ANP Bridge MCP Server
Connects MCP-powered AI agents to the decentralized Agent Network Protocol (ANP) for DID-based identity, agent discovery, and secure agent-to-agent communication.
README
ANP Bridge MCP Server
The first MCP bridge for the Agent Network Protocol (ANP) — connect MCP-powered AI agents to the decentralized "Agent Web".
What is ANP?
Agent Network Protocol (ANP) is an emerging open standard for decentralized agent-to-agent communication. It uses DIDs (Decentralized Identifiers) for identity and .well-known/agent.json for discovery — enabling a permissionless, cryptographically secure web of AI agents.
Features
| Tool | Description |
|---|---|
resolve_agent_did |
Resolve any DID (did:web, did:key, did:ethr) via Universal Resolver |
fetch_agent_wellknown |
Fetch an agent's capabilities from .well-known/agent.json |
discover_anp_agents |
Search for ANP-compatible agents in the network |
create_anp_agent_profile |
Generate a compliant ANP Agent Card / Profile |
format_anp_message |
Create ANP-formatted messages for agent-to-agent communication |
validate_anp_message |
Validate ANP messages for spec compliance |
compare_agent_protocols |
Compare agent protocols: ANP, A2A, MCP, ACP, AGNTCY, AGP, UTCP |
Installation
pip install anp-bridge-mcp-server
Usage with Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"anp-bridge": {
"command": "anp-bridge-mcp-server"
}
}
}
Example Usage
# Discover ANP-compatible agents
discover_anp_agents(capability="text-generation")
# Resolve a DID
resolve_agent_did("did:web:example.com")
# Create an agent profile
create_anp_agent_profile(
name="My AI Agent",
description="A helpful AI assistant",
capabilities=["text-generation", "tool-use"],
endpoint="https://my-agent.example.com"
)
# Format a message
format_anp_message(
sender_did="did:web:my-agent.com",
receiver_did="did:web:other-agent.com",
content="Hello, I need help with a task",
message_type="task"
)
# Compare protocols
compare_agent_protocols("ANP", "A2A")
Agent Protocol Landscape (2026)
This server covers 7 competing agent protocols:
- ANP — Decentralized, DID-based (Agent Network Protocol)
- A2A — Google's Agent-to-Agent Protocol
- MCP — Anthropic's Model Context Protocol (now AAIF/Linux Foundation)
- ACP — IBM's Agent Communication Protocol
- AGNTCY — Cisco's enterprise protocol (75+ companies)
- AGP — Cisco's Agent Gateway Protocol (gRPC)
- UTCP — Universal Tool Calling Protocol
Related Servers
- a2a-protocol-mcp-server — Google A2A Protocol Bridge
- agent-server-card-mcp — .well-known Discovery & Server Cards
- agent-identity-mcp-server — OAuth for Agents
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.