// SCAN REPORT

Scan Your Ai Toolkit

29 tools. 4 can modify or destroy data without limits.

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

Last updated: 3 Jul 2026

4 can modify or destroy data

25 read-only

29 tools total

Community server · catalogue entry verified 03/07/2026

How to control Scan Your Ai Toolkit ↓

TOOL MAP

What Scan Your Ai Toolkit exposes to your agents

Read (25) Write / Execute (4) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Scan Your Ai Toolkit tools

Execute · Medium mcp_doctor_checkup This tool executes diagnostic operations that probe the state of external systems (MCP servers) by validating paths, checking connectivity, and reading environment variables. Write · High context_sync_push This tool modifies data (context files) across multiple external systems. Write · High context_sync_update The tool modifies context entries that persist across AI tool sessions. Write · Medium mcp_doctor_fix The tool creates or modifies configuration data (binary paths, environment variables, package commands) to repair broken MCP servers.

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

POLICY

How to control Scan Your Ai Toolkit

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

Rate limit write operations

{
  "context_sync_push": {
    "limits": [
      {
        "counter": "context_sync_push_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "ai_stack_generate": {
    "limits": [
      {
        "counter": "ai_stack_generate_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 Scan Your Ai Toolkit — 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 SCAN YOUR AI TOOLKIT →

Instant setup, no code required.

FULL CATALOGUE

All 29 Scan Your Ai Toolkit tools

EXECUTE 1 tools

Execute mcp_doctor_checkup Run a full health check on all configured MCP servers: validates binary paths, checks connectivity, reports mi

WRITE 3 tools

Write context_sync_push Push all stored context entries out to every connected AI tool (Claude, Cursor, Copilot, etc.), overwriting th Write context_sync_update Add a new context entry or overwrite an existing one by key. Context entries are synced to all connected AI to Write mcp_doctor_fix Generate auto-fix suggestions for broken MCP servers — such as corrected binary paths, missing env var stubs,

READ 25 tools

Read ai_stack_generate Generate your AI Stack profile card showing all AI tools on your machine Read context_sync_read Read all stored AI context entries — persistent key-value pairs (preferences, project facts, coding standards) Read context_sync_status Show the current sync status for each connected AI tool — which tools are up-to-date and which have stale or m Read cost_optimize Analyze your AI spending patterns and return prioritized cost-reduction recommendations — such as unused subsc Read cost_report Generate a unified AI spend report aggregating subscription fees, API token costs, and local model compute acr Read eval_batch Score multiple AI outputs against the same rubric in parallel and return aggregate statistics (mean, min, max, Read eval_compare A/B test two sets of AI outputs against the same rubric. Returns score distributions, a winner declaration, an Read eval_score Score a single AI-generated output against a named rubric (jira-ticket, code-review, email-draft, sql-query, d Read mcp_audit_scan Scan MCP server configurations and produce security scorecards with grades for permissions, data sensitivity, Read mcp_audit_score Score a single MCP server by name and return its full security scorecard Read mcp_doctor_status Return a concise up/down status summary for all MCP servers in the config — useful as a quick sanity check bef Read model_match_compare Compare multiple AI models side-by-side for a specific task type. Scores each model on quality, speed, cost-pe Read model_match_recommend Return the single best-fit AI model for a task, with a plain-English rationale covering quality, latency, and Read probe_scan Scan the current environment for AI tools, MCP servers, agent frameworks, API keys, and local models Read prompt_craft_challenge Fetch this week Read prompt_craft_improve Rewrite a prompt to maximize clarity, specificity, and model alignment. Returns the improved prompt alongside Read prompt_craft_profile Retrieve your prompt-engineering player profile: current level, XP, streak, average score, score history, and Read prompt_craft_score Score a prompt across quality dimensions and award XP toward your prompt-engineering level. Returns numeric sc Read prompt_score_analyze Score prompt quality across 6 dimensions (specificity, structure, efficiency, model fit, best practices, anti- Read prompt_score_improve Get an improved version of your prompt with explanations Read prompt_score_track View prompt quality scores over time Read sub_audit_run Detect all AI subscriptions and API credentials on this machine, then flag redundant overlaps (e.g. Copilot + Read trace_analyze Analyze traces across a time window to surface patterns: most common failure steps, average latency per step t Read trace_list List recent agent execution traces, optionally filtered by agent name and time range. Returns trace IDs, times Read trace_view Retrieve the full execution graph for a specific trace ID, showing each step with its inputs, outputs, latency

EXPLORE

Related servers

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

FAQ

Questions about Scan Your Ai Toolkit

How do I prevent bulk modifications through Scan Your Ai Toolkit? +

The Scan Your Ai Toolkit server has 3 write tools including context_sync_push, context_sync_update, mcp_doctor_fix. 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 Scan Your Ai Toolkit.

How many tools does the Scan Your Ai Toolkit MCP server expose? +

29 tools across 3 categories: Execute, Read, Write. 25 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on Scan Your Ai Toolkit? +

Register the Scan Your Ai Toolkit 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 Scan Your Ai Toolkit tool call.

Deterministic rules across all 29 Scan Your Ai Toolkit tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SCAN YOUR AI TOOLKIT →

Instant setup, no code required.

29 Scan Your Ai Toolkit tools catalogued and risk-classified — across an index of 43,000+ MCP servers.