1. Conduid
  2. AI
  3. agentkit-mesh
MCP server · AI

agentkit-mesh

Agent-to-agent discovery and delegation via MCP (Model Context Protocol)

39Low

Scored 24 days ago · breakdown

About agentkit-mesh

agentkit-mesh is an MCP server published by git+agentkitai in the AI category: agent-to-agent discovery and delegation via MCP (Model Context Protocol). It has been installed 0 times through Conduid.

Install

Install
npx agentkit-mesh
Claude Code
claude mcp add agentkit-mesh -- npx -y agentkit-mesh
npx
npx -y agentkit-mesh

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

Ask AI about agentkit-mesh

Powered by Claude · Grounded in docs

I know everything about agentkit-mesh. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ·README presentNot checked yet.
  • ·License declaredNot checked yet.
  • ·Tests presentNot checked yet.
  • ·Dependencies pinnedNot checked yet.
  • ·No dynamic code executionNot checked yet.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

README


Agents register their capabilities, discover each other by semantic search, and delegate tasks — all through standard MCP tools.

Quick Start

npx agentkit-mesh

This starts an MCP server over stdio, ready to connect to Claude Desktop, OpenClaw, or any MCP client.

MCP Configuration

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "agentkit-mesh": {
      "command": "npx",
      "args": ["agentkit-mesh"]
    }
  }
}

OpenClaw

Add to your OpenClaw config:

mcp:
  agentkit-mesh:
    command: npx agentkit-mesh

Architecture

┌─────────────┐     MCP      ┌──────────────────┐
│  AI Agent A  │◄────────────►│                  │
└─────────────┘              │  agentkit-mesh   │
                             │                  │
┌─────────────┐     MCP      │  ┌────────────┐  │
│  AI Agent B  │◄────────────►│  │  Registry   │  │
└─────────────┘              │  │  (SQLite)   │  │
                             │  └────────────┘  │
┌─────────────┐     MCP      │  ┌────────────┐  │
│  AI Agent C  │◄────────────►│  │  Discovery  │  │
└─────────────┘              │  └────────────┘  │
                             │  ┌────────────┐  │
                             │  │ Delegation  │  │
                             │  └────────────┘  │
                             └──────────────────┘

MCP Tools

mesh_register

Register an agent with its capabilities.

Parameter Type Description
name string Unique agent name
description string What this agent does
capabilities string[] List of capabilities
endpoint string Agent's MCP endpoint URL

mesh_discover

Discover agents matching a natural language query.

Parameter Type Description
query string Search query (e.g. "budget management")
limit number? Max results to return

Returns agents ranked by relevance score with matched capability terms.

mesh_unregister

Remove an agent from the registry.

Parameter Type Description
name string Agent name to remove

mesh_delegate

Delegate a task to another agent by name.

Parameter Type Description
targetName string Name of the target agent
task string Task description to delegate
context string? Optional JSON context

Connects to the target agent's MCP endpoint and calls its handle_task tool.

Use Case: FormBridge

An HR agent filling an expense form discovers the Finance agent:

import { AgentRegistry, DiscoveryEngine } from 'agentkit-mesh';

const registry = new AgentRegistry();

// Agents register themselves
registry.register({
  name: 'finance-agent',
  description: 'Budget management and expense approval',
  capabilities: ['budget', 'cost_center', 'expense_approval'],
  endpoint: 'http://localhost:4002/mcp',
});

// HR agent discovers who can help with budget fields
const discovery = new DiscoveryEngine();
const results = discovery.discover('budget cost center', registry);
// → [{ agent: finance-agent, score: 0.67, matchedTerms: ['budget', 'cost', 'center'] }]

See examples/ for a runnable demo.

Optional: Lore Integration

For semantic search beyond keyword matching, connect to a Lore server:

import { LoreDiscoveryEngine } from 'agentkit-mesh';

const engine = new LoreDiscoveryEngine('http://lore:8080', registry, 'api-key');
const results = await engine.discover('financial planning');
// Falls back to text matching if Lore is unavailable

Programmatic API

import { AgentRegistry, DiscoveryEngine, DelegationClient, createServer } from 'agentkit-mesh';

All classes are exported for direct use without the MCP server layer.

🤝 Contributing

Contributions are welcome! Fork the repo, make your changes, and open a pull request. For major changes, open an issue first to discuss what you'd like to change.

🧰 AgentKit Ecosystem

Project Description
AgentLens Observability & audit trail for AI agents
Lore Cross-agent memory and lesson sharing
AgentGate Human-in-the-loop approval gateway
FormBridge Agent-human mixed-mode forms
AgentEval Testing & evaluation framework
agentkit-mesh Agent discovery & delegation ⬅️ you are here
agentkit-cli Unified CLI orchestrator
agentkit-guardrails Reactive policy guardrails

License

ISC © Amit Paz

README mirrored from the source repository 24 days ago. The original is authoritative.

Questions

About agentkit-mesh

How do I install agentkit-mesh?

Run npx agentkit-mesh, then add the server to your MCP client's configuration. Conduid has recorded 0 installs, so the command is known to work with current clients.

Is agentkit-mesh safe to use with an AI agent?

Its trust score is 39 out of 100 (low). It passes 0 of 1 static security checks; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is agentkit-mesh still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.