New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

Deloc

45 tools. 29 can modify or destroy data without limits.

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

Last updated:

29 can modify or destroy data
16 read-only
45 tools total

Community server · catalogue entry checked 02/08/2026

How to control Deloc ↓

What Deloc exposes to your agents

Read (16) Write / Execute (21) Destructive / Financial (8)
Critical Risk

The most dangerous Deloc tools

29 of Deloc's 45 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Deloc

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

Deny destructive operations
{
  "delete_action": {
    "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
{
  "connect_bigquery": {
    "limits": [
      {
        "counter": "connect_bigquery_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "bigquery_get_table_schema": {
    "limits": [
      {
        "counter": "bigquery_get_table_schema_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 Deloc — 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 DELOC →

Instant setup, no code required.

All 45 Deloc tools

WRITE 17 tools
Write connect_bigquery Connect the user Write create_action Create a new server-side Action on a published app. Actions let browser code call external APIs without exposi Write create_dashboard_query create_dashboard_query Write create_oauth_credential Create an OAuth credential that actions can reference by name to get a fresh access token at invoke time (inje Write disable_action Disable an Action so invocations are rejected. Config and secrets are preserved. Write enable_action Re-enable a disabled or auto-disabled Action. Idempotent. Write enable_app Re-enable a disabled app so it is served again Write renew_app Extend a free-tier app Write set_action_secret Set or rotate a secret for an Action. Values are encrypted at rest (libsodium secretbox) and never returned by Write set_og_image Set a custom OG preview image for an app (shown in link previews on X, Slack, etc.). Accepts a local PNG file Write set_password Set, change, or remove password protection on an app Write setup_data_refresh Generate a complete backend script that queries a data warehouse and auto-refreshes a Deloc dashboard. Creates Write setup_deloc Set up Deloc — sign in to start deploying. Ask the user which sign-in method they prefer: Google, Microsoft, o Write update_action Update an existing Action. Every field is optional — send only what Write update_dashboard_query Update a scheduled dashboard query: change its SQL, repoint it to a different connection, adjust caps, or enab Write update_oauth_credential Update an OAuth credential. Rotate the secret (client_secret/password/private key) by passing a new grant + se Write upload_data Upload or replace a data file (CSV, JSON, TSV, XML, TXT, max 10MB) inside an already-deployed Deloc app WITHOU
READ 16 tools
Read bigquery_get_table_schema Get the column names and types of a BigQuery table. Use this to write correct SQL for create_dashboard_query. Read bigquery_list_datasets List the datasets in a GCP project visible to a BigQuery connection. Read bigquery_list_projects List the GCP projects a BigQuery connection can access. Use the project id as gcp_project_id when creating das Read bigquery_list_tables List the tables in a BigQuery dataset. Read check_bigquery_connection Check whether a pending BigQuery connect session (started with connect_bigquery) has been approved. Polls brie Read get_account Get current user info including tier, usage, and limits Read get_action_logs Fetch recent invocation history for an app Read get_app Get detailed info about a published app including bandwidth usage Read list_action_secrets List secret NAMES configured for an Action. Values are never returned — secrets are write-only after set. Read list_actions List Actions configured for a published app. Shows method, status, and recent invocation stats. Read list_apps List published apps with their URLs and status Read list_dashboard_queries List the scheduled dashboard queries on an app, with their output files and last-run results. Read list_data_connections List the user Read list_data_files List the refreshable data files (uploaded via upload_data) for a Deloc app, with sizes and last-updated time. Read list_oauth_credentials List OAuth credentials the authenticated user can see. Org users see the team-shared credentials for their org Read suggest_deploy_options Analyze a project directory and suggest deployment options including framework detection, build needs, app nam

Related servers

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

Questions about Deloc

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

Yes. The Deloc server exposes 8 destructive tools including delete_action, delete_action_secret, delete_app. 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 Deloc? +

The Deloc server has 17 write tools including connect_bigquery, create_action, create_dashboard_query. 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 Deloc.

How many tools does the Deloc MCP server expose? +

45 tools across 4 categories: Destructive, Execute, Read, Write. 16 are read-only. 29 can modify, create, or delete data.

How do I enforce a policy on Deloc? +

Register the Deloc 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 Deloc tool call.

Deterministic rules across all 45 Deloc tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

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

// WHERE THIS COMES FROM

These policies come from Deloc'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.