Agent Handoff Certified MCP
This server enables signed, verifiable agent-to-agent task handoffs with non-repudiable provenance and chain attestation.
Initiate a handoff with
initiate_handoff: an initiating agent offers a task and receives ahandoff_idplus a signed offer with configurable expiry/context.Accept and sign a handoff with
accept_handoff: the receiving agent signs acceptance to complete the provenance chain.Verify a handoff chain with
verify_chain: re-check signatures and return the trace plus integrity status.List tenant handoffs with
list_handoffs: retrieve handoffs for a tenant, optionally filtered by status and limited.Emit signed chain-integrity attestations with
sign_handoff_chain_attestation: create a signed attestation for a time window (Pro+).Supports MCP stdio use, self-hosting, and EU AI Act-aligned compliance features per the README.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Agent Handoff Certified MCP hand off the customer support ticket to agent-bravo with signed certification"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Agent Handoff Certified MCP
Verifiable agent-to-agent task handoff with signed provenance chain
Verifiable agent-to-agent task handoff with signed provenance chain. Initiating agent signs the offer, accepting agent signs acceptance, chain is verifiable offline. Non-repudiable A2A delegation.
๐ Quick Start
# Install via pip
pip install agent_handoff_certified_mcp
# Or install via Smithery
npx -y @smithery/cli@latest install agent-handoff-certified-mcp --client claudeRelated MCP server: agentpassport
โจ Features
MCP protocol compliant
Easy installation
Well-documented API
Production-ready
Active maintenance
๐ Documentation
๐ก๏ธ Compliance
This MCP server is built with EU AI Act compliance built-in:
Free โ generous daily limit (100-1,000 depending on operation)
โ Article 9 โ Risk Management System
โ Article 13 โ Transparency & Instructions for Use
โ Article 15 โ Bias Detection & Testing
โ Article 26 โ FRIA Support (where applicable)
โ Article 50 โ AI Content Watermarking (where applicable)
Need help getting compliant? Book a free 15-min diagnostic โ
How MEOK charges
MEOK has no subscriptions and no tiers. You pay per job, and only when the agreed artifact has been delivered to you. There is no public price list. See https://meok.ai/pricing.
This repository's source is MIT-licensed and free to self-host.
๐ค Part of the MEOK Ecosystem
This server is part of the MEOK AI Labs ecosystem โ 300+ MCP servers for sovereign AI governance.
Domain | Purpose |
EU AI Act compliance marketplace | |
AI safety & monitoring | |
Sovereign AI platform | |
Legacy modernization |
๐ License
MIT ยฉ CSOAI-ORG
Prompt Injection Firewall โ
uvx agent-prompt-injection-firewall-mcpยท PyPI ยท GitHubData Residency โ
uvx agent-data-residency-mcpยท PyPI ยท GitHubPolicy Enforcement โ
uvx agent-policy-enforcement-mcpยท PyPI ยท GitHubAudit Logger โ
uvx agent-audit-logger-mcpยท PyPI ยท GitHubRate Limiter โ
uvx agent-rate-limiter-mcpยท PyPI ยท GitHub
Full catalogue + Anthropic Registry verify links: https://meok.ai
Protocol coverage + Universal PAYG
This MCP is part of MEOK's 47-MCP fleet that bridges every active agent-interop protocol and 30+ regulatory frameworks. See the full coverage matrix at meok.ai/protocols.
Agent interop protocols supported (8 live):
โ MCP (Anthropic) โ native
โ A2A (Google + Linux Foundation, absorbed IBM ACP Sept 2025)
โ IBM ACP โ covered via A2A merge
โ Stripe ACP (Agentic Commerce Protocol) โ Q3 bridge via agent-commerce-protocol-mcp
โ AP2 (Google Agent Payments) โ partial via agent-commerce-payments-mcp
โ x402 (Coinbase HTTP 402) โ partial via api.meok.ai gateway
โ OASF / AGNTCY (Cisco Outshift + Linux Foundation) โ Q3 bridge
๐ ANP (Cisco Agent Network) โ watch-list
Pricing options:
Option | Price | Best for |
Self-host (this MCP) | ยฃ0 โ MIT | Devs |
Each tier above the free self-host adds HMAC-signed attestations verifiable at
verify.meok.ai. Linux Foundation governance on the A2A spine means EU regulated
buyers can deploy without vendor-lock-in objections.
Configuration
Add to your claude_desktop_config.json (Claude Desktop) or your MCP client config:
{
"mcpServers": {
"agent-handoff-certified-mcp": {
"command": "uvx",
"args": ["agent-handoff-certified-mcp"]
}
}
}Or: pip install agent-handoff-certified-mcp then run the agent-handoff-certified-mcp command (stdio transport).
Examples
Once configured, ask your assistant, for example:
"Use
initiate_handoffto โฆ""Use
accept_handoffto โฆ""Use
verify_chainto โฆ"
Available Tools
5 toolsaccept_handoffCInspect
Receiving agent accepts + signs. Completes the chain.
Inputs: handoff_id (required), accepting_agent_id (required), accepting_agent_ref, api_key. Returns: result
initiate_handoffAInspect
Initiating agent offers a task. Returns handoff_id + signed offer.
The receiving agent must call accept_handoff within expires_in_seconds to
complete the signed chain.
Inputs: tenant_id (required), from_agent (required), to_agent (required), task (required), +3 more. Returns: result
list_handoffsBInspect
List handoffs for a tenant, optionally filtered by status.
Inputs: tenant_id (required), status_filter, limit, api_key. Returns: result
sign_handoff_chain_attestationCInspect
Emit a signed attestation of the handoff chain integrity for a window. Pro+.
Inputs: tenant_id (required), window_start_utc (required), window_end_utc (required), api_key, +1 more. Returns: result
verify_chainCInspect
Re-verify the handoff signatures. Returns full trace + integrity status.
Inputs: handoff_id (required), api_key. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogโฆ
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose: initiate starts a handoff, accept completes it, list retrieves handoffs, sign provides attestation, and verify re-verifies signatures. No overlap.
All tools follow snake_case with a verb_noun pattern (e.g., initiate_handoff, list_handoffs). Even the longer name sign_handoff_chain_attestation is consistent in style.
Five tools cover the core functionality of handoff certification without being excessive or insufficient. Each tool earns its place in the workflow.
The set covers initiation, acceptance, listing, verification, and attestation. A potential gap is a reject or cancel handoff tool, but the core lifecycle is well-represented.
Maintenance
Related MCP Connectors
Bounded authorization and independently verifiable execution evidence for agents.
Shared task queue for humans and AI agents: leases, handoffs, approvals and signed receipts.
Durable agent-to-agent handoffs and shared scratchpad for multi-agent workflows.
Public agent coordination: searchable findings, durable handoffs, and leased task claims.
Related MCP Servers
AlicenseNot gradedqualityDmaintenanceTamper-evident receipts for AI agent actions. The notary layer for agent-to-agent transactions.1MIT- FlicenseNot gradedqualityDmaintenanceCryptographically verifiable, scope-narrowing delegation chains for AI agents, enabling human-anchored authorization across multiple hops.-
- AlicenseAqualityCmaintenanceEnables AI agents to create cryptographically verifiable receipts of their delegated work, with capabilities for multi-party approval and offline verification.1166 npmApache 2.0
- AlicenseBqualityCmaintenanceEnables AI agents to create, validate, verify, and merge tamper-evident task handoff records with SHA-256 receipts, so they can pass work without redoing everything and distinguish verified claims from unconfirmed ones.3MIT