When you need to trace what recomputes if X changes, call this once — not nanostores_store_summary on each downstream store. Returns the full ordered downstream chain in a single response: computed stores that depend on X at hop 1, their dependents at hop 2, and so on. Subscribers appear at the s...
AI agents call nanostores_store_impact to retrieve information from Nanostores MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | — | Store name. Used if storeId is not provided. |
storeId | string | — | Exact store id. If provided, takes priority. |
projectRoot | string | — | Project root path (uses default if omitted) |
Parameters from the server's own tool schema.
This is a debugging/analysis tool that queries the dependency graph of Nanostores to understand which stores and subscribers would be affected by a change. It only retrieves and returns dependency information without modifying state, executing code, or triggering side effects. The blast radius of misuse is minimal—worst case an AI agent spends compute cycles on unnecessary queries.
From the tool's definition Tool performs tracing and analysis of store dependencies: 'trace what recomputes if X changes', 'returns the full ordered downstream chain', 'computed stores that depend on X', 'every computed store and subscriber that recomputes'.
Attacks that exploit this kind of access
When you need to trace what recomputes if X changes, call this once — not nanostores_store_summary on each downstream store. Returns the full ordered downstream chain in a single response: computed stores that depend on X at hop 1, their dependents at hop 2, and so on. Subscribers appear at the same hop as the store they react to. Use nanostores_store_subgraph instead when you also need upstream ancestors (BFS in both directions). Example: {name: "$isLoggedIn"} returns every computed store and subscriber that recomputes when $isLoggedIn changes, ordered by distance. It is categorised as a Read tool in the Nanostores MCP MCP Server, which means it retrieves data without modifying state.
nanostores_store_impact accepts 3 parameters: name, storeId, projectRoot. The full parameter table on this page comes from the server's own tool schema.
Register the Nanostores MCP server in PolicyLayer and add a rule for nanostores_store_impact: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Nanostores MCP. Nothing to install.
nanostores_store_impact is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the nanostores_store_impact rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for nanostores_store_impact. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
nanostores_store_impact is provided by the Nanostores MCP server (nanostores-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →