// SCAN REPORT

0gzk

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

1 write tool that can modify data. Rate limits recommended.

Last updated: 2 Sept 2026

1 can modify or destroy data

7 read-only

8 tools total

Community server · catalogue entry checked 02/09/2026 · full schemas captured for 8 of 8 tools

How to control 0gzk ↓

TOOL MAP

What 0gzk exposes to your agents

Read (7) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What 0gzk costs in tokens

1,493 tokens of tool definitions, loaded on every request

0.7% of a 200k context window

345 heaviest tool: prove_circuit

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

MOST DANGEROUS TOOLS

High Risk

The most dangerous 0gzk tools

Write · Medium resolve_circuit Resolve a "name" or "name@version" spec against the on-chain registries and report the published record per chain (rootHash, vkeyHash, verif

1 of 0gzk's 8 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control 0gzk

PolicyLayer is an MCP gateway — it sits between your AI agents and 0gzk, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "resolve_circuit": {
    "limits": [
      {
        "counter": "resolve_circuit_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_circuit": {
    "limits": [
      {
        "counter": "get_circuit_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 0gzk — 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 0GZK →

Instant setup, no code required.

FULL CATALOGUE

All 8 0gzk tools

WRITE 1 tools

Write resolve_circuit Resolve a "name" or "name@version" spec against the on-chain registries and report the published record per ch

READ 7 tools

Read get_circuit Get the full record for one circuit: metadata (inputs/outputs), constraints, example input, publications, and Read get_example_input Get the committed example_input.json for a catalog circuit — the fastest way to see a valid input shape. Read list_circuits List known circuits. source=catalog lists the local repo catalog (name/version/description/tags/publications); Read prove_circuit Generate a Groth16 proof (and locally verify it) for a circuit, optionally saving the artifacts to disk. Bundl Read read_input_file Read a JSON file of circuit inputs from the user's machine so it can be validated and proved. Returns only the Read search_circuits Search 0gzk ZK circuits by natural-language query (matched against names, tags, keywords, use cases, and descr Read validate_inputs Check a set of user-supplied circuit inputs against the circuit's declared signal schema WITHOUT proving. Retu

FAQ

Questions about 0gzk

How do I prevent bulk modifications through 0gzk? +

The 0gzk server has 1 write tools including resolve_circuit. 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 0gzk.

How many tools does the 0gzk MCP server expose? +

8 tools across 2 categories: Read, Write. 7 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on 0gzk? +

Register the 0gzk 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 0gzk tool call.

Deterministic rules across all 8 0gzk tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON 0GZK →

Instant setup, no code required.

8 0gzk tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from 0gzk's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →