// SCAN REPORT

Blop

28 tools. 8 can modify or destroy data without limits.

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

Last updated: 30 Jun 2026

8 can modify or destroy data

20 read-only

28 tools total

Community server · catalogue entry verified 30/06/2026

How to control Blop ↓

TOOL MAP

What Blop exposes to your agents

Read (20) Write / Execute (7) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Blop tools

Destructive · Medium cancel_run Cancelling a running test is an irreversible action — once cancelled, the in-progress test execution is terminated and marked as cancelled, which cannot be undone. Execute · High navigate_to_journey This tool executes browser navigation to a specific URL derived from journey context. Execute · High navigate_to_url Navigation to a URL causes the browser to load, parse, and potentially execute JavaScript and other code at that destination. Execute · High run_release_check Although the tool description is empty, the name 'run_release_check' and the server's purpose of executing 'browser execution' and making 'go/no-go decisions' indicates this tool triggers external operations whose effect

8 of Blop's 28 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Blop

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

Deny destructive operations

{
  "cancel_run": {
    "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

{
  "record_run_observation": {
    "limits": [
      {
        "counter": "record_run_observation_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "capture_artifact": {
    "limits": [
      {
        "counter": "capture_artifact_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 Blop — 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 BLOP →

Instant setup, no code required.

FULL CATALOGUE

All 28 Blop tools

DESTRUCTIVE 1 tools

Destructive cancel_run Cancel a running test and mark it as cancelled.

EXECUTE 5 tools

Execute evaluate_web_task evaluate_web_task Execute navigate_to_journey Open a recorded journey's entry URL (flow_id == journey_id). Execute navigate_to_url Navigate the shared browser session to a URL (ok/data envelope). Execute perform_step One structured step: click | type | wait | press_key | navigate (see PerformStepSpec). Execute run_release_check run_release_check

WRITE 2 tools

Write record_run_observation Idempotent agent observation keyed by (run_id, observation_key). Write save_auth_profile save_auth_profile

READ 20 tools

Read capture_artifact Capture screenshot, dom_snapshot, or network_log; optional run_id routes under runs/. Read capture_auth_session capture_auth_session Read debug_test_case debug_test_case Read discover_critical_journeys discover_critical_journeys Read export_run_trace Export OTLP-shaped JSON (resourceSpans) for a run — local SQLite only, no network upload. Read get_journeys_for_release List recorded journeys filtered by release brief app_url or explicit app_url. Read get_mcp_capabilities O(1) probe: package version, surface flags, registered tool count, and canonical tool names. Read get_page_snapshot Compact interactive DOM snapshot (ARIA-ish) for the current page. Read get_prd_and_acceptance_criteria Summaries and acceptance-style criteria from recorded flows / release brief (no external PRD yet). Read get_process_insights Derive process-mining style variants from run health events (optional PM4Py when installed). Read get_qa_recommendations get_qa_recommendations Read get_release_and_journeys Batch: release context plus journeys for the release app URL in one call. Read get_release_context Return structured release brief (decision, risk, blockers) for a release_id. Read get_test_results get_test_results Read get_ux_taxonomy Static UX/criticality hints for planning (cached, small JSON). Read get_workspace_context Return compact workspace metadata, resource URIs, and discovery defaults. Read package_authenticated_saas_baseline package_authenticated_saas_baseline Read record_test_flow record_test_flow Read triage_release_blocker triage_release_blocker Read validate_release_setup validate_release_setup

EXPLORE

Related servers

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

FAQ

Questions about Blop

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

Yes. The Blop server exposes 1 destructive tools including cancel_run. 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 Blop? +

The Blop server has 2 write tools including record_run_observation, save_auth_profile. 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 Blop.

How many tools does the Blop MCP server expose? +

28 tools across 4 categories: Destructive, Execute, Read, Write. 20 are read-only. 8 can modify, create, or delete data.

How do I enforce a policy on Blop? +

Register the Blop 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 Blop tool call.

Deterministic rules across all 28 Blop tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON BLOP →

Instant setup, no code required.

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