CAT
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

SettlementWitness

nutstrut/default-settlement-verifier
HTTPregistry active
Summary

Connects Claude to DefaultVerifier's SAR (Settlement Attestation Receipt) infrastructure for cryptographic verification of agent task completion. Exposes endpoints to submit task specs and outputs, receive signed receipts with verdict and confidence scores, retrieve receipts by ID or wallet address, and access public verification keys. Useful when you need provable attestation that an AI agent actually fulfilled its specification, especially in multi-party scenarios where settlement or payment depends on verified execution. Receipts are Ed25519-signed, publicly retrievable, and include counterparty binding for bilateral agreements. Ships with verification examples in Node and Python for local signature checking against the published JWKS.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →

DefaultVerifier — SAR Verification Infrastructure

SAR (Settlement Attestation Receipt) is a verification protocol that produces cryptographically signed receipts proving whether an AI agent completed a task according to its specification.

DefaultVerifier is a live SAR verifier implementation with a public receipt registry, metrics API, and explorer.

If it matters—Verify it.

Architecture

Understand the SAR stack and verification model:

👉 SAR Architecture


Example Response

{ "witness": "SettlementWitness", "witness_version": "v0", "task_id": "example", "verifier_endpoint": "https://defaultverifier.com/verify", "witness_timestamp": "2026-01-01T00:00:00Z", "receipt_id": "...", "receipt_v0_1": { "task_id_hash": "sha256:...", "verdict": "PASS", "confidence": 1.0, "reason_code": "SPEC_MATCH", "ts": "...", "verifier_kid": "...", "counterparty": "0xABC...", "receipt_id": "sha256:...", "sig": "base64url:..." },

"_ext": { "agent_id": "0x123:demo" } }


Notes

  • receipt_v0_1 is the signed canonical receipt payload used by this implementation
  • when counterparty is present, it is included in signature scope and in receipt_id derivation
  • legacy receipts (sar-prod-ed25519-01 and sar-prod-ed25519-02) remain valid and do not include counterparty in signature scope
  • this behavior is implemented and publicly verifiable via the live receipt and key endpoints

SAR Compatibility: This implementation follows SAR verification semantics, with an extended signed payload when counterparty is present.

Demo

Run a full end-to-end verification in ~2 minutes: DEMO.md

Quick Start

1. Create a receipt

curl -X POST https://defaultverifier.com/settlement-witness
-H 'content-type: application/json'
-d '{ "task_id":"quickstart-001", "spec":{"goal":"demo"}, "output":{"goal":"demo"}, "counterparty":"0x1234567890abcdef1234567890abcdef12345678" }'

2. Fetch the receipt

curl https://defaultverifier.com/settlement-witness/receipt/<receipt_id>

Note: use the receipt_id inside receipt_v0_1

3. Verify locally (Node)

cd examples/node-verify node verify.js receipt.json jwks.json

Examples

Node.js verification example: examples/node-verify/

Python verification example: examples/verify_receipt_python.py

Usage: python3 examples/verify_receipt_python.py <receipt_id>

API Endpoints

Create Receipt

POST /settlement-witness

Submits a task verification request and returns a signed SAR receipt.


Retrieve Receipt

GET /settlement-witness/receipt/{receipt_id}

Note: Use the receipt_id inside receipt_v0_1 (sha256:...) for retrieval.

Returns a previously issued receipt.


Wallet Receipt Explorer

GET /settlement-witness/receipts?wallet={address}

Returns recent receipts associated with a wallet address.

The public explorer is available at:

https://defaultverifier.com/explorer

This interface allows browsing recent receipts and wallet-indexed delivery history.


Public Verification Keys

https://defaultverifier.com/.well-known/jwks.json

Alternative (SAR protocol reference): https://defaultverifier.com/.well-known/sar-keys.json

Used to verify Ed25519 signatures for receipts.


Key Registry

https://defaultverifier.com/.well-known/sar-keys.json

Registry of verifier public keys referenced by verifier_kid.

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Categories
AI & LLM Tools
Registryactive
TransportHTTP
UpdatedFeb 8, 2026
View on GitHub

Related AI & LLM Tools MCP Servers

View all →
SkillFM LLM Cost Optimizer

io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage

LLM cost optimizer for OpenAI, Anthropic, token usage, BYOK, and SkillFM Beacon audits.
Llm Orchestration Agent

io.github.mikerawsonnz/llm-orchestration-agent

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith
Authenticated Llm Agent

io.github.mikerawsonnz/authenticated-llm-agent

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.
Copilot Memory MCP

labforgedev/copilot-memory-mcp

Persistent semantic memory for AI agents using local ChromaDB vector search. No cloud required.
1
Agent Prompt Injection Firewall Mcp

csoai-org/agent-prompt-injection-firewall-mcp

The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...
Authenticated Multi Llm Agent

io.github.mikerawsonnz/authenticated-multi-llm-agent

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f