file extension sets the format Write create_goal Create a new persistent goal. Goals are long-running objectives managed in the FlowDot Hub. After creating a Write create_input_preset Create a new input preset (community input) for a workflow. This allows you to share pre-configured input valu Write create_knowledge_category Create a new category to organize documents in your knowledge base. Categories help group related documents fo Write create_shared_result Create a shareable link for a workflow execution result. This allows you to share specific execution outputs w Write create_workflow Create a new empty workflow with a name and optional description. The workflow will be private by default. Write duplicate_agent_character Duplicate one of your own agent characters. Unlike fork, this copies the full LLM choice as well — useful for Write duplicate_workflow Create a copy of an existing workflow. The new workflow will be private and editable. Write email_archive Archive an email message (removes from inbox). Subject to mailbox grant permissions. Write email_draft Create an email draft in a connected mailbox. The draft is saved but not sent. Write email_label Add or remove labels on an email message. Subject to mailbox grant permissions. Write email_reply Reply to an email message. Subject to mailbox grant permissions. Write favorite_custom_node Add or remove a custom node from your favorites. Write favorite_recipe Add or remove a recipe from your favorites. Favorited recipes can be filtered in list_recipes. Write favorite_workflow Add or remove a workflow from your favorites. Favorited workflows can be filtered in list_workflows. Write fork_agent_character Fork a public agent character to your library by hash. Voice config + persona are copied; the LLM choice is re Write fork_recipe Create a copy of a public recipe into your account. The copy will be private and editable. Write mcp__flowdot__add_toolkit_comment Add a comment to a toolkit. Share feedback, ask questions, or discuss the toolkit with the community. Write mcp__flowdot__copy_agent_toolkit Copy/duplicate a toolkit. Creates a private copy of a toolkit that you can customize. Write mcp__flowdot__create_toolkit_tool Create a new tool in a toolkit. Add HTTP or Workflow-based tools to your agent toolkit with custom input/outp Write mcp__flowdot__favorite_toolkit Add or remove a toolkit from your favorites. Write mcp__flowdot__install_toolkit Install a toolkit to your account. After installation, you can configure credentials and use the toolkit Write mcp__flowdot__toggle_toolkit_active Enable or disable a toolkit installation. Inactive toolkits won Write mcp__flowdot__toggle_toolkit_visibility Change toolkit visibility (private, public, or unlisted). Public toolkits are searchable by others. Unlisted Write mcp__flowdot__update_toolkit_installation Update toolkit installation (configure credential mapping). Map toolkit credential requirements to your store Write mcp__flowdot__update_toolkit_tool Update an existing tool in a toolkit. Modify tool configuration, schemas, endpoints, or credentials. Write mcp__flowdot__vote_toolkit Vote on a toolkit (upvote, downvote, or remove your vote). Write move_document_to_category Move a document to a different category, or remove it from its current category (make it uncategorized). Write patch_knowledge_document_section Edit a targeted section of a knowledge base document by find-and-replace. The old_text must be at least 10 cha Write prepend_app_code Prepends content to the beginning of app code. CRITICAL: Remember export rules: - NO IMPORTS - React is globa Write publish_app Publish an app to make it publicly visible in the FlowDot app marketplace. Once published: - Other users can Write rename_app_file Rename or move a file within a multi-file FlowDot app. Changes the file Write restore_recipe_version Restore a recipe to one of its prior versions. The current state is automatically snapshotted before the resto Write resume_goal Resume a paused goal. Write set_app_entry_file Set a file as the entry point for a multi-file FlowDot app. The entry point is the main file that gets render Write set_workflow_tags Set or update the tags/categories on a workflow. Replaces existing tags. Write toggle_agent_character_public Toggle a character Write toggle_community_inputs Enable or disable community inputs (input presets) for a workflow. When enabled, users can create and share pr Write toggle_custom_node_visibility Change the visibility of a custom node (private, public, or unlisted). Write toggle_workflow_public Make a workflow public or private. Public workflows are visible to all users. Write transfer_document_ownership Transfer a document between your personal knowledge base and a team knowledge base. You can also optionally as Write unlink_app_workflow Unlink a workflow from an app. After unlinking, the app will no longer be able to invoke that workflow. Make Write unpublish_app Unpublish an app to make it private. The app will no longer be visible in the public marketplace. Existing cl Write update_agent_character Update an agent character. Send only the fields you want to change. The Hub validates the post-merge state — i Write update_app_file Update the content of an existing file in a FlowDot app. Updates the file Write update_custom_node Update an existing custom node. Only provide fields you want to change. When updating script_code, remember: Write update_goal Update a goal\ Write update_input_preset Update an existing input preset. You can only update presets you created. Write update_knowledge_category Update an existing knowledge base category name, description, or color. Write update_knowledge_document_content Replace the full content of a knowledge base document. Overwrites the file on disk and triggers reprocessing ( Write update_node Update a node\ Write update_recipe_step Update a step Write update_recipe_store Update a store Write upload_document_from_url Download a document from a URL and add it to your knowledge base. Supports PDF, DOCX, TXT, Markdown, CSV, and Write upload_image Upload an image (bare base64) to your FlowDot storage bucket and get back a public direct URL you can embed an Write upload_text_document Upload text content directly as a document to your knowledge base. Ideal for creating documents from AI-genera Write vote_custom_node Vote on a custom node. You can upvote, downvote, or remove your vote. Write vote_input_preset Vote on an input preset (upvote, downvote, or remove your vote). Write vote_recipe Vote on a recipe (upvote, downvote, or remove your vote). Only works on public recipes. Write vote_shared_result Vote on a shared execution result (upvote, downvote, or remove your vote). Write vote_workflow Vote on a workflow (upvote, downvote, or remove your vote). Only works on public workflows or your own workflo
READ 90 tools
Read agent_chat Chat with the FlowDot AI agent. The agent can help discover workflows, suggest which workflow to run, and expl Read audit_property Audit a FlowDot property — a deterministic, full-scope inspection of what it can DO and REACH — before recomme Read browse_community_input_presets Browse community-shared input presets across ALL workflows on the platform. Returns only presets the author ha Read browse_recipes Browse public agent recipes shared by other users. Search by name, category, or tags. Read browser_describe Read the current page: title, url, headings, interactive elements (with selectors), visible text, forms, modal Read browser_find Find candidate elements matching a natural-language description or text. Returns ranked selectors. Read browser_list_sessions List all open browser/Electron sessions. Read browser_read_form Return a schema of the page Read browser_screenshot Capture a PNG of the current page. Returns a base64 image (or writes to save_path if given). Read email_list_threads List email threads from a connected mailbox. Returns recent threads with subject, participants, and message co Read email_read Read a specific email message by ID. Returns full message content including headers, body, and attachments lis Read email_search Search emails in a connected mailbox. Requires an active email integration. Read get_agent_character Get full detail on an agent character including its voice/STT/LLM config and a per-field Completeness section. Read get_app Get detailed information about a FlowDot app, including its React code and linked workflows. Apps are React f Read get_app_file Get the content and details of a specific file in a multi-file FlowDot app. Returns the file Read get_custom_node Get detailed information about a custom node including inputs, outputs, properties, and script code. Read get_custom_node_comments Get comments and ratings for a custom node. Read get_custom_node_template Generate a working script template for a custom node based on inputs and outputs. Use this tool to get a corr Read get_document_info Get a document Read get_execution_history Get past execution history for a workflow including timestamps, status, and duration. Read get_execution_status Get the status and results of a workflow execution. Use after execute_workflow with wait_for_completion=false. Read get_goal Get details for a specific goal by its hash. Read get_input_preset Get detailed information about a specific input preset (community input), including all input values. Read get_knowledge_document Get detailed information about a specific document in your knowledge base by ID or hash. Read get_knowledge_document_content Fetch the full raw text content of a knowledge base document by ID or hash. Use this when you need to read an Read get_knowledge_storage Get storage usage information for your knowledge base, including total space used, limits, and document counts Read get_node_connections Get all connections to and from a specific node in a workflow. Read get_node_schema Get the full schema for a specific node type including inputs, outputs, and properties. Read get_public_workflows Browse public workflows shared by other users. Returns paginated results with workflow details. Read get_recipe Get detailed information about a specific agent recipe including its steps, stores, and metadata. Read get_recipe_benchmark Get a published recipe benchmark with all of its grouped runs side-by-side. Each run carries totals, model lin Read get_recipe_definition Get the complete recipe definition in YAML format. Returns all steps, stores, entry_step_id, and configuration Read get_recipe_version Fetch the complete definition snapshot of one recipe version. Use this to inspect a prior state before decidin Read get_shared_recipe_run Get full details of one published recipe run: per-step trace (model, tokens, duration, tool calls), total toke Read get_shared_result Get detailed information about a specific shared execution result, including the shared outputs and inputs. Read get_shared_result_comments Get user comments on a shared execution result. Read get_workflow_comments Get user comments and ratings on a workflow. Only available for public workflows. Read get_workflow_details Get detailed workflow information including nodes, connections, input/output signature, and metadata. Read get_workflow_graph Get the complete graph structure of a workflow including all nodes and connections. Read get_workflow_inputs_schema Get the input schema for a workflow - shows what inputs are expected, their types, and whether they are requir Read get_workflow_metrics Get execution metrics for a workflow including total executions, success/failure rates, average duration, and Read get_workflow_public_url Get the public shareable URL for a workflow. Returns the URL and indicates if the workflow is currently access Read get_workflow_tags Get the tags/categories associated with a workflow. Read learn_about Load a FlowDot area: returns a short how-to AND unlocks that area\ Read list_agent_characters List your agent characters (voice-call personas). Each row shows a completeness badge — ready to call (✅) vs. Read list_app_files List all files in a multi-file FlowDot app. Returns a list of files with their paths, types, and entry point Read list_apps List the user Read list_comms_channels List the user\ Read list_custom_nodes List your own custom nodes. Supports search and category filtering. Read list_email_integrations List the user\ Read list_goal_milestones List all milestones for a goal. Read list_goal_tasks List all tasks for a goal. Optionally filter by status. Read list_goals List all goals for the authenticated user. Optionally filter by status. Read list_images List images you have uploaded to your FlowDot storage bucket (most recent first), with their public URLs, ids, Read list_input_presets List input presets (community inputs) for a workflow. These are pre-configured input values that users can sha Read list_kb_grants List the property Knowledge-Base grants YOU have approved (your own standing consent). What is a grant? A per Read list_knowledge_categories List all document categories in your knowledge base. Categories help organize documents for easier retrieval a Read list_knowledge_documents List documents in your knowledge base. Optionally filter by category, team, or status. Shows document title, s Read list_my_input_presets List every input preset YOU have created across every workflow. Use this to inspect your personal preset libra Read list_my_resources List the current user Read list_notifications List recent notifications for the authenticated user. Shows comments, replies, votes, and other activity. Read list_property_kb_links List the Knowledge-Base source links declared on a property you OWN (app, recipe, toolkit, or workflow). What Read list_recipe_benchmarks List published benchmarks for a recipe. A benchmark groups two or more runs together so viewers can compare co Read list_recipe_steps List all steps in a recipe with their types, connections, and configurations. Read list_recipe_stores List all stores (variables) in a recipe. Stores hold data that flows between steps. Read list_recipe_versions List recent version snapshots for a recipe (rollback history). Newest first, up to the retention limit (20). E Read list_shared_recipe_runs List published runs for a recipe. Each run is a frozen snapshot of one execution including total tokens, durat Read list_shared_results List all shared execution results for a workflow. Shows shareable links, view counts, and metadata for each sh Read list_user_teams List all teams you belong to. Use this to discover available teams before filtering knowledge base operations Read list_workflows List FlowDot workflows available to the user. Returns workflow IDs, names, and descriptions. Read mcp__flowdot__check_toolkit_credentials Check credential status for a toolkit installation. Shows which credentials are required and which are missin Read mcp__flowdot__get_agent_toolkit Get detailed information about a specific agent toolkit. Returns comprehensive toolkit details including tool Read mcp__flowdot__get_toolkit_comments Get comments on a toolkit. View community feedback and discussions about a toolkit. Read mcp__flowdot__get_toolkit_tool Get detailed information about a specific tool in a toolkit. Shows input schema, configuration, and requireme Read mcp__flowdot__list_agent_toolkits List your own MCP agent toolkits with optional filtering. Toolkits are collections of custom tools that can b Read mcp__flowdot__list_installed_toolkits List all toolkits you have installed. Shows installation status and credential configuration for each toolkit Read mcp__flowdot__list_toolkit_tools List all tools in a toolkit. Shows tool names, descriptions, and types (HTTP or Workflow). Read mcp__flowdot__search_agent_toolkits Search the public MCP toolkit marketplace for toolkits created by other users. Discover reusable tool collect Read panic_status Read the current emergency-stop status for your account. Read pause_goal Pause an active goal. The daemon will stop processing tasks for this goal. Read query_knowledge_base Search your knowledge base using semantic and keyword search. Returns relevant document chunks with source att Read read_document Read the full text of a local document (pdf, docx, pptx, xlsx, md, txt, csv) by file path. Read reprocess_document Reprocess a document that failed processing or is stuck in pending/processing status. Clears existing chunks a Read search Search for resources like workflows, apps, and custom nodes within the FlowDot platform. Read search_apps Search the FlowDot app marketplace for public apps created by other users. Apps are React frontend applicatio Read search_public_custom_nodes Search public custom nodes shared by the community. Read search_workflows Search for workflows by name, description, or tags. Searches your own workflows. Read stream_execution Get real-time streaming information for a workflow execution. Returns the SSE endpoint URL and authentication Read validate_workflow Validate a workflow for errors such as missing connections, invalid configurations, or disconnected nodes. Read whoami Get information about the currently authenticated user and MCP token.
EXPLORE

Related servers

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

Yaver 812 tools
paymentsadminautomation
Binance MCP Server 734 tools
paymentsadminautomation
GoHighLevel MCP Server 566 tools
paymentsadminautomation
Ruflo 486 tools
paymentsadminautomation
Claude Flow 454 tools
paymentsadminautomation
ServiceTitan MCP Server 454 tools
paymentsadminautomation
CloudStack MCP Server 442 tools
paymentsadminautomation
Serac 432 tools
paymentsadminautomation
FAQ

Questions about FlowDot MCP Server

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

Yes. The FlowDot MCP Server server exposes 26 destructive tools including browser_act, cancel_execution, delete_agent_character. 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 FlowDot MCP Server? +

The FlowDot MCP Server server has 77 write tools including abandon_goal, add_connection, add_custom_node_comment. 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 FlowDot MCP Server.

How many tools does the FlowDot MCP Server MCP server expose? +

207 tools across 5 categories: Destructive, Execute, Financial, Read, Write. 90 are read-only. 117 can modify, create, or delete data.

How do I enforce a policy on FlowDot MCP Server? +

Register the FlowDot MCP Server 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 FlowDot MCP Server tool call.

Deterministic rules across all 207 FlowDot MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON FLOWDOT →

Instant setup, no code required.

207 FlowDot MCP Server tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from FlowDot MCP Server's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.