// SCAN REPORT

Nanostores MCP

12 tools. 1 can modify or destroy data without limits.

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

Last updated: 30 Jun 2026

1 can modify or destroy data

11 read-only

12 tools total

Verified server · catalogue entry verified 30/06/2026 · full schemas captured for 12 of 12 tools

How to control Nanostores MCP ↓

TOOL MAP

What Nanostores MCP exposes to your agents

Read (11) Write / Execute (0) Destructive / Financial (1)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Nanostores MCP costs in tokens

2,089 tokens of tool definitions, loaded on every request

1.0% of a 200k context window

278 heaviest tool: nanostores_docs_search

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

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Nanostores MCP tools

Destructive · Low nanostores_clear_cache The tool irreversibly clears/purges a cached index.

1 of Nanostores MCP'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 Nanostores MCP

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

Deny destructive operations

{
  "nanostores_clear_cache": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Cap read operations

{
  "nanostores_docs_search": {
    "limits": [
      {
        "counter": "nanostores_docs_search_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 Nanostores MCP — 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 NANOSTORES →

Instant setup, no code required.

FULL CATALOGUE

All 12 Nanostores MCP tools

DESTRUCTIVE 1 tools

Destructive nanostores_clear_cache Use this when scan results seem stale or after making file changes that the server may not have detected. Clea

READ 11 tools

Read nanostores_docs_search Find Nanostores documentation by topic or store kind. Use query for free-text search across guides, API refere Read nanostores_find_noisy_stores Use this when investigating performance issues or excessive re-renders. Returns stores ranked by activity — fr Read nanostores_ping Use this when you need to verify the MCP server is alive or check whether the runtime logger bridge is connect Read nanostores_project_outline Use this for a quick overview of Nanostores usage in the project — store kind distribution, top directories, a Read nanostores_runtime_coverage Compare static analysis graph with runtime event data to find stores declared in the static graph but not obse Read nanostores_runtime_overview Use this when you want a high-level health check of the running app's state management. Returns active stores, Read nanostores_scan_project Returns the complete store/subscriber/relation index for the project. Use compact:true for a token-efficient d Read nanostores_store_activity Use this when debugging a specific store's runtime behavior — why it updates too often, what actions trigger c Read nanostores_store_impact When you need to trace what recomputes if X changes, call this once — not nanostores_store_summary on each dow Read nanostores_store_subgraph If your question is 'what recomputes downstream when X changes?', use nanostores_store_impact instead — it giv Read nanostores_store_summary Use this when you need details about a specific store — its kind, file location, direct subscribers, and first

EXPLORE

Related servers

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

FAQ

Questions about Nanostores MCP

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

Yes. The Nanostores MCP server exposes 1 destructive tools including nanostores_clear_cache. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How many tools does the Nanostores MCP server expose? +

12 tools across 3 categories: Destructive, Execute, Read. 11 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on Nanostores MCP? +

Register the Nanostores 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 Nanostores MCP tool call.

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

ENFORCE POLICY ON NANOSTORES →

Instant setup, no code required.

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