// SCAN REPORT

Perceptdot

21 tools. 2 can modify or destroy data without limits.

2 write tools that can modify data. Rate limits recommended.

Last updated: 3 Jul 2026

2 can modify or destroy data

19 read-only

21 tools total

Community server · catalogue entry verified 03/07/2026

How to control Perceptdot ↓

TOOL MAP

What Perceptdot exposes to your agents

Read (19) Write / Execute (2) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Perceptdot tools

Execute · Medium visual_check The tool performs an active external operation (fetching and screenshotting a URL) and then executes AI-based analysis. Write · Low percept_feedback This tool submits user feedback (a rating and comment) to an external service, which is a reversible write/post action.

2 of Perceptdot's 21 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Perceptdot

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

Rate limit write operations

{
  "percept_feedback": {
    "limits": [
      {
        "counter": "percept_feedback_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "ga4_events": {
    "limits": [
      {
        "counter": "ga4_events_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 Perceptdot — 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 PERCEPTDOT →

Instant setup, no code required.

FULL CATALOGUE

All 21 Perceptdot tools

EXECUTE 1 tools

Execute visual_check Screenshot a URL and analyze it for visual bugs using AI.

WRITE 1 tools

Write percept_feedback Submit feedback to unlock 100 more free calls. Rate 1-5 and leave a comment (max 150 chars).

READ 19 tools

Read ga4_events Get GA4 event counts (clicks, conversions, signups). Read ga4_overview Get GA4 period overview: sessions, users, pageviews, bounce rate, avg session duration. Read ga4_realtime Read GA4 realtime active users and device breakdown in one call. Read ga4_top_pages Get top pages by views. Returns structured page path, title, views, users. Read github_issues Get open issues, filterable by labels. Read github_pr_detail Get full PR detail: diff stats, reviewer approvals, changed files. Read github_prs Get open pull requests with review status, labels, and dates (up to 20). Read github_workflows Get recent GitHub Actions workflow runs with status (up to 10). Read percept_discover Scan this project and auto-discover which MCP servers would be useful. Read percept_installed List all MCP servers currently configured in this environment. Read percept_recommend Search for MCP servers by keyword, category, or use case. Read percept_roi_summary Report how many tokens, dollars, and minutes perceptdot/core saved this session. Read sentry_events Get recent error events (level:error, limit 10). Use for real-time error detection after deploys. Structured d Read sentry_issue_detail Get full detail for a specific Sentry issue: stack trace summary, tags, event count. One call replaces copying Read sentry_issues Get unresolved Sentry issues sorted by priority. Replaces manual Sentry dashboard browsing (~500 tokens saved, Read sentry_stats Get project error statistics: received/resolved/unresolved counts for 24h/7d/30d. Quick health check without o Read vercel_deployments Get recent Vercel deployments with status, commit messages, and timing. Read vercel_latest_status Instant pass/fail check on the most recent deployment. Read vercel_projects List all Vercel projects with their latest deployment state.

FAQ

Questions about Perceptdot

How do I prevent bulk modifications through Perceptdot? +

The Perceptdot server has 1 write tools including percept_feedback. 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 Perceptdot.

How many tools does the Perceptdot MCP server expose? +

21 tools across 2 categories: Read, Write. 19 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on Perceptdot? +

Register the Perceptdot 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 Perceptdot tool call.

Deterministic rules across all 21 Perceptdot tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PERCEPTDOT →

Instant setup, no code required.

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