// SCAN REPORT

Dephq

12 tools. 6 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 23 Jul 2026

6 can modify or destroy data

6 read-only

12 tools total

Community server · catalogue entry checked 23/07/2026 · full schemas captured for 10 of 12 tools

How to control Dephq ↓

TOOL MAP

What Dephq exposes to your agents

Read (6) Write / Execute (5) Destructive / Financial (1)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Dephq costs in tokens

1,918 tokens of tool definitions, loaded on every request

1.0% of a 200k context window

280 heaviest tool: dephq_app_rollback

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Dephq tools

Destructive · High dephq_app_unpublish Unpublishing an app removes it from public availability, which is an irreversible operational action in the sense that any users depending on the app lose access immediately. Execute · Medium dephq_app_check The tool runs checks on a live app, which constitutes executing an operation against external infrastructure. Write · High dephq_project_sync The tool uploads/syncs local project files to a remote draft, which is a reversible write operation (draft state, not published). Write · High dephq_app_publish Publishing an app and submitting it for Store review is a significant write operation that creates/modifies a public-facing artifact.

6 of Dephq's 12 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Dephq

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

Deny destructive operations

{
  "dephq_app_unpublish": {
    "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

{
  "dephq_app_publish": {
    "limits": [
      {
        "counter": "dephq_app_publish_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "dephq_account": {
    "limits": [
      {
        "counter": "dephq_account_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 Dephq — 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 DEPHQ →

Instant setup, no code required.

FULL CATALOGUE

All 12 Dephq tools

DESTRUCTIVE 1 tools

Destructive dephq_app_unpublish Return an owned Dephq app to draft and remove it from public use.

EXECUTE 1 tools

Execute dephq_app_check Run the platform runtime readiness checks for an owned app.

WRITE 4 tools

Write dephq_app_publish Publish an owned app privately, or publish it privately and submit its Store listing for review. Write dephq_app_rollback Restore an owned app's source from a selected historical version. This creates a new current version. Write dephq_project_init Scaffold a complete Dephq React and TypeScript project. Choose a page, records app, API-backed tool, or full a Write dephq_project_sync Delta-sync a local Dephq app project to its creator-owned remote draft and wait for validation/build completio

READ 6 tools

Read dephq_account Check which Dephq creator account and API endpoint the local CLI is authenticated with. Read dephq_app_show Return source metadata, status, listing information, and other safe creator details for one owned app. Read dephq_app_versions List version history for an owned Dephq app. Read dephq_apps_list List apps owned by the authenticated Dephq creator. Read dephq_project_validate Validate the Dephq app source in a local directory without changing the remote app. Read dephq_sync_status Check an asynchronous Dephq source sync by ID.

EXPLORE

Related servers

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

FAQ

Questions about Dephq

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

Yes. The Dephq server exposes 1 destructive tools including dephq_app_unpublish. 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 Dephq? +

The Dephq server has 4 write tools including dephq_app_publish, dephq_app_rollback, dephq_project_init. 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 Dephq.

How many tools does the Dephq MCP server expose? +

12 tools across 4 categories: Destructive, Execute, Read, Write. 6 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Dephq? +

Register the Dephq 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 Dephq tool call.

Deterministic rules across all 12 Dephq tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DEPHQ →

Instant setup, no code required.

12 Dephq tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Dephq'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 →