// SCAN REPORT

Flowchart MCP

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

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

Last updated: 29 Jun 2026

10 can modify or destroy data

3 read-only

13 tools total

Community server · catalogue entry verified 29/06/2026

How to control Flowchart MCP ↓

TOOL MAP

What Flowchart MCP exposes to your agents

Read (3) Write / Execute (8) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Flowchart MCP tools

Destructive · Medium remove_edge Removing an edge deletes it from the diagram with no indication of an undo mechanism. Destructive · High remove_node This tool permanently deletes a node and cascades to remove all connected edges. Write · Low add_edge add_edge creates a new connection in a flowchart diagram, which is a reversible modification operation. Write · Low add_node Adding a node to a flowchart creates or modifies diagram data but is reversible and has no external side effects.

10 of Flowchart MCP's 13 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Flowchart MCP

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

Deny destructive operations

{
  "remove_edge": {
    "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_edge": {
    "limits": [
      {
        "counter": "add_edge_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_diagram": {
    "limits": [
      {
        "counter": "get_diagram_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 Flowchart MCP — 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 FLOWCHART →

Instant setup, no code required.

FULL CATALOGUE

All 13 Flowchart MCP tools

DESTRUCTIVE 2 tools

Destructive remove_edge Remove an edge from the diagram. Destructive remove_node Remove a node (and all its connected edges) from the diagram.

WRITE 8 tools

Write add_edge Add a directed edge (connection) between two nodes. Write add_node Add a node to the flowchart. Write apply_theme Apply a color theme to the diagram. Write auto_layout Automatically arrange nodes using a layered graph layout algorithm. Write create_diagram Create a new flowchart diagram. Returns diagram ID. Write export_diagram Export the diagram to a file (PNG, SVG, or JSON). Write update_edge Update an existing edge Write update_node Update an existing node

READ 3 tools

Read get_diagram Read the current state of the diagram (nodes, edges, positions). Use this to observe changes the user made in Read list_diagrams List all diagrams created in this session. Read open_editor Get the URL to open the visual flowchart editor in the browser.

EXPLORE

Related servers

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

FAQ

Questions about Flowchart MCP

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

Yes. The Flowchart MCP server exposes 2 destructive tools including remove_edge, remove_node. 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 Flowchart MCP? +

The Flowchart MCP server has 8 write tools including add_edge, add_node, apply_theme. 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 Flowchart MCP.

How many tools does the Flowchart MCP server expose? +

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

How do I enforce a policy on Flowchart MCP? +

Register the Flowchart 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 Flowchart MCP tool call.

Deterministic rules across all 13 Flowchart MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON FLOWCHART →

Instant setup, no code required.

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