Skip to main content
Glama
Agent Handoff Certified MCP

Agent Handoff Certified MCP

MCP Scorecard: 90/100

Agent Handoff Certified MCP

MEOK AI Labs License PyPI

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.


๐Ÿš€ 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 claude

Related MCP server: agentpassport

โœจ Features

  • MCP protocol compliant

  • Easy installation

  • Well-documented API

  • Production-ready

  • Active maintenance

๐Ÿ“– Documentation

๐Ÿ›ก๏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)

  • โœ… Article 9 โ€” Risk Management System

  • โœ… Article 13 โ€” Transparency & Instructions for Use

  • โœ… Article 15 โ€” Bias Detection & Testing

  • โœ… Article 26 โ€” FRIA Support (where applicable)

  • โœ… 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.

๐Ÿค 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

councilof.ai

EU AI Act compliance marketplace

safetyof.ai

AI safety & monitoring

meok.ai

Sovereign AI platform

cobolbridge.ai

Legacy modernization

๐Ÿ“œ License

MIT ยฉ CSOAI-ORG


  • Prompt Injection Firewall โ†’ uvx agent-prompt-injection-firewall-mcp ยท PyPI ยท GitHub

  • Data Residency โ†’ uvx agent-data-residency-mcp ยท PyPI ยท GitHub

  • Policy Enforcement โ†’ uvx agent-policy-enforcement-mcp ยท PyPI ยท GitHub

  • Audit Logger โ†’ uvx agent-audit-logger-mcp ยท PyPI ยท GitHub

  • Rate Limiter โ†’ uvx agent-rate-limiter-mcp ยท 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):

  • โœ… MCP (Anthropic) โ€” native

  • โœ… A2A (Google + Linux Foundation, absorbed IBM ACP Sept 2025)

  • โœ… 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

  • ๐Ÿ‘ 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_handoff to โ€ฆ"

  • "Use accept_handoff to โ€ฆ"

  • "Use verify_chain to โ€ฆ"

Available Tools

5 tools
accept_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 changelogโ€ฆ

    TDQS

    B3.4/5.0

    Scored across 5 tools

    Disambiguation5/5

    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.

    Naming Consistency5/5

    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.

    Tool Count5/5

    Five tools cover the core functionality of handoff certification without being excessive or insufficient. Each tool earns its place in the workflow.

    Completeness4/5

    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

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers