# NullClear Pre-Execution Firewall & Arbiter (remote · api.nullclear.dev)

7-chain EVM/Solana 1-call Pre-Sign Firewall, Guarded RPC, Proxy/ABI Inspector & x402 Escrow

- Trust score: 63/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `api.nullclear.dev`: 63/100 (this document), [markdown](https://verifymcp.io/servers/nullclear-protocol-nullclear/api.md), [page](https://verifymcp.io/servers/nullclear-protocol-nullclear/api)
- npm · `@nullclear/mcp`: 65/100, [markdown](https://verifymcp.io/servers/nullclear-protocol-nullclear/nullclear-mcp.md), [page](https://verifymcp.io/servers/nullclear-protocol-nullclear/nullclear-mcp)

## Channel facts

- Endpoint: `https://api.nullclear.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.6.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS check failed: the endpoint is reachable over plaintext HTTP.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 78/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2804 tokens (~175/item across 16 items; 14 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: schema churn in the 5 days we've observed: 12 tool removals, 0 breaking changes, 0 auth/transport breaks, 13 additions.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 83/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 1 of 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "nullclear_simulate_transaction" implies "execute" and declares readOnlyHint instead, contradicting what its own name says it does.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the NullClear Pre-Execution Firewall & Arbiter MCP server?

NullClear Pre-Execution Firewall & Arbiter is a hosted endpoint at https://api.nullclear.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http nullclear-protocol-nullclear 'https://api.nullclear.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "nullclear-protocol-nullclear": {
      "url": "https://api.nullclear.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "nullclear-protocol-nullclear": {
      "type": "http",
      "url": "https://api.nullclear.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.nullclear-protocol-nullclear]
url = "https://api.nullclear.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "nullclear-protocol-nullclear": {
      "type": "remote",
      "url": "https://api.nullclear.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add nullclear-protocol-nullclear --url 'https://api.nullclear.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  nullclear-protocol-nullclear:
    url: "https://api.nullclear.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "nullclear-protocol-nullclear": {
      "Transport": "http",
      "Url": "https://api.nullclear.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add nullclear-protocol-nullclear -t streamable-http -u 'https://api.nullclear.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "nullclear-protocol-nullclear": {
      "type": "http",
      "url": "https://api.nullclear.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 63, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional] Server version: 1.5.1 → 1.6.0

### 2026-11-19 (score 63, −1)

- [security] Tool “nullclear_preflight_guard” rewrote its description, which is the text the model reads
- [security] Tool “nullclear_audit_paid_token” rewrote its description, which is the text the model reads
- [security] Tool “nullclear_read_markdown” rewrote its description, which is the text the model reads
- [security] Tool “nullclear_simulate_transaction” rewrote its description, which is the text the model reads
- [security] Tool “nullclear_scan_token” rewrote its description, which is the text the model reads
- [security] Tool “nullclear_decode_calldata” rewrote its description, which is the text the model reads
- [security] Tool “nullclear_inspect_contract” rewrote its description, which is the text the model reads
- [functional] New tool “nullclear_preflight_guard”
- [cosmetic] “nullclear_simulate_transaction” added an optional parameter “stateOverrides”
- [cosmetic] “nullclear_simulate_transaction” added an optional parameter “transaction”
- [cosmetic] “nullclear_simulate_transaction” added an optional parameter “transactions”
- [cosmetic] “nullclear_decode_calldata” added an optional parameter “typedData”
- [cosmetic] “nullclear_scan_token” reworded the description of “address”
- [cosmetic] “nullclear_simulate_transaction” reworded the description of “chain”
- [cosmetic] “nullclear_simulate_transaction” reworded the description of “data”
- [cosmetic] “nullclear_simulate_transaction” reworded the description of “from”
- [cosmetic] “nullclear_simulate_transaction” reworded the description of “to”
- [cosmetic] “nullclear_scan_token” reworded the description of “chain”
- [cosmetic] “nullclear_decode_calldata” reworded the description of “chain”
- [cosmetic] “nullclear_decode_calldata” reworded the description of “input”
- [cosmetic] “nullclear_inspect_contract” reworded the description of “address”
- [cosmetic] “nullclear_inspect_contract” reworded the description of “chain”
- [cosmetic] “nullclear_simulate_transaction” made “to” optional
- [cosmetic] “nullclear_decode_calldata” made “input” optional

### 2026-11-17 (score 64, +1)

- [security regression] Stability: unverified → fail
- [security regression] Tool “nullclear_token_security_audit” was removed
- [security regression] Tool “decode_calldata_or_failed_tx” was removed
- [security regression] Tool “inspect_contract_abi_and_proxy” was removed
- [security regression] Tool “nullclear_crypto_market_oracle” was removed
- [security regression] Tool “nullclear_discover_verified_x402_apis” was removed
- [security regression] Tool “nullclear_escrow_x402_call” was removed
- [security regression] Tool “nullclear_safe_fetch” was removed
- [security regression] Tool “nullclear_verify_kya_mandate” was removed
- [security regression] Tool “nullclear_wallet_risk_score” was removed
- [security regression] Tool “read_url_clean_markdown” was removed
- [security regression] Tool “scan_token_forensics” was removed
- [security regression] Tool “simulate_transaction_preflight” was removed
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “nullclear_check_reputation” rewrote its description, which is the text the model reads
- [security] Tool “nullclear_safe_fetch” rewrote its description, which is the text the model reads
- [security] Tool “nullclear_token_security_audit” rewrote its description, which is the text the model reads
- [security] Tool “nullclear_wallet_risk_score” rewrote its description, which is the text the model reads
- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 1.5.0 → 1.5.1
- [functional] Server version: 1.4.0 → 1.5.0
- [functional] New tool “nullclear_audit_paid_token”
- [functional] New tool “nullclear_decode_calldata”
- [functional] New tool “nullclear_discover_apis”
- [functional] New tool “nullclear_execute_escrow”
- [functional] New tool “nullclear_fetch_guarded”
- [functional] New tool “nullclear_fetch_spot_price”
- [functional] New tool “nullclear_inspect_contract”
- [functional] New tool “nullclear_read_markdown”
- [functional] New tool “nullclear_scan_token”
- [functional] New tool “nullclear_score_wallet”
- [functional] New tool “nullclear_simulate_transaction”
- [functional] New tool “nullclear_verify_mandate”

### 2026-11-16 (score 63)

First indexed and scored.

## MCP tools (14)

### `nullclear_scan_token` (~186 tokens)

Perform a free multi-chain (Base, Ethereum, Arbitrum, Optimism, Polygon, BSC, Solana) token security, proxy resolution, Token-2022 extension/mint/freeze authority audit, honeypot, and buy/sell tax audit (10 free calls/day/IP, zero API key; then $0.005 USDC). Returns score, verdict, recommendedAgentAction, proxy implementation, tax percentages, LP USD, and provenance block number (<400 tokens). Do NOT use for low-level 4-byte selector disassembly on non-token contracts (use nullclear_inspect_contract).

Input parameters:

- `address` (string, required): Token or contract address (0x-prefixed 42-char EVM hex, or Base58 mint address for Solana)
- `chain` (string): Target blockchain network; auto-detects if address exists on an alternate supported chain

### `nullclear_inspect_contract` (~147 tokens)

Disassemble deployed EVM bytecode across Base, Ethereum, Arbitrum, Optimism, Polygon, or BSC to resolve EIP-1967/1822/1167/Beacon/Diamond/Safe proxies, query Sourcify v2 verified ABIs, batch-resolve PUSH4 selectors via OpenChain, and analyze control-flow opcode risks (tx.origin, mutable DELEGATECALL, unguarded SELFDESTRUCT) without an Etherscan key (10 free calls/day/IP).

Input parameters:

- `address` (string, required): 0x-prefixed 42-char EVM smart contract address
- `chain` (string): Target EVM chain (default 'base')

### `nullclear_decode_calldata` (~155 tokens)

Decode EVM calldata (recursively unwrapping Multicall3, Uniswap Universal Router, Safe execTransaction), EIP-712 typed-data signatures (Permit, Permit2, Seaport), Solana wire transactions (Base64/Base58), custom Solidity revert bytes, or mined tx hashes with verified-router spender trust classification (10 free calls/day/IP).

Input parameters:

- `chain` (string): Target network (default 'base')
- `input` (string): 0x-prefixed hex calldata/revert bytes, 66-char tx hash, or Base64/Base58 Solana transaction
- `typedData` (object): Optional EIP-712 typedData JSON (Permit, Permit2, Seaport, SafeTx)

### `nullclear_simulate_transaction` (~211 tokens)

Execute stateful pre-flight simulation across EVM (eth_simulateV1 with stateOverrides, multi-tx bundles, and Transfer/Approval net asset diffs; fallback eth_call + eth_estimateGas) and Solana (simulateTransaction + wire instruction audit) BEFORE signing (10 free calls/day/IP).

Input parameters:

- `chain` (string): Target network (default 'base')
- `data` (string): 0x-prefixed hex calldata payload
- `from` (string): Sender 0x EVM address
- `stateOverrides` (object): Optional EVM stateOverrides map
- `to` (string): Destination 0x smart contract address (required for single EVM call)
- `transaction` (string): Base64/Base58 serialized Solana transaction when chain='solana'
- `transactions` (array): Optional ordered multi-tx EVM bundle [{ to, data, value }]
- `value` (string): Native wei amount as hex ('0x0') or decimal string

### `nullclear_read_markdown` (~127 tokens)

Fetch and convert any public web documentation URL or HTML article into clean, stripped Markdown (<400 tokens) with a SHA-256 content hash. Use this when reading documentation, blog posts, or web pages while minimizing context-window noise (10 free calls/day/IP). Returns markdown body and provenance hash. Do NOT use for JSON REST APIs or schema-enforced x402 data endpoints needing LLM-refusal/5xx protection (use nullclear_fetch_guarded or nullclear_execute_escrow).

Input parameters:

- `url` (string, required): Public HTTPS webpage or documentation URL to extract into clean Markdown

### `nullclear_preflight_guard` (~309 tokens)

All-in-one 1-call Pre-Sign Firewall across Base, Ethereum, Arbitrum, Optimism, Polygon, BSC, and Solana (10 free calls/day/IP). In one pass, recursively unwraps Multicall3/Uniswap Universal Router/Safe calldata or EIP-712 Permits or Solana wire txs, runs stateful eth_simulateV1 / Solana simulateTransaction with asset balance diffs, and automatically scans all touched token contracts for honeypots, taxes, and Token-2022 permanent delegates. Returns one deterministic recommendedAgentAction (EXECUTE_SAFE / CAUTION_HIGH_RISK / ABORT_*).

Input parameters:

- `chain` (string): Target network (default 'base')
- `data` (string): 0x-prefixed EVM calldata
- `from` (string): Sender 0x EVM address
- `stateOverrides` (object): Optional EVM eth_simulateV1/eth_call stateOverrides map
- `to` (string): Target contract 0x address or Solana mint
- `transaction` (string): Optional Base64/Base58 serialized Solana transaction to decode and simulate
- `transactions` (array): Optional ordered multi-tx bundle [{ to, data, value }]
- `typedData` (object): Optional EIP-712 typedData object (Permit, Permit2, Seaport, SafeTx) to audit before signing
- `value` (string): Native wei amount ('0x0')

### `nullclear_discover_apis` (~231 tokens)

Search NullClear's audited x402 and ERC-8004 endpoint directory by keyword, category, minimum uptime, and maximum latency. Use this before paying external x402 sellers to find reliable APIs and retrieve their NullClear Zero-Loss Proxy URL (`https://api.nullclear.dev/https://...`). Returns matched endpoints with priceAtomic, uptimeScore, latencyMs, and proxy URL. Do NOT use to execute a call (pass the returned URL to nullclear_execute_escrow).

Input parameters:

- `category` (string): Exact category filter ('oracle', 'security', 'data', or 'ai')
- `maxLatencyMs` (number): Maximum acceptable edge round-trip latency in milliseconds (default 2000)
- `minUptime` (number): Minimum rolling uptime percentage threshold from 0 to 100 (default 95)
- `query` (string): Keyword filter matching endpoint URL or description (e.g. 'oracle', 'security', 'token', 'wallet')
- `verifiedOnly` (boolean): When true, filter exclusively to canary-verified HTTP 402 endpoints (default true)

### `nullclear_audit_paid_token` (~136 tokens)

Run NullClear's x402 Bazaar paid oracle for Base Mainnet (8453) ERC-20 tokens returning a cryptographically signed clearing receipt (10 free trial calls/day, then $0.005 USDC). Use this ONLY when you specifically require a Base Bazaar EIP-712/keccak256 settlement receipt alongside token LP and bytecode verification. For free (10/day) multi-chain Base/ETH/Solana token & proxy scanning, use nullclear_scan_token instead.

Input parameters:

- `tokenAddress` (string, required): 0x-prefixed Base Mainnet (chain 8453) ERC-20 token contract address

### `nullclear_score_wallet` (~164 tokens)

Profile a raw 0x EVM wallet address on Base Mainnet (8453) for OFAC sanctions exposure, on-chain counterparty wash-trade concentration, ETH/USDC balances, transaction count, and ERC-8004 ownership (10 free trials/day, then $0.005 USDC). Returns riskScore (0-100), riskLevel, and ERC-8004 registration status. Do NOT pass a numeric ERC-8004 agent ID here — use nullclear_check_reputation for numeric agentId trust audits.

Input parameters:

- `chainId` (number): EVM chain ID (default 8453 for Base Mainnet)
- `walletAddress` (string, required): 0x-prefixed 42-char EVM wallet address on Base Mainnet to screen

### `nullclear_fetch_spot_price` (~121 tokens)

Query cross-exchange spot prices (Coinbase + Binance) for major crypto pairs with deterministic positive-price invariant verification and signed attestation (10 free trials/day, then $0.01 USDC). Returns priceUsd, source, invariantCheck ('PASSED'), and execution receipt. Use this whenever a verified non-hallucinated crypto spot price feed is needed.

Input parameters:

- `pair` (string, required): Asset ticker or pair such as 'ETH/USDC', 'BTC/USDC', 'SOL/USDC', or 'ETH-USD'

### `nullclear_fetch_guarded` (~184 tokens)

Execute a zero-schema Auto-Guarded HTTP GET/POST request through NullClear's firewall against HTTP 5xx crashes, empty JSON bodies, Cloudflare/soft-paywall traps, and LLM refusal strings (10 free trials/day, then $0.005 USDC via Bazaar). Returns verified payload and executionReceipt, or voids settlement on failure. Do NOT use for plain HTML docs-to-Markdown conversion (use nullclear_read_markdown) or when custom JSON Schema/invariants/failover are needed (use nullclear_execute_escrow).

Input parameters:

- `body` (string): Optional serialized JSON request body string for POST requests
- `method` (string): HTTP method ('GET' or 'POST', default 'GET')
- `url` (string, required): Public HTTPS API or data endpoint URL to fetch with automatic crash, paywall, and refusal guards

### `nullclear_execute_escrow` (~335 tokens)

Execute a paid x402 API request protected by NullClear deferred non-custodial EIP-3009 escrow, custom JSON Schema/value invariants, multi-seller failover routing, and outbound spend caps (10 free trials/day, then requires configured wallet key). Settles upstream payment ONLY when all schema, numeric, staleness, and refusal checks pass; otherwise voids authorization ($0 lost). Use this instead of nullclear_fetch_guarded whenever calling third-party x402 paid APIs with strict output contracts or fallback sellers.

Input parameters:

- `fallbacks` (array): Up to 3 ordered backup seller objects ({ targetUrl, sellerAgentId, paymentSignatureHeader }) for automatic failover
- `invariants` (array): Field-level semantic invariants (numeric bounds, regex, forbidden substrings, timestamp freshness)
- `jsonSchema` (object): JSON Schema Draft-07 object that upstream JSON must strictly satisfy
- `method` (string): HTTP method for upstream call
- `minTrustScore` (number): Minimum seller trust score (0-100, default 50)
- `rejectRefusals` (boolean): Void settlement if response contains canonical LLM refusal strings (default true)
- `requiredFields` (array): Dot-notation field paths that must exist in upstream JSON
- `sellerAgentId` (string): ERC-8004 seller agent ID for pre-flight trust and Sybil gating
- `spendPolicy` (object): Outbound spend firewall caps ({ maxPerCallAtomic, maxDailyWalletAtomic })
- `targetUrl` (string, required): Primary upstream HTTPS endpoint demanding HTTP 402 payment

### `nullclear_check_reputation` (~166 tokens)

Retrieve an ERC-8004 registered agent's composite trust score (0-100), letter grade (A-F), historical clearing count, and Sybil wash-trading penalty flags by numeric agentId. Returns arbiter-signed reputation metrics and sybilFlags. Use this ONLY for registered ERC-8004 agent IDs (e.g. '124595'); for raw 0x wallet address OFAC/balance profiling use nullclear_score_wallet, and for legal corporate liability limits use nullclear_verify_mandate.

Input parameters:

- `agentId` (string, required): Registered numeric ERC-8004 agent token ID (e.g. '124595')
- `chainId` (number): Target EVM chain ID (8453 for Base Mainnet, 84532 for Base Sepolia)

### `nullclear_verify_mandate` (~161 tokens)

Verify an autonomous agent's Know Your Agent (KYA) EIP-712 corporate liability mandate, jurisdiction, expiration status, and whether a proposed USD transaction amount complies with corporate per-transaction caps. Returns approved boolean, corporateEntity, liabilityCoverageUsd, maxTxLimitUsd, and expiration/limit flags. Use this specifically for corporate authorization checks — not for on-chain Sybil scoring (use nullclear_check_reputation).

Input parameters:

- `agentId` (string, required): Registered numeric ERC-8004 agent token ID bound to a KYA mandate
- `chainId` (number): EVM chain ID (default 8453 for Base Mainnet)
- `transactionAmountUsd` (number, required): Proposed transaction size in USD to validate against the mandate limit

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/nullclear-protocol-nullclear/api#diagnostics

## Score history

- 2026-11-21: 63
- 2026-11-20: 63
- 2026-11-19: 63
- 2026-11-18: 64
- 2026-11-17: 64
- 2026-11-16: 63

## Common questions

### What is the NullClear Pre-Execution Firewall & Arbiter MCP server?

NullClear Pre-Execution Firewall & Arbiter is an MCP server listed in the public MCP registry as io.github.Nullclear-Protocol/nullclear. 7-chain EVM/Solana 1-call Pre-Sign Firewall, Guarded RPC, Proxy/ABI Inspector & x402 Escrow. This page covers its hosted endpoint (https://api.nullclear.dev/mcp).

### Is the NullClear Pre-Execution Firewall & Arbiter MCP server safe to use?

NullClear Pre-Execution Firewall & Arbiter scores 63 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the NullClear Pre-Execution Firewall & Arbiter MCP server expose?

NullClear Pre-Execution Firewall & Arbiter exposes 14 tools: nullclear_scan_token, nullclear_inspect_contract, nullclear_decode_calldata, nullclear_simulate_transaction, nullclear_read_markdown, and 9 more. Their descriptions and schemas cost roughly 2,633 tokens of context every time the server is loaded.

### Does the NullClear Pre-Execution Firewall & Arbiter MCP server require authentication?

No. We connected to NullClear Pre-Execution Firewall & Arbiter without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the NullClear Pre-Execution Firewall & Arbiter MCP server still maintained?

NullClear Pre-Execution Firewall & Arbiter is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the NullClear Pre-Execution Firewall & Arbiter MCP server?

VerifyMCP ran 13 checks on NullClear Pre-Execution Firewall & Arbiter, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://api.nullclear.dev/mcp
- Repository: https://github.com/Nullclear-Protocol/nullclear
- Website: https://nullclear.dev/
- Changelog RSS feed: https://verifymcp.io/servers/nullclear-protocol-nullclear/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/nullclear-protocol-nullclear/api/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/nullclear-protocol-nullclear/api.json
- HTML version of this page: https://verifymcp.io/servers/nullclear-protocol-nullclear/api
