Default Settlement Verifier
The Default Settlement Verifier is a stateless, deterministic verification service used to evaluate whether the declared settlement results meet the preset conditions. It provides a signed binary verdict (pass/fail), does not hold funds or enforce, and aims to provide neutral and replayable verification credentials for inter-agent payments and programmatic settlement processes.
rating : 2 points
downloads : 0
What is the Default Settlement Verifier?
The Default Settlement Verifier is a stateless verification service that specifically answers one question: 'Given this settlement statement and these conditions, does it pass verification?' It evaluates settlement results through deterministic rules and generates verification results with cryptographic signatures, providing a reliable basis for downstream payment or execution decisions.How to use the Default Settlement Verifier?
It's very simple to use: Send a JSON object containing the task ID, specification (spec), and actual output (output) to the verification endpoint via an HTTP POST request. The service will immediately return a response containing the verification result (PASS/FAIL), confidence score, and digital signature. This signed result can be used by any downstream system (such as a payment gateway, smart contract, or agent workflow) to trigger settlement.Use cases
It is most suitable for automated scenarios that require 'verify first, then pay' or 'conditional release'. For example: After an AI agent completes a data scraping task, it needs to prove that it has output the correct data format before it can receive payment; or in a multi-step workflow, only after the output of the previous step is verified to meet the specification will the payment for the next step be triggered.Main features
Deterministic verification
The same input (task ID, specification, output) always produces exactly the same signed verification result, ensuring the reproducibility and fairness of the results.
Stateless service
The service does not save any session or task state. Each verification request is independent, which makes the service highly reliable and easy to scale.
Cryptographic receipts
Each verification result is accompanied by a cryptographic signature, generating an untamperable'receipt'. Anyone can verify the authenticity of the receipt using the public key.
SettlementWitness wrapper
It provides a simpler interface (SettlementWitness), specifically designed for agent workflows, and returns structured receipts for easy integration into AI agents or automated systems.
MCP (Model Context Protocol) integration
It can be directly called through the MCP protocol, enabling AI assistants (such as Claude Desktop) to directly request settlement verification without complex backend integration.
Neutral arbiter
The service itself has no bias, does not favor the buyer or the seller, and does not participate in any fund custody or dispute mediation. It only provides objective verification based on rules.
Advantages
Reduce trust costs: Replace subjective trust in trading partners with verifiable code rules.
Reduce disputes: Provide clear, signed proof of completion to reduce disputes about whether a task has been completed.
Composability: Verification results can be easily integrated into existing payment systems, smart contracts, or workflow engines.
No custody required: The service does not touch funds, eliminating custody risks and legal complexities.
Instant verification: Provide near-real-time verification results, suitable for automated, high-frequency microtask settlements.
Limitations
Does not enforce payment: It only provides 'proof' and does not guarantee that payment will occur. Payment execution depends on downstream systems.
Rule-dependent: Verification completely depends on pre-defined, computable rules (spec). It cannot verify subjective or vague task requirements.
No dispute resolution: If there is a dispute about the rules (spec) themselves, the service cannot resolve it. This needs to be clearly agreed upon by both parties before the task starts.
Network-dependent: As an online service, its availability depends on the network and server operating status.
How to use
Define the task specification (Spec)
Before starting the task, clearly define and agree on the verification rules. This is usually a JSON object that describes the key features of the expected output (such as hash value, data structure, specific fields, etc.).
Execute the task and obtain the output
Let the AI agent or service execute the task and produce the actual output.
Call the verification interface
Package the task ID, the previously agreed specification (spec), and the actual output (output), and send them to the verification endpoint via an HTTP POST request.
Process the verification result
Parse the returned JSON response. If the 'verdict' is 'PASS' and the signature verification passes, you can safely trigger downstream payments or subsequent operations. Save the receipt as proof.
Usage examples
AI content creation payment settlement
A user hires an AI agent to write a 500-word blog post about 'climate change'. They agree on the topic, word count, and keywords in advance. After the AI completes the writing, it submits its output to the Default Settlement Verifier for verification. After the verification passes, the automatic payment system pays the AI agent according to the returned signed receipt.
Quality gating for data scraping tasks
In a data processing pipeline, the first agent is responsible for scraping data from a specific API and organizing it into JSON format. Only after its output is verified to conform to the pre-defined JSON Schema will the next agent responsible for data analysis start working and receive budget allocation.
Milestone payments for multi-agent collaboration
A complex project is decomposed into multiple subtasks and completed by different AI agents. After each subtask is completed, its deliverables need to be verified by the Default Settlement Verifier. Only after the verification receipt of the previous task is provided will the funds for paying the next agent be released, and the next task will be started.
Frequently Asked Questions
Will the Default Settlement Verifier hold my funds?
What if I'm not satisfied with the verification result?
How to verify that the returned signed receipt is genuine?
Can I use it directly in my AI assistant (such as Claude)?
Is this service free?
Related resources
Official technical specification (SAR v0.1)
Understand the detailed data structure and rules of verification requests and responses.
GitHub code repository
View the open-source code, report issues, or contribute ideas.
Public verification key
Get the public key for verifying receipt signatures.
Project news and discussions (X/Twitter)
Follow the latest updates and community discussions of the project.
Support the project development
Sponsor through GitHub Sponsors to help maintain the stable operation of the service.

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
34.2K
5 points

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
24.4K
4.3 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
71.7K
4.3 points

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
20.4K
4.5 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
31.0K
5 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
64.3K
4.5 points

Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
47.4K
4.8 points

Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
22.0K
4.5 points




