# search_circuits

Search 0gzk ZK circuits by natural-language query (matched against names, tags, keywords, use cases, and descriptions). In repo mode this searches the local catalog; without a repo it falls back to substring-matching circuit names on a live registry.

Agent View of the PolicyLayer registry record for `search_circuits`. HTML page: https://policylayer.com/tools/0gzk-mcp/search-circuits

## Facts

- Tool: `search_circuits`
- Server: 0gzk (`@0gzk/mcp`) — https://policylayer.com/tools/0gzk-mcp.md
- Install: `npx -y @0gzk/mcp`
- Homepage: https://www.npmjs.com/package/@0gzk/mcp
- Risk category: Read (Low risk)
- Registry record: grade B, identity unverified
- Server rate-limited: no
- Parameters: 3 (1 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `chain` | string | no | Only report publications on this chain (catalog mode) / registry to enumerate (discovery mode) |
| `limit` | integer | no | Maximum results |
| `query` | string | yes | What the circuit should do, e.g. "prove age over 18" |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "search_circuits",
    "arguments": {
      "query": "<query>"
    }
  }
}
```

## Why search_circuits is rated Low

Even though search_circuits only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

## Use case

AI agents call search_circuits to retrieve information from 0gzk without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches 0gzk:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "search_circuits": {}
  }
}
```

## Other tools on 0gzk (7)

- `get_circuit` — Read — https://policylayer.com/tools/0gzk-mcp/get-circuit.md
- `get_example_input` — Read — https://policylayer.com/tools/0gzk-mcp/get-example-input.md
- `list_circuits` — Read — https://policylayer.com/tools/0gzk-mcp/list-circuits.md
- `prove_circuit` — Read — https://policylayer.com/tools/0gzk-mcp/prove-circuit.md
- `read_input_file` — Read — https://policylayer.com/tools/0gzk-mcp/read-input-file.md
- `validate_inputs` — Read — https://policylayer.com/tools/0gzk-mcp/validate-inputs.md
- `resolve_circuit` — Write — https://policylayer.com/tools/0gzk-mcp/resolve-circuit.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=0gzk-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/0gzk-mcp