Permet aux agents IA de découvrir et d'appeler des outils et services MCP distants via un maillage peer-to-peer authentifié.
Aussi connu sous google/agentmesh, agentmesh, @agentmesh-p2p/sdk
- Étoiles
- 1 198
- Outils
- —
- Téléchargements, 30 jours
- 798
- Dernière version
- 0.2.0
- Dernier commit
- 13 nov. 2026
- Licence
- Apache-2.0
Qu'est-ce que Agent Mesh MCP ?
Agent Mesh est un serveur MCP. Permet aux agents IA de découvrir et d'appeler des outils et services MCP distants via un maillage peer-to-peer authentifié.
Résumé généré à partir du README du projet
À propos du MCP server Agent Mesh
Agent Mesh fournit un SDK JavaScript natif qui permet aux agents IA de rejoindre un maillage peer-to-peer authentifié. Ce système permet aux agents de découvrir et d'interagir avec des services, des outils et d'autres agents distants sans nécessiter de démon sidecar local. Il est conçu pour les développeurs qui construisent des applications Node.js ou des agents basés sur navigateur devant communiquer à travers un réseau distribué en utilisant un plan de contrôle pour la gestion de l'identité et des politiques.
Les utilisateurs peuvent se connecter au maillage en fournissant une URL de plan de contrôle ainsi qu'un chemin vers un jeton de bootstrap ou un chemin vers un JWT. Le SDK gère l'identité et les identifiants au sein d'un répertoire d'état spécifié, permettant aux exécutions suivantes de reprendre les sessions sans ré-enrôlement. Pour ceux qui utilisent des clients MCP standards, l'exécutable fourni expose cinq outils spécifiques : get_mesh_info, discover_remote_services, find_remote_tools, describe_remote_tool, et call_remote_tool. Cette configuration permet à un client de trouver et d'exécuter des fonctions distantes tout en respectant les interdictions et les politiques de sécurité du maillage.
Ce que vous pouvez faire avec
- 1Découvrir des outils MCP distantsUn client IA peut parcourir le maillage pour trouver des outils spécifiques fournis par d'autres membres.
- 2Exécuter des fonctions de services distantsUn développeur peut ordonner à un agent d'appeler un outil spécifique situé sur un service distant via le maillage.
- 3Activer la communication agent-à-agentLes agents peuvent répondre aux requêtes d'autres pairs en utilisant le protocole A2A.
- 4S'intégrer aux clients MCP existantsVous pouvez utiliser l'exécutable agentmesh comme un MCP server standard via stdio.
Extrait du README du projet. Chaque cas d'utilisation est vérifié par rapport à une citation du document.
Comment installer Agent Mesh MCP
Formats vérifiés le 10 nov. 2026Ajouter à CursorAjouter à GooseInstaller Agent Mesh MCP dans 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/sdkInstaller Agent Mesh MCP dans 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>"
}
}
}
}Installer Agent Mesh MCP dans 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>"
}
}
}
}Installer Agent Mesh MCP dans VS Code CLI
$ code --add-mcp '{"name":"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>"}}'Installer Agent Mesh MCP dans 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>"
}
}
}
}Installer Agent Mesh MCP dans Codex
$ codex mcp add agentmesh --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>' -- npx -y @agentmesh-p2p/sdkInstaller Agent Mesh MCP dans Codex config.toml
~/.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>"
Installer Agent Mesh MCP dans Gemini CLI
$ gemini mcp add -s user -e 'AGENTMESH_CONTROL_PLANE_URL=<AGENTMESH_CONTROL_PLANE_URL>' -e 'AGENTMESH_BOOTSTRAP_TOKEN_PATH=<YOUR_AGENTMESH_BOOTSTRAP_TOKEN_PATH>' -e 'AGENTMESH_JWT_PATH=<YOUR_AGENTMESH_JWT_PATH>' agentmesh npx -- -y @agentmesh-p2p/sdkInstaller Agent Mesh MCP dans Gemini settings.json
~/.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>"
}
}
}
}Configuration
AGENTMESH_CONTROL_PLANE_URLRequisControl plane URL supplied by your mesh operator. HTTPS is required beyond loopback unless explicitly permitted below.
AGENTMESH_BOOTSTRAP_TOKEN_PATHSecretAbsolute 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_PATHSecretAbsolute 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.
| Nom | Description | Type |
|---|---|---|
| AGENTMESH_CONTROL_PLANE_URL | Control plane URL supplied by your mesh operator. HTTPS is required beyond loopback unless explicitly permitted below. | Requis |
| 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. | Secret |
| AGENTMESH_JWT_PATH | Absolute path to an OIDC/workload token file. Alternative to the bootstrap token; reread during credential refresh. | Secret |
| 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. |
Vérifications automatisées
Exécuté le 12 nov. 2026Rapport complet →A passé nos vérifications automatisées. Il ne s'agit pas d'un audit de sécurité : lisez le code et donnez au serveur l'accès le plus restreint dont il a besoin. Fonctionnement des vérifications
- Dépôt source lié et accessibleRéussi
- Licence open source (OSI)Réussi
- Commit ou version publiée au cours de l'année écouléeRéussi
- Nom du package non proche d'un package populaireRéussi
- L'endpoint distant utilise HTTPSNon vérifié
- Les outils destructifs sont étiquetésNon vérifié
- Aucune instruction cachée destinée au modèleRéussi
- Aucun avis critique dans le package ou ses dépendancesRéussi
README
Voir sur 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.
Questions sur Agent Mesh MCP
Comment ajouter Agent Mesh MCP à Claude Code ?
Exécutez 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 dans votre terminal. Ajoutez --scope user pour le rendre disponible dans tous les projets.
Comment ajouter Agent Mesh MCP à Cursor ?
Ouvrez ~/.cursor/mcp.json et ajoutez le serveur sous mcpServers, avec la configuration Cursor indiquée dans la section d'installation ci-dessus.
Comment puis-je utiliser Agent Mesh avec un client MCP ?
Vous pouvez utiliser l'exécutable agentmesh qui rejoint le maillage en tant que membre et expose cinq outils MCP : get_mesh_info, discover_remote_services, find_remote_tools, describe_remote_tool, et call_remote_tool.
L'exécutable Agent Mesh publie-t-il des services locaux ?
Non, l'exécutable ne publie aucun service ; il est conçu pour découvrir et appeler des outils distants. Pour publier des services, vous devez utiliser agentmesh-node.
Puis-je utiliser un plan de contrôle HTTP classique ?
Le HTTP classique n'est autorisé que sur l'adresse loopback, à moins que vous ne l'activiez explicitement en utilisant la variable d'environnement AGENTMESH_INSECURE_CONTROL_PLANE=true.