@nullclear/mcp

MCPcommunitylive

v1.2.0NullClear ProtocolMITUpdated 4d agonpm GitHub

Model Context Protocol server for autonomous agents using NullClear

Endpoint healthlive

checked 17h ago · 356ms

100% of the last 1 check reached this endpoint

Works in

ClaudeCursorCopilotChatGPTGemini

Inferred from the transports this listing declares (stdio, streamable-http). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →

345Downloads/wk

1GitHub stars

4d agoLast update

Package

AuthorNullClear Protocol

LicenseMIT

Version1.2.0

Sourcenpm+mcp-registry

npm@nullclear/mcp

GitHubNullclear-Protocol/nullclear

SBOMCycloneDX 1.6 ↓

Trust Status

B

60/100Good

✓Listed in Forge index+10/10

—Publisher identity verified+0/20

→ Publisher: run `forge publish` from the package repo to claim ownership

—Ed25519 publish signature+0/5

→ Included automatically when the publisher runs `forge publish`

—Domain verification+0/5

→ Publisher: host /.well-known/forge.json on the package homepage with { "publisher": "<github-login>" }

—npm Trusted Publishing (Sigstore)+0/5

→ Publish from GitHub Actions with --provenance so the attestation binds this package to this repo

—npm maintainer match+0/5

→ Earned once your identity is verified above and that login is an npm maintainer of this package

✓CVE scan · clean+30/30

✓Static analysis · clean+20/20

Paste into Claude Code, Cursor, or any AI assistant to fix all gaps

StatusCommunity-indexed

PublisherUnverified

SignatureUnsigned

Domain—

Provenance—

Dependencies✓ 60 resolved+ · none vulnerable

Tool surface14 tools · none privileged

Security scan✓ Cleanv1.2.0 · todayHow well does this scan work?

EvalsNone

IndexedOct 19, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.

Tools

14 tools · none privileged

Statically extracted from the published packagev1.2.0 · 17h ago

Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.

Filter toolsPrivileged only

nullclear_token_security_auditAudit any Base ERC-20 token address for honeypots, buy/sell taxes, verified bytecode, and x402 compatibility via NullClear Bazaar. Works out-of-the-box with zero configuration (10 free daily calls included).

Audit any Base ERC-20 token address for honeypots, buy/sell taxes, verified bytecode, and x402 compatibility via NullClear Bazaar. Works out-of-the-box with zero configuration (10 free daily calls included).

No input schema was published for this tool.

nullclear_wallet_risk_scoreCheck any wallet or agent address on Base for OFAC sanctions, Sybil wash-trading concentration flags, and ERC-8004 counterparty reputation. Works out-of-the-box with zero configuration (10 free daily calls included).

Check any wallet or agent address on Base for OFAC sanctions, Sybil wash-trading concentration flags, and ERC-8004 counterparty reputation. Works out-of-the-box with zero configuration (10 free daily calls included).

No input schema was published for this tool.

nullclear_crypto_market_oracleFetch multi-exchange spread-verified crypto spot prices (ETH/USDC, BTC/USDC, SOL/USDC, BASE/USDC) with cryptographic NullClear invariant receipts. Works out-of-the-box with zero configuration (10 free daily calls included).

Fetch multi-exchange spread-verified crypto spot prices (ETH/USDC, BTC/USDC, SOL/USDC, BASE/USDC) with cryptographic NullClear invariant receipts. Works out-of-the-box with zero configuration (10 free daily calls included).

No input schema was published for this tool.

nullclear_safe_fetchZero-config drop-in URL fetcher with automatic Canonical LLM Refusal Guard, HTTP 5xx crash guard, empty-JSON guard, and cryptographic execution receipt. Protects agents from hallucinated or broken API responses.

Zero-config drop-in URL fetcher with automatic Canonical LLM Refusal Guard, HTTP 5xx crash guard, empty-JSON guard, and cryptographic execution receipt. Protects agents from hallucinated or broken API responses.

No input schema was published for this tool.

nullclear_escrow_x402_callExecute an x402-gated HTTP API call through NullClear deferred schema escrow. The arbiter guarantees payment is only settled if upstream returns valid data matching your schema contract. Works out-of-the-box with 10 free daily trial calls before requiring NULLCLEAR_PRIVATE_KEY.

Execute an x402-gated HTTP API call through NullClear deferred schema escrow. The arbiter guarantees payment is only settled if upstream returns valid data matching your schema contract. Works out-of-the-box with 10 free daily trial calls before requiring NULLCLEAR_PRIVATE_KEY.

No input schema was published for this tool.

nullclear_check_reputationInspect an AI agent's trust score (0-100), clearing reliability, Sybil wash-trade penalty flags, and corporate KYA backing on Base

Inspect an AI agent's trust score (0-100), clearing reliability, Sybil wash-trade penalty flags, and corporate KYA backing on Base

No input schema was published for this tool.

nullclear_verify_kya_mandateVerify an agent's Know Your Agent (KYA) corporate liability mandate, active validity, and whether a proposed transaction amount is within corporate limits

Verify an agent's Know Your Agent (KYA) corporate liability mandate, active validity, and whether a proposed transaction amount is within corporate limits

No input schema was published for this tool.

safe-x402-paymentGenerate safety invariants and schema-escrow directives for an autonomous agent paying an upstream x402 seller.

Generate safety invariants and schema-escrow directives for an autonomous agent paying an upstream x402 seller.

No input schema was published for this tool.

targetUrlUpstream API endpoint demanding x402 payment

Upstream API endpoint demanding x402 payment

No input schema was published for this tool.

sellerAgentIdSeller's ERC-8004 agent token ID to verify reputation

Seller's ERC-8004 agent token ID to verify reputation

No input schema was published for this tool.

maxSpendAtomicMaximum atomic USDC units authorized (default: 10000 = $0.01 USDC)

Maximum atomic USDC units authorized (default: 10000 = $0.01 USDC)

No input schema was published for this tool.

audit-erc8004-agentConduct an end-to-end trust audit on an ERC-8004 agent on Base including Sybil risk and corporate KYA backing.

Conduct an end-to-end trust audit on an ERC-8004 agent on Base including Sybil risk and corporate KYA backing.

No input schema was published for this tool.

agentIdERC-8004 agent token ID (e.g. '124595')

ERC-8004 agent token ID (e.g. '124595')

No input schema was published for this tool.

chainIdBase chain ID (default: 8453)

Base chain ID (default: 8453)

No input schema was published for this tool.

14 of 14 tools published a description.

Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.

About

Model Context Protocol server for autonomous agents using NullClear

Keywords

mcpmodel-context-protocolx402erc-8004agent-paymentsescrowreputationbasesmithery

Alternatives

Comparing tool surfaces…

Tools exposed

14 tools · none privileged · observed 2026-10-19 by static extraction. A tool surface is what one scan read on one day, not a live capability list.

nullclear_token_security_audit
nullclear_wallet_risk_score
nullclear_crypto_market_oracle
nullclear_safe_fetch
nullclear_escrow_x402_call
nullclear_check_reputation
nullclear_verify_kya_mandate
safe-x402-payment
targetUrl
sellerAgentId
maxSpendAtomic
audit-erc8004-agent
agentId
chainId

Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.

Dependency tree

What one Forge scan resolved from npm metadata on 2026-10-19 — observed resolution, not a publisher declaration.

60 packages resolved · 5 direct · none carrying advisories Resolution stops at depth 4 and 60 packages.

zod3.25.76
viem2.57.78 dependencies
- ox0.14.56+4 not drawn4 dependencies
  - @scure/bip321.7.0+2 not drawn1 dependency
    @noble/hashes1.8.0
  - @scure/bip391.6.0+1 not drawn1 dependency
    @noble/hashes1.8.0shown above
  - @noble/curves1.9.11 dependency
    @noble/hashes1.8.0shown above
  - @noble/hashes1.8.0shown above
- ws8.21.0
- isows1.0.7
- abitype1.2.3
- @scure/bip321.7.0shown above+2 not drawn
- @scure/bip391.6.0shown above+1 not drawn
- @noble/curves1.9.1shown above
- @noble/hashes1.8.0shown above
@nullclear/shared1.2.02 dependencies
- zod3.25.76shown above
- viem2.57.7shown above
@nullclear/x402-arbiter1.2.03 dependencies
- zod3.25.76shown above
- viem2.57.7shown above
- @nullclear/shared1.2.0shown above
@modelcontextprotocol/sdk1.32.1+6 not drawn11 dependencies
- ajv8.20.0+4 not drawn
- zod4.6.7
- cors2.8.6+2 not drawn
- hono4.13.13
- jose6.2.12
- express5.3.0incomplete+20 not drawn
- raw-body3.0.2incomplete
- ajv-formats3.0.1incomplete
- cross-spawn7.0.6incomplete
- eventsource3.0.7incomplete
- content-type1.0.5

The crawl stopped at the 60-package limit. The rest of the tree was never resolved.

36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)

Declared but not resolved

58 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.

package cap reached: 58

http-errors ^2.0.0 — required by express@5.3.0package cap reached
on-finished ^2.4.1 — required by express@5.3.0package cap reached
content-type ^2.0.0 — required by express@5.3.0package cap reached
finalhandler ^2.1.0 — required by express@5.3.0package cap reached
range-parser ^1.2.1 — required by express@5.3.0package cap reached
serve-static ^2.2.0 — required by express@5.3.0package cap reached
cookie-signature ^1.2.1 — required by express@5.3.0package cap reached
merge-descriptors ^2.0.0 — required by express@5.3.0package cap reached
content-disposition ^2.0.1 — required by express@5.3.0package cap reached
bytes ~3.1.2 — required by raw-body@3.0.2package cap reached
unpipe ~1.0.0 — required by raw-body@3.0.2package cap reached
iconv-lite ~0.7.0 — required by raw-body@3.0.2package cap reached

+46 more not listed. The counts by reason above cover all of them.

Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.

Topics

Related in payments & commerce

stripe/agent-toolkitStripe's official toolkit for AI-powered products — includes MCP server, tools, and SDKs
@respira/wordpress-mcp-serverWordPress MCP server + companion plugin giving AI native access to page builder content, n
ecommerce-visual-copywriting电商主图与详情页视觉策划 Skill。根据产品资料、资质边界、目标平台和视觉参考，先判断转化驱动力并锁定 Campaign Style Lock，再输出主图/详情页 Storybo
cyberdyne-mcpEngagement marketplace on Base, native to the Bankr ecosystem: AI agents and communities f
@three-ws/agentcore-payments-mcpGoverned x402 payment sessions: pay any endpoint with budget, allowlist & per-tx caps, no
socialcrawl-mcpOne unified API for social and web data — social media (incl. Douyin, Xiaohongshu, Telegra
bizfile-mcpPre-payment counterparty verification for AI agents. KYC, risk screening across 386 data s
apiguru-mcpLive Amazon marketplace data for AI agents as MCP tools: product details, reviews, keyword