// SCAN REPORT

Framedeck

32 tools. 22 can modify or destroy data without limits.

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

Last updated: 3 Jul 2026

22 can modify or destroy data

10 read-only

32 tools total

Community server · catalogue entry verified 03/07/2026

How to control Framedeck ↓

TOOL MAP

What Framedeck exposes to your agents

Read (10) Write / Execute (20) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Framedeck tools

Destructive · High delete_card This tool irreversibly removes data (a card/frame) from the Framedeck production management system. Destructive · High delete_column This tool performs an irreversible deletion of a board column/stage. Write · Low remove_label_from_card Removing a label from a card is a reversible modification — the label can be re-added at any time. Write · Low add_checklist_item Adding a checklist item to a card creates or appends data to an existing card in the Framedeck Kanban system.

22 of Framedeck's 32 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Framedeck

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

Deny destructive operations

{
  "delete_card": {
    "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

{
  "add_checklist_item": {
    "limits": [
      {
        "counter": "add_checklist_item_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_active_board": {
    "limits": [
      {
        "counter": "get_active_board_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 Framedeck — 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 FRAMEDECK →

Instant setup, no code required.

FULL CATALOGUE

All 32 Framedeck tools

DESTRUCTIVE 2 tools

Destructive delete_card Permanently delete a card/frame Destructive delete_column Delete a stage/column from a board. Cards in this stage will be moved to the first remaining stage.

WRITE 20 tools

Write add_checklist_item Add a subtask/checklist item to a card Write add_comment Add a comment to a card Write add_labels_to_card Add one or more labels to an existing card Write archive_card Archive a card (soft delete — can be restored in the UI) Write assign_card Assign or unassign a user to a card Write create_board Create a new project/board in Framedeck Write create_card Create a new card/frame. Uses active board if set, or Idea Pool as fallback for quick idea capture. Write create_column Create a new stage in a board. Uses active board if not specified. Write create_label Create a new label/tag Write create_multiple_cards Create multiple cards/frames at once. Ideal for batch idea capture via voice. Uses active board if board is no Write duplicate_card Duplicate a card including its checklist items Write graduate_to_production Promote an idea from the Idea Pool into its own dedicated production with full stages (Idea → Scripting → Film Write link_commit Link a git commit to a card. Automatically adds commit info as a comment. Write log_work Logs time spent on a card Write move_card Move a card/frame to a different stage Write remove_label_from_card Remove a label from a card Write set_active_board Set the active board/production context. Once set, other tools will use this board by default when no board is Write set_card_color Set or clear the color of a card for visual categorization Write toggle_checklist_item Check or uncheck a subtask/checklist item Write update_card Update an existing card/frame

READ 10 tools

Read get_active_board Show which board/production is currently set as the active context. Read get_board_overview Get a quick overview of a board: stages with card counts, overdue items. Uses active board if not specified. Read get_card_details Get full details of a card including comments, checklists, attachments, and labels Read get_my_cards Get cards assigned to the current user, grouped by status. Read get_sprint_summary Shows a summary of activity across all boards for the past N days Read list_boards List all projects/productions in Framedeck Read list_cards List cards/frames with optional filters. Uses active board if set and no board specified. Read list_columns List stages in a board. Uses active board if set and no board specified. Read list_labels List all labels/tags Read search_cards Search for cards by keyword across all boards

EXPLORE

Related servers

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

FAQ

Questions about Framedeck

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

Yes. The Framedeck server exposes 2 destructive tools including delete_card, delete_column. 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 Framedeck? +

The Framedeck server has 20 write tools including add_checklist_item, add_comment, add_labels_to_card. 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 Framedeck.

How many tools does the Framedeck MCP server expose? +

32 tools across 3 categories: Destructive, Read, Write. 10 are read-only. 22 can modify, create, or delete data.

How do I enforce a policy on Framedeck? +

Register the Framedeck 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 Framedeck tool call.

Deterministic rules across all 32 Framedeck tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON FRAMEDECK →

Instant setup, no code required.

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