A2areplayreceipt Mcp
- Updated May 20, 2026
- clauxel/a2a-replay-receipt-mcp
A2A Replay Receipt MCP is a MCP server that records agent-to-agent failure replays as structured receipts, audit logs, and reviewer-ready evidence.
About
A2A Replay Receipt MCP is a hosted Model Context Protocol server for developers and small teams running Claude Code, Cursor, or similar agents in agent-to-agent pipelines. When an A2A step fails, ad-hoc chat logs rarely prove what was sent, what failed, or how to reproduce the issue. This server focuses on failure replay, structured receipts, and audit trails that read like evidence a reviewer can trust—not a one-off stack trace. Connect via streamable HTTP with a Bearer token, point your MCP-capable client at the remote endpoint, and use it during review and incident triage. It complements agent skills rather than replacing them: you still fix the bug in code, but the MCP gives you a durable paper trail for regressions, customer support, or internal QA. Best when multi-agent orchestration is already in production or staging and you need parity between what the agent saw and what you archive.
- Remote streamable-HTTP MCP at a2areplayreceipt.clauxel.com with Bearer auth from the product site
- Structured receipts and audit logs tuned for A2A failure replay workflows
- Reviewer-ready evidence export for agent handoff debugging
- Publisher tags: a2a, replay, receipt, failure, remote-mcp
- Open-source implementation on GitHub (clauxel/a2a-replay-receipt-mcp), registry version 1.0.0
A2areplayreceipt Mcp by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add --transport http a2areplayreceipt-mcp https://a2areplayreceipt.clauxel.com/mcp --header "Authorization: Bearer YOUR_TOKEN"Add your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Transport | HTTP |
|---|---|
| Auth | Required |
| Last updated | May 20, 2026 |
| Repository | clauxel/a2a-replay-receipt-mcp ↗ |
What it does
Capture structured replay receipts and audit evidence when agent-to-agent (A2A) workflows fail so you can debug and show reviewers what happened.
Who is it for?
Best when you're shipping multi-agent automations and need reproducible failure evidence before launch or during production incidents.
Skip if: Single-shot coding sessions with no A2A hops, or teams that only need local unit tests without audit trails.
What you get
After registration you get consistent failure replay artifacts and audit-friendly receipts your agent can attach to debugging and review workflows.
- Structured failure replay receipts for A2A runs
- Audit logs suitable for reviewer or compliance review
- Consistent evidence artifacts linked from agent tooling
By the numbers
- Registry version 1.0.0
- Single remote endpoint: streamable-http at a2areplayreceipt.clauxel.com/mcp
- Authorization via Bearer token header
README.md
A2A 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: support@aigeamy.com
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.
Recommended MCP Servers
0piFree, 2hr expiry agent storage to cache contexts, bridge workflows, or dump data.
100Hires AI ATS & Recruitment SoftwareOfficial 100Hires MCP: AI ATS & Recruitment Software for candidates, jobs, applications, interviews.
123elec McpInterface MCP officielle du site marchand 123elec, catalogue, stock, panier, commandes.
1stayHotel booking MCP server.2
2D Assets MCPMCP server for generating advanced mock 2D PNG assets for game prototypes.43D MeshWeaverMesh spatial optimizer reducing geometric overhead in 3D assets.How it compares
MCP evidence and replay server, not a general debugging skill or test runner.
FAQ
Who is A2A Replay Receipt MCP for?
It is for developers operating agent-to-agent workflows who need structured receipts and audit logs when handoffs fail.
When should I use A2A Replay Receipt MCP?
Use it when validating multi-agent flows before release, during code review of agent integrations, or when triaging production A2A errors.
How do I add A2A Replay Receipt MCP to my agent?
Register the remote MCP URL https://a2areplayreceipt.clauxel.com/mcp in your client, set Authorization to a Bearer token from the Clauxel product website, and use streamable-http transport per the server card.