// SCAN REPORT

Directus MCP Server

56 tools. 40 can modify or destroy data without limits.

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

Last updated:

40 can modify or destroy data
16 read-only
56 tools total

Community server · catalogue entry verified 03/07/2026

How to control Directus MCP Server ↓

TOOL MAP

What Directus MCP Server exposes to your agents

Read (16) Write / Execute (27) Destructive / Financial (13)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS
Critical Risk

The most dangerous Directus MCP Server tools

Destructive · Critical bulk_delete_items The tool irreversibly deletes data in bulk. Destructive · Critical delete_collection This tool permanently and irreversibly deletes an entire collection including all associated data. Destructive · High delete_dashboard The tool permanently removes a dashboard without recovery option. Destructive · High delete_dashboards This tool permanently removes dashboards and cannot be reversed, meeting the definition of Destructive.

40 of Directus MCP Server's 56 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Directus MCP Server

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

Deny destructive operations
{
  "bulk_delete_items": {
    "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
{
  "apply_schema_diff": {
    "limits": [
      {
        "counter": "apply_schema_diff_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "get_collection": {
    "limits": [
      {
        "counter": "get_collection_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 Directus 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 DIRECTUS →

Instant setup, no code required.

FULL CATALOGUE

All 56 Directus MCP Server tools

DESTRUCTIVE 13 tools
Destructive bulk_delete_items Delete multiple items from a collection at once by their IDs. This action cannot be undone. Example: {collecti Destructive delete_collection Delete a collection and all its data. This action cannot be undone. Use with caution. Destructive delete_dashboard Delete a dashboard from Directus by ID. This action cannot be undone. Destructive delete_dashboards Delete multiple dashboards from Directus at once by their IDs. This action cannot be undone. Example: {ids: [ Destructive delete_field Remove a field from a collection. This will delete the column and all its data. Use with caution. Destructive delete_flow Delete a flow from Directus by ID. This action cannot be undone. Destructive delete_flows Delete multiple flows from Directus at once by their IDs. This action cannot be undone. Example: {ids: [ Destructive delete_item Delete an item from a collection by ID. This action cannot be undone. Destructive delete_operation Delete an operation from Directus by ID. This action cannot be undone. Destructive delete_operations Delete multiple operations from Directus at once by their IDs. This action cannot be undone. Example: {ids: [ Destructive delete_panel Delete a panel from Directus by ID. This action cannot be undone. Destructive delete_panels Delete multiple panels from Directus at once by their IDs. This action cannot be undone. Example: {ids: [ Destructive delete_relation Delete a relation. Specify the collection and field that contains the relation.
EXECUTE 1 tools
Execute trigger_flow Trigger a flow with GET or POST webhook trigger. For GET: {id:
WRITE 26 tools
Write apply_schema_diff Update the instance\ Write bulk_create_items Create multiple items in a collection at once. More efficient than creating items one by one. Example: {collec Write bulk_update_items Update multiple items in a collection at once. Each item must include an id field. Example: {collection: Write create_collection Create a new collection (database table) in Directus. Automatically creates a proper database table with schem Write create_dashboard Create a new dashboard in Directus. Provide the dashboard data including name and optional configuration. Exam Write create_dashboards Create multiple dashboards in Directus at once. More efficient than creating dashboards one by one. Example: { Write create_field Add a new field to a collection. Specify field type, interface, and constraints. Example: {collection: Write create_flow Create a new flow in Directus. Provide the flow data including name, trigger type, and optional configuration. Write create_flows Create multiple flows in Directus at once. More efficient than creating flows one by one. Example: {flows: [{n Write create_item Create a new item in a collection. Provide the item data as key-value pairs. Example: {collection: Write create_operation Create a new operation in Directus. Provide the operation data including name, key, type, and optional configu Write create_operations Create multiple operations in Directus at once. More efficient than creating operations one by one. Example: { Write create_panel Create a new panel in Directus. Provide the panel data including dashboard, name, type, position, and dimensio Write create_panels Create multiple panels in Directus at once. More efficient than creating panels one by one. Example: {panels: Write create_relation Create a relation between collections (M2O, O2M, or M2M). For M2O: specify collection, field, and related_coll Write update_collection Update collection metadata such as icon, note, visibility settings, etc. Write update_dashboard Update an existing dashboard in Directus. Provide the dashboard ID and fields to update. Example: {id: Write update_dashboards Update multiple dashboards in Directus at once. Each dashboard must include an id field. Example: {dashboards: Write update_field Update field properties such as metadata, interface options, or schema constraints. Write update_flow Update an existing flow in Directus. Provide the flow ID and fields to update. Example: {id: Write update_flows Update multiple flows in Directus at once. Each flow must include an id field. Example: {flows: [{id: Write update_item Update an existing item in a collection. Provide the item ID and fields to update. Example: {collection: Write update_operation Update an existing operation in Directus. Provide the operation ID and fields to update. Example: {id: Write update_operations Update multiple operations in Directus at once. Each operation must include an id field. Example: {operations: Write update_panel Update an existing panel in Directus. Provide the panel ID and fields to update. Example: {id: Write update_panels Update multiple panels in Directus at once. Each panel must include an id field. Example: {panels: [{id:
READ 16 tools
Read get_collection Get detailed information about a specific collection including all fields, metadata, and schema configuration. Read get_dashboard Get a single dashboard by ID from Directus. Optionally specify fields to return and metadata options. Read get_flow Get a single flow by ID from Directus. Optionally specify fields to return and metadata options. Read get_item Get a single item by ID from a collection. Optionally specify fields to return and deep query for relational d Read get_operation Get a single operation by ID from Directus. Optionally specify fields to return and metadata options. Read get_panel Get a single panel by ID from Directus. Optionally specify fields to return and metadata options. Read get_schema_diff Compare the current instance\ Read get_schema_snapshot Get a complete schema snapshot of the Directus instance including all collections, fields, and relations. Opti Read list_collections List all collections in the Directus instance. Returns collection names, metadata, and schema information. Read list_dashboards List all dashboards that exist in Directus. Supports filtering, sorting, pagination, and search. Example: {fil Read list_fields List all fields in a specific collection with their types, metadata, and schema configuration. Read list_flows List all flows that exist in Directus. Supports filtering, sorting, pagination, and search. Example: {filter: Read list_operations List all operations that exist in Directus. Supports filtering, sorting, pagination, and search. Example: {fil Read list_panels List all panels that exist in Directus. Supports filtering, sorting, pagination, and search. Example: {filter: Read list_relations List all relations (foreign keys, M2O, O2M, M2M) in the Directus instance. Read query_items Query items from a collection with advanced filtering, sorting, pagination, and search. Supports Directus filt
EXPLORE

Related servers

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

Yaver 1060 tools
adminautomation
Nodebench 824 tools
adminautomation
UnClick 813 tools
adminautomation
Binance MCP Server 734 tools
adminautomation
Fortimanager 584 tools
adminautomation
Crow 573 tools
adminautomation
Mcp 571 tools
adminautomation
GoHighLevel MCP Server 566 tools
adminautomation
FAQ

Questions about Directus MCP Server

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

Yes. The Directus MCP Server server exposes 13 destructive tools including bulk_delete_items, delete_collection, delete_dashboard. 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 Directus MCP Server? +

The Directus MCP Server server has 26 write tools including apply_schema_diff, bulk_create_items, bulk_update_items. 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 Directus MCP Server.

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

56 tools across 4 categories: Destructive, Execute, Read, Write. 16 are read-only. 40 can modify, create, or delete data.

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

Register the Directus 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 Directus MCP Server tool call.

Deterministic rules across all 56 Directus MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DIRECTUS →

Instant setup, no code required.

56 Directus MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.