About a2areplayreceipt-mcp
A2A Replay Receipt is a hosted remote MCP service for developer platform teams, release owners, AI engineering leads, and reviewers investigating A2A failures. It replays failures, classifies agent errors, suggests retries, and exports structured receipts and logs as evidence.
Key features
- 01Replay A2A failures
- 02Classify agent errors
- 03Suggest retry plans
- 04Issue structured replay receipts
- 05Export failure logs
Use cases
- 01Reproduce an A2A failure for evaluation
- 02Classify errors during an agent investigation
- 03Review suggested recovery steps
- 04Share structured evidence with release reviewers
MCP support
The remote Streamable HTTP MCP server exposes tools for failure replay, error classification, retry planning, receipt issuance, and failure-log export. Production calls use bearer-token access.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://a2areplayreceipt.clauxel.com/mcpclaude mcp add --transport http com-clauxel-a2areplayreceipt-a2areplayreceipt https://a2areplayreceipt.clauxel.com/mcp{"mcpServers":{"com-clauxel-a2areplayreceipt-a2areplayreceipt":{"type":"http","url":"https://a2areplayreceipt.clauxel.com/mcp"}}}Open in Cursor{"servers":{"com-clauxel-a2areplayreceipt-a2areplayreceipt":{"type":"http","url":"https://a2areplayreceipt.clauxel.com/mcp"}}}Open in VS Code{"mcpServers":{"com-clauxel-a2areplayreceipt-a2areplayreceipt":{"type":"http","url":"https://a2areplayreceipt.clauxel.com/mcp"}}}{"mcpServers":{"com-clauxel-a2areplayreceipt-a2areplayreceipt":{"serverUrl":"https://a2areplayreceipt.clauxel.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://a2areplayreceipt.clauxel.com/mcpAuth requiredTools
Details
From the project READMEA2A Replay Receipt
A2A Replay Receipt is a hosted remote MCP for A2A failure replay MCP.
This repository is a public documentation project for A2A Replay Receipt. Its structure follows the public documentation pattern used by MiroFish: a short front door, a clear reading order, practical guides, reference pages, and a public-safe boundary.
Start Here
- Website: https://a2areplayreceipt.clauxel.com/?utm_source=github&utm_medium=documentation&utm_campaign=a2areplayreceipt_public_docs&utm_content=readme_home
- Pricing: https://a2areplayreceipt.clauxel.com/pricing/?utm_source=github&utm_medium=documentation&utm_campaign=a2areplayreceipt_public_docs&utm_content=readme_pricing
- Checkout: https://a2areplayreceipt.clauxel.com/checkout/?utm_source=github&utm_medium=documentation&utm_campaign=a2areplayreceipt_public_docs&utm_content=readme_checkout
- Support: [email protected]
Remote MCP
- Endpoint: https://a2areplayreceipt.clauxel.com/mcp
- Server card: https://a2areplayreceipt.clauxel.com/server-card.json
- Registry name:
com.clauxel.a2areplayreceipt/a2areplayreceipt-mcp - Tools:
replay_a2a_failure,classify_agent_error,suggest_retry_plan,issue_replay_receipt,export_failure_log
Reading Order
- Quickstart
- Evaluation guide
- Checkout and pricing
- Workflow notes
- Security model
- Public link reference
Audience
developer platform teams, release owners, AI engineering leads, and delivery reviewers.
Capabilities
- Streamable HTTP MCP endpoint
- Bearer-token access for production calls
- Structured tool-call output
- Receipt-oriented evidence export
- Public server card and registry metadata
- MCP tool: replay_a2a_failure
- MCP tool: classify_agent_error
- MCP tool: suggest_retry_plan
- MCP tool: issue_replay_receipt
- MCP tool: export_failure_log
Public-Safe Boundary
This repository contains documentation only. It does not contain production source code, credentials, payment configuration, Cloudflare configuration, customer records, private analytics, or local machine paths.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.