Permite que los agentes de IA descubran y llamen a herramientas y servicios MCP remotos a través de una malla peer-to-peer autenticada.
También conocido como google/agentmesh, agentmesh, @agentmesh-p2p/sdk
- Stars
- 1198
- Herramientas
- —
- Descargas, 30 días
- 798
- Última versión
- 0.2.0
- Último commit
- 13 nov 2026
- Licencia
- Apache-2.0
¿Qué es Agent Mesh MCP?
Agent Mesh es un MCP server. Permite que los agentes de IA descubran y llamen a herramientas y servicios MCP remotos a través de una malla peer-to-peer autenticada.
Resumen generado a partir del README del proyecto
Acerca del MCP server de Agent Mesh
Agent Mesh proporciona un SDK nativo de JavaScript que permite a los agentes de IA unirse a una malla peer-to-peer autenticada. Este sistema permite que los agentes descubran e interactúen con servicios, herramientas y otros agentes remotos sin necesidad de un demonio sidecar local. Está diseñado para desarrolladores que construyen aplicaciones en Node.js o agentes basados en navegador que necesitan comunicarse a través de una red distribuida utilizando un plano de control para la gestión de identidad y políticas.
Los usuarios pueden conectarse a la malla proporcionando una URL del plano de control y una ruta para un token de arranque (bootstrap token) o una ruta para un JWT. El SDK gestiona la identidad y las credenciales dentro de un directorio de estado especificado, lo que permite que las ejecuciones posteriores reanuden las sesiones sin necesidad de volver a registrarse. Para quienes utilizan clientes MCP estándar, el ejecutable proporcionado expone cinco herramientas específicas: get_mesh_info, discover_remote_services, find_remote_tools, describe_remote_tool y call_remote_tool. Esta configuración permite que un cliente encuentre y ejecute funciones remotas cumpliendo con las restricciones y políticas de seguridad de toda la malla.
Qué puedes hacer con él
- 1Descubrir herramientas MCP remotasUn cliente de IA puede buscar en la malla para encontrar herramientas específicas proporcionadas por otros miembros.
- 2Ejecutar funciones de servicios remotosUn desarrollador puede instruir a un agente para que llame a una herramienta específica ubicada en un servicio remoto a través de la malla.
- 3Habilitar la comunicación agente a agenteLos agentes pueden responder a solicitudes de otros pares utilizando el protocolo A2A.
- 4Integración con clientes MCP existentesPuedes usar el ejecutable agentmesh como un MCP server estándar a través de stdio.
Escrito a partir del README del proyecto. Cada caso de uso se verifica con una cita del mismo.
Cómo instalar Agent Mesh MCP
Formatos verificados el 10 nov 2026Instalar Agent Mesh MCP en Claude Code
$ claude mcp add --env AGENTMESH_CONTROL_PLANE_URL=<AGENTMESH_CONTROL_PLANE_URL> --env AGENTMESH_BOOTSTRAP_TOKEN_PATH=<YOUR_AGENTMESH_BOOTSTRAP_TOKEN_PATH> --env AGENTMESH_JWT_PATH=<YOUR_AGENTMESH_JWT_PATH> agentmesh -- npx -y @agentmesh-p2p/sdkInstalar Agent Mesh MCP en Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agentmesh": {
"command": "npx",
"args": [
"-y",
"@agentmesh-p2p/sdk"
],
"env": {
"AGENTMESH_CONTROL_PLANE_URL": "<AGENTMESH_CONTROL_PLANE_URL>",
"AGENTMESH_BOOTSTRAP_TOKEN_PATH": "<YOUR_AGENTMESH_BOOTSTRAP_TOKEN_PATH>",
"AGENTMESH_JWT_PATH": "<YOUR_AGENTMESH_JWT_PATH>"
}
}
}
}Instalar Agent Mesh MCP en VS Code
.vscode/mcp.json
{
"servers": {
"agentmesh": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@agentmesh-p2p/sdk"
],
"env": {
"AGENTMESH_CONTROL_PLANE_URL": "<AGENTMESH_CONTROL_PLANE_URL>",
"AGENTMESH_BOOTSTRAP_TOKEN_PATH": "<YOUR_AGENTMESH_BOOTSTRAP_TOKEN_PATH>",
"AGENTMESH_JWT_PATH": "<YOUR_AGENTMESH_JWT_PATH>"
}
}
}
}Instalar Agent Mesh MCP en Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"agentmesh": {
"command": "npx",
"args": [
"-y",
"@agentmesh-p2p/sdk"
],
"env": {
"AGENTMESH_CONTROL_PLANE_URL": "<AGENTMESH_CONTROL_PLANE_URL>",
"AGENTMESH_BOOTSTRAP_TOKEN_PATH": "<YOUR_AGENTMESH_BOOTSTRAP_TOKEN_PATH>",
"AGENTMESH_JWT_PATH": "<YOUR_AGENTMESH_JWT_PATH>"
}
}
}
}Instalar Agent Mesh MCP en Codex
~/.codex/config.toml
[mcp_servers.agentmesh] command = "npx" args = ["-y", "@agentmesh-p2p/sdk"] [mcp_servers.agentmesh.env] AGENTMESH_CONTROL_PLANE_URL = "<AGENTMESH_CONTROL_PLANE_URL>" AGENTMESH_BOOTSTRAP_TOKEN_PATH = "<YOUR_AGENTMESH_BOOTSTRAP_TOKEN_PATH>" AGENTMESH_JWT_PATH = "<YOUR_AGENTMESH_JWT_PATH>"
Instalar Agent Mesh MCP en Gemini CLI
~/.gemini/settings.json
{
"mcpServers": {
"agentmesh": {
"command": "npx",
"args": [
"-y",
"@agentmesh-p2p/sdk"
],
"env": {
"AGENTMESH_CONTROL_PLANE_URL": "<AGENTMESH_CONTROL_PLANE_URL>",
"AGENTMESH_BOOTSTRAP_TOKEN_PATH": "<YOUR_AGENTMESH_BOOTSTRAP_TOKEN_PATH>",
"AGENTMESH_JWT_PATH": "<YOUR_AGENTMESH_JWT_PATH>"
}
}
}
}Configuración
AGENTMESH_CONTROL_PLANE_URLObligatorioControl plane URL supplied by your mesh operator. HTTPS is required beyond loopback unless explicitly permitted below.
AGENTMESH_BOOTSTRAP_TOKEN_PATHSecretoAbsolute path to a bootstrap token file for first enrollment. Set this OR AGENTMESH_JWT_PATH; leave both empty only when resuming saved credentials.
AGENTMESH_JWT_PATHSecretoAbsolute path to an OIDC/workload token file. Alternative to the bootstrap token; reread during credential refresh.
AGENTMESH_INSECURE_CONTROL_PLANEAllow plaintext HTTP beyond loopback. Development only: exposes enrollment traffic to the network.
AGENTMESH_STATE_DIRAbsolute directory for this client identity. Use a distinct directory per client and mesh. If omitted, uses ~/.config/agentmesh/mcp.
| Nombre | Descripción | Tipo |
|---|---|---|
| AGENTMESH_CONTROL_PLANE_URL | Control plane URL supplied by your mesh operator. HTTPS is required beyond loopback unless explicitly permitted below. | Obligatorio |
| AGENTMESH_BOOTSTRAP_TOKEN_PATH | Absolute path to a bootstrap token file for first enrollment. Set this OR AGENTMESH_JWT_PATH; leave both empty only when resuming saved credentials. | Secreto |
| AGENTMESH_JWT_PATH | Absolute path to an OIDC/workload token file. Alternative to the bootstrap token; reread during credential refresh. | Secreto |
| AGENTMESH_INSECURE_CONTROL_PLANE | Allow plaintext HTTP beyond loopback. Development only: exposes enrollment traffic to the network. | |
| AGENTMESH_STATE_DIR | Absolute directory for this client identity. Use a distinct directory per client and mesh. If omitted, uses ~/.config/agentmesh/mcp. |
Verificaciones automáticas
Ejecutado 12 nov 2026Informe completo →Pasó nuestras verificaciones automáticas. Esto no es una auditoría de seguridad: lee el código y dale al servidor el acceso más limitado que necesite. Cómo funcionan las verificaciones
- Repositorio de origen vinculado y accesibleAprobado
- Licencia de código abierto (OSI)Aprobado
- Commit o lanzamiento en el último añoAprobado
- El nombre del paquete no es similar a un paquete popularAprobado
- El endpoint remoto usa HTTPSNo verificado
- Las herramientas destructivas están etiquetadasNo verificado
- Sin instrucciones ocultas para el modeloAprobado
- Sin avisos críticos en el paquete ni en sus dependenciasAprobado
README
Ver en GitHub@agentmesh-p2p/sdk
Native JavaScript SDK for joining an Agent Mesh from inside the agent
process. It replaces the agentmesh-node sidecar for agents written for Node.js
or running in a browser page:
the agent enrolls with the control plane, joins the mesh through a router,
finds services and calls them, answers A2A requests for the agent itself,
and follows the control plane's keys, bans and policy while it runs. It
publishes no service; a tool or a model others should find by name runs
behind a agentmesh-node.
Guide: google.github.io/agentmesh/docs/guides/native-sdks, from an empty machine to two programs on a mesh. Source: github.com/google/agentmesh/tree/main/sdk/js.
Install
npm install @agentmesh-p2p/sdk @modelcontextprotocol/sdk zod
Requires Node.js 22.18 or later. In a browser, bundle it with the page
(the package's browser field selects the browser files); the guide's
In a browser
section has the details and an example page.
MCP client over stdio
The package's agentmesh executable joins as its own mesh member and exposes
five MCP tools: get_mesh_info, discover_remote_services, find_remote_tools,
describe_remote_tool and call_remote_tool. A stdio-capable MCP client starts
and stops the process; no node daemon is needed for this caller. Providers still
publish their services through agentmesh-node.
To try the executable from a source checkout:
cd sdk/js
npm ci
npm run build
Use absolute paths in your MCP client's configuration:
{
"mcpServers": {
"agentmesh": {
"command": "node",
"args": ["/absolute/path/to/agentmesh/sdk/js/dist/cli.js"],
"env": {
"AGENTMESH_CONTROL_PLANE_URL": "https://your-control-plane.example",
"AGENTMESH_BOOTSTRAP_TOKEN_PATH": "/absolute/path/to/join-token",
"AGENTMESH_STATE_DIR": "/absolute/path/to/this-client-identity"
}
}
}
}
Get the control plane URL and token file from your mesh operator or
agentmesh-one.
Alternatively, set AGENTMESH_JWT_PATH to a workload/OIDC token file; do not set
both token paths. Credentials are read from files, never command-line values.
The first run enrolls and saves its identity; later runs resume from the state
directory without the bootstrap token. JWT enrollment rereads the token file
when refreshing. Use a distinct state directory for each client identity and
mesh; do not run multiple processes against the same directory. The default is
~/.config/agentmesh/mcp. Plain HTTP is allowed on loopback only unless
AGENTMESH_INSECURE_CONTROL_PLANE=true explicitly permits it elsewhere.
Stdout contains only MCP messages; diagnostics go to stderr. Closing stdin or
sending SIGINT/SIGTERM shuts down the mesh session. Tool calls use the member's
existing authenticated streams and policy, including provider label checks.
Remote tool results retain text, non-text content, structured output and errors.
Discovery follows tool pagination, rejects looping catalogs and bounds each
search to 64 providers, 256 services per provider, 256 tools per service and
1024 results. Requests have a 10-second deadline; narrow a large search by peer
or service. intent is accepted but ignored, matching the node's current tool.
This member publishes no services, so it has no list_local_services tool.
Inference and A2A discovery return metadata, but this executable provides no
HTTP proxy, /v1 endpoint, local socket or local_proxy_url. Use an SDK client
or an agentmesh-node HTTP proxy to invoke those protocols.
Use
Both programs below are in
examples/ and
run against a real mesh in the repository's tests. They read the mesh from
AGENTMESH_CONTROL_PLANE_URL and the enrollment token from
AGENTMESH_BOOTSTRAP_TOKEN_PATH; the guide shows how to get both from agentmesh-one
or from the operator of an existing mesh.
Find a service and call it:
// Calls something on the mesh: a tool of an MCP service or a path of an
// inference or A2A service someone published, found by name, or an agent that
// published nothing, reached by its peer ID.
//
// node call.js mcp://everything echo '{"message": "hi"}'
// node call.js inference://ollama /v1/models
// node call.js 12D3KooW... a2a://agent /card
//
// AGENTMESH_CONTROL_PLANE_URL names the mesh. The first run enrolls with the file
// AGENTMESH_BOOTSTRAP_TOKEN_PATH (a token the mesh operator gave you) or
// AGENTMESH_JWT_PATH (a workload identity token your platform issues, such as a
// Kubernetes projected service account token), and keeps the identity and
// credential in AGENTMESH_STATE_DIR; later runs resume from there without it.
import { homedir } from "node:os";
import { AgentMesh, type DiscoveredProvider } from "@agentmesh-p2p/sdk";
let argv = process.argv.slice(2);
// A first argument that is not a service target is the peer ID of an agent.
let peerId: string | undefined;
if (argv[0] !== undefined && !argv[0].includes("://")) {
[peerId, ...argv] = argv as [string, ...string[]];
}
const [service = peerId !== undefined ? "a2a://agent" : "mcp://everything", toolOrPath = peerId !== undefined ? "/card" : "echo", args = '{"message": "hi"}'] = argv;
const mesh = await AgentMesh.enroll({
controlPlaneUrl: process.env.AGENTMESH_CONTROL_PLANE_URL ?? "https://mesh.example.com",
bootstrapTokenPath: process.env.AGENTMESH_BOOTSTRAP_TOKEN_PATH,
jwtPath: process.env.AGENTMESH_JWT_PATH,
stateDir: process.env.AGENTMESH_STATE_DIR ?? `${homedir()}/.config/agentmesh/caller`,
// A plaintext http:// control plane is otherwise accepted only on loopback.
allowInsecure: process.env.AGENTMESH_INSECURE_CONTROL_PLANE === "true",
});
const session = await mesh.join();
console.log(`on the mesh as ${session.peerId}`);
// The peer to call: an agent named by ID, or a provider of a published service.
let provider: DiscoveredProvider = { peerId: peerId ?? "", addrs: [] };
if (peerId !== undefined) {
// An agent is not in the discovery table; the SDK finds the path to its
// peer ID through the routers.
await session.connect(peerId);
} else {
const providers = await session.discover(service);
if (providers.length === 0) {
throw new Error(`no member of the mesh serves ${service}`);
}
// A provider record can outlive its member; the first that answers is used.
let reached = false;
for (const candidate of providers) {
try {
await session.connect(candidate);
provider = candidate;
reached = true;
break;
} catch (err) {
console.error(`${candidate.peerId}: ${(err as Error).message}`);
}
}
if (!reached) {
throw new Error(`no provider of ${service} is reachable`);
}
}
console.log(`${service} is served by ${provider.peerId}`);
if (service.startsWith("mcp://")) {
const tools = await session.listTools(provider, service);
console.log(`tools: ${tools.map((t) => t.name).join(", ")}`);
const result = await session.callTool(provider, service, toolOrPath, JSON.parse(args));
console.log(result.text.join("\n"));
} else {
const response = await session.request(provider, service, toolOrPath);
console.log(response.status, response.text());
}
await session.close();
Be an agent others can call. Nothing is published; a caller reaches the agent by its peer ID, the one it prints, through a router:
// An agent on the mesh: joins, then answers A2A requests from other members
// until stopped. It publishes nothing. There is no service name to look up; a
// caller reaches the agent by its peer ID, through a router, as a2a://agent.
// The mesh policy decides which members may call; the SDK turns the others
// away before anything reaches this code.
//
// node agent.js # answered by the handler below
// node agent.js http://127.0.0.1:9999 # forwarded to an A2A server beside it
//
// AGENTMESH_CONTROL_PLANE_URL names the mesh. The first run enrolls with the file
// AGENTMESH_BOOTSTRAP_TOKEN_PATH (a token the mesh operator gave you) or
// AGENTMESH_JWT_PATH (a workload identity token your platform issues, such as a
// Kubernetes projected service account token), and keeps the identity and
// credential in AGENTMESH_STATE_DIR; later runs resume from there, as the same
// peer, without it.
import { homedir } from "node:os";
import { AgentMesh } from "@agentmesh-p2p/sdk";
const [backendURL] = process.argv.slice(2);
const mesh = await AgentMesh.enroll({
controlPlaneUrl: process.env.AGENTMESH_CONTROL_PLANE_URL ?? "https://mesh.example.com",
bootstrapTokenPath: process.env.AGENTMESH_BOOTSTRAP_TOKEN_PATH,
jwtPath: process.env.AGENTMESH_JWT_PATH,
stateDir: process.env.AGENTMESH_STATE_DIR ?? `${homedir()}/.config/agentmesh/agent`,
// A plaintext http:// control plane is otherwise accepted only on loopback.
allowInsecure: process.env.AGENTMESH_INSECURE_CONTROL_PLANE === "true",
});
const session = await mesh.join();
// Answers every path with who was asked and who asked; a real agent runs an
// A2A server here, or beside this process at backendURL.
const target = await session.acceptA2A(
backendURL !== undefined
? { url: backendURL }
: { handler: (request, caller) => Response.json({ name: "agent", path: new URL(request.url).pathname, caller: caller.peerId }) },
);
console.log(`accepting ${target} as ${session.peerId}`);
const stop = () => void session.close().then(() => process.exit(0));
process.on("SIGINT", stop);
process.on("SIGTERM", stop);
enroll reuses the identity and credential saved in stateDir when they
are still valid for that control plane, and needs exactly one of
bootstrapTokenPath, bootstrapToken, jwtPath or jwt (a token string or
a () => string | Promise<string> callback invoked at enrollment and on every
refresh) otherwise. Read tokens from a file, a callback or the environment; do
not put them on a command line. labels are attested at enrollment;
join({ egressRequireLabels }) is the floor every peer the session calls must
attest, all of it, held for the session.
A plaintext http:// control plane is accepted only on loopback. Pass
allowInsecure: true for a network you trust.
License
Apache-2.0. Issues and contributions at github.com/google/agentmesh.
Preguntas sobre Agent Mesh MCP
¿Cómo agrego Agent Mesh MCP a Claude Code?
Ejecuta claude mcp add --env AGENTMESH_CONTROL_PLANE_URL=<AGENTMESH_CONTROL_PLANE_URL> --env AGENTMESH_BOOTSTRAP_TOKEN_PATH=<YOUR_AGENTMESH_BOOTSTRAP_TOKEN_PATH> --env AGENTMESH_JWT_PATH=<YOUR_AGENTMESH_JWT_PATH> agentmesh -- npx -y @agentmesh-p2p/sdk en tu terminal. Añade --scope user para que esté disponible en todos los proyectos.
¿Cómo agrego Agent Mesh MCP a Cursor?
Abre ~/.cursor/mcp.json y añade el servidor en mcpServers, usando la configuración de Cursor que se muestra en la sección de instalación de arriba.
¿Cómo puedo usar Agent Mesh con un cliente MCP?
Puedes usar el ejecutable agentmesh, que se une como miembro de la malla y expone cinco herramientas MCP: get_mesh_info, discover_remote_services, find_remote_tools, describe_remote_tool y call_remote_tool.
¿El ejecutable de Agent Mesh publica algún servicio local?
No, el ejecutable no publica ningún servicio; está diseñado para descubrir y llamar a herramientas remotas. Para publicar servicios, debes usar agentmesh-node.
¿Puedo usar un plano de control HTTP simple?
El uso de HTTP simple solo está permitido en la dirección de loopback, a menos que lo habilites explícitamente mediante la variable de entorno AGENTMESH_INSECURE_CONTROL_PLANE=true.