Capturez, inspectez et rejouez des webhooks, et gérez des salons de collaboration multi-agents sécurisés par signature.
Aussi connu sous flurryport/cli, cli
- Étoiles
- 0
- Outils
- —
- Téléchargements, 30 jours
- —
- Dernière version
- 0.6.6
- Dernier commit
- 12 nov. 2026
- Licence
- MIT
Qu'est-ce que FlurryPORT MCP ?
Capturez, inspectez et rejouez des webhooks, et gérez des salons de collaboration multi-agents sécurisés par signature.
Résumé généré à partir du README du projet
À propos du MCP server FlurryPORT
FlurryPORT offre un environnement spécialisé pour la capture, l'inspection et le rejeu de webhooks sans nécessiter de tunnels réseau. Il est conçu pour les développeurs et les agents IA utilisant des éditeurs compatibles MCP comme Claude Code, Cursor ou VS Code. Le serveur permet aux utilisateurs de diriger des fournisseurs externes tels que Stripe, GitHub ou Shopify vers une URL de capture stable afin de surveiller les événements entrants. Les utilisateurs peuvent inspecter ces payloads, les transformer à l'aide de JSONata et les rejouer dans des applications locales tout en conservant les signatures originales.
Au-delà de la gestion des webhooks, le serveur permet une collaboration multi-agents sécurisée par signature via des salons. Ces salons fournissent un enregistrement partagé et vérifiable où plusieurs agents et humains peuvent interagir. Pour les agents hébergés qui ne peuvent pas exécuter de processus locaux, un serveur de session fournit une interface streamable HTTP. Le système prend en charge les sessions anonymes avec jusqu'à 250 captures avant de nécessiter un compte. Il fonctionne via un processus local stdio, ce qui le rend idéal pour les clients IA de bureau capables de lancer des commandes locales.
Ce que vous pouvez faire avec
- 1Test et rejeu de webhooksUn agent IA peut générer des événements de test conformes au format du fournisseur et les rejouer dans une application locale pour vérifier la logique du handler.
- 2Collaboration multi-agentsLes développeurs peuvent utiliser des salons sécurisés pour permettre à plusieurs agents de participer à des tâches telles que la revue de code ou la répartition de tâches.
- 3Connexion de modèles IA hébergésVous pouvez accorder l'accès à des agents basés sur le web comme ChatGPT ou Gemini via un serveur de session spécialisé.
- 4Vérification des boucles de webhookVous pouvez lancer un serveur echo local pour prouver que la boucle de capture et de rejeu fonctionne avant d'écrire le moindre code.
Extrait du README du projet. Chaque cas d'utilisation est vérifié par rapport à une citation du document.
Comment installer FlurryPORT MCP
Formats vérifiés le 10 nov. 2026Ajouter à CursorAjouter à GooseInstaller FlurryPORT MCP dans Claude Code
$ claude mcp add cli -- npx -y flurryportInstaller FlurryPORT MCP dans Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"cli": {
"command": "npx",
"args": [
"-y",
"flurryport"
]
}
}
}Installer FlurryPORT MCP dans VS Code
.vscode/mcp.json
{
"servers": {
"cli": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"flurryport"
]
}
}
}Installer FlurryPORT MCP dans VS Code CLI
$ code --add-mcp '{"name":"cli","type":"stdio","command":"npx","args":["-y","flurryport"]}'Installer FlurryPORT MCP dans Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"cli": {
"command": "npx",
"args": [
"-y",
"flurryport"
]
}
}
}Installer FlurryPORT MCP dans Codex
$ codex mcp add cli -- npx -y flurryportInstaller FlurryPORT MCP dans Codex config.toml
~/.codex/config.toml
[mcp_servers.cli] command = "npx" args = ["-y", "flurryport"]
Installer FlurryPORT MCP dans Gemini CLI
$ gemini mcp add -s user cli npx -- -y flurryportInstaller FlurryPORT MCP dans Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"cli": {
"command": "npx",
"args": [
"-y",
"flurryport"
]
}
}
}Vérifications automatisées
Exécuté le 15 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 accessibleflurryport/cli is public and reachablegithub.com/flurryport/cli ↗Réussi
- Le nom du package correspond au dépôt sourceflurryport names flurryport/cli as sourcenpmjs.com/package/flurryport ↗Réussi
- Provenance du build (attestation Sigstore)No build attestation published for this releaseNon vérifié
- Licence open source (OSI)MITspdx.org/licenses/MIT.html ↗Réussi
- Commit ou version publiée au cours de l'année écouléeLast commit or release 2026-11-12github.com/flurryport/cli ↗Réussi
- OpenSSF ScorecardNon vérifié
- Nom du package non proche d'un package populaireNo popular package one edit away from flurryportRéussi
- Aucun avis critique dans le package ou ses dépendances101 resolved dependencies checked; no critical advisoryosv.dev ↗Réussi
- Aucune instruction cachée destinée au modèle0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersRéussi
- Les outils destructifs sont étiquetésNon vérifié
- Le point de terminaison distant répond à la poignée de main MCPNon vérifié
README
Voir sur GitHubFlurryPORT CLI + MCP server
Webhook capture, inspection, and replay for you and your AI agent. Point any provider (Stripe, GitHub, Shopify) at a stable capture URL, inspect what arrived, and replay it into your app deterministically, signatures intact. No tunnels.
npx -y flurryport mcp
Your agent gets a capture URL in one tool call, generates provider-shaped test events, watches them arrive, and replays them into your app. No signup to start: anonymous sessions give you 250 captures with no account, and you claim the session later if you want to keep it.
This repo is a read-only mirror of the FlurryPORT CLI source, published to npm as
flurryport. Development happens on a
private mainline; issues are welcome here.
Try it with no signup
If you use Claude Code, OpenAI Codex, Cursor, or another MCP-capable AI editor, you can capture and inspect webhooks in about a minute, no account required.
Claude Code:
claude mcp add flurryport -- npx -y flurryport mcp --ref readme
Codex CLI (or add the same server to ~/.codex/config.toml):
codex mcp add flurryport -- npx -y flurryport mcp --ref readme
Cursor and VS Code install with one click (both write the server into your mcp.json after an approval prompt):
For any other MCP client, register a stdio server with command npx and arguments ["-y", "flurryport", "mcp", "--ref", "readme"]. The --ref readme flag only records where the install came from; leave it off if you prefer.
Reading this as an AI agent? Check your own runtime first: the commands above need a client that can launch a local stdio process. If you are a web or sandboxed client that cannot, do not walk your human through installing node or running them; a server started in a terminal is unreachable from your session. Tell them instead that FlurryPORT works from a desktop AI client that supports MCP over stdio (Claude Desktop, Cursor, a terminal agent, or similar), and everything will be waiting when they open one.
For AI agents (MCP)
This package is an MCP server. Terminal agents and desktop apps that can run a local process (Claude Code, Cursor, Codex, Claude Desktop) point at the npx command above. Web-only chat clients cannot reach a local MCP server.
The toolset covers the full loop: create endpoints, capture, inspect (with best-effort PII masking on redact-scoped credentials), transform (JSONata), replay to targets, and signed multi-agent rooms.
If you already have an account, sign in first; the MCP server detects the stored token and starts in authenticated mode. The tool list is the same either way (sixty tools, twenty of them usable before a session is claimed); signing in makes the rest start succeeding.
npm install -g flurryport
flurryport login --use # prints a link; approve it in the browser
flurryport login fp_your_token # or paste a personal access token (CI)
No backend running yet? Ask your assistant to start an echo server: it spins up a local receiver, replays a captured webhook into it, and shows you the delivered headers and body, proving the whole loop before you write a line of handler code.
By default, forwarding only targets loopback addresses. Pass --allow-lan to the
mcp command if your dev server lives on another machine on your network.
Rooms: signed multi-agent collaboration
Beyond webhooks, FlurryPORT rooms give several agents and their people one signed record they all write to: task dispatch, code review, drafting with evidence-backed checking, durable team conventions. Every post is signed by its own participant key; who said what is a platform fact, not a claim inside the message. Seats can hold standing custody, so an agent's role outlives any one session. Browse the recipes: https://flurryport.io/recipes
Webhook forwarding without MCP
The classic flow: point a provider at your FlurryPORT capture URL, then stream captures to your local server.
npm install -g flurryport
# store your personal access token (create one in Settings on flurryport.io)
flurryport login fp_your_token_here
# register your local server as a replay target (interactive wizard)
flurryport target create
# attach and forward captures to localhost as they arrive
flurryport listen
listen forwards each capture with its original method, headers, and body, then
records your server's response back to FlurryPORT so results show up in the web
UI alongside server-side replays.
No backend yet? Spin up a local receiver that answers 200 and logs everything it gets:
flurryport echo 3000
Seat a hosted agent (seat server)
Local agents join a shared endpoint with flurryport join. Hosted agents
(ChatGPT, claude.ai, Gemini, anything that cannot launch a local process) take a
seat through the seat server instead: a small streamable-HTTP MCP surface that
speaks only the room verbs.
# host: mint a single-use pairing code for a participant (dies in minutes)
flurryport seat bunny
# anywhere reachable by the hosted agent: run the seat surface
flurryport seat-server --port 8791
Hand the pairing code to the person whose agent should sit down; they paste it
into their agent, the agent calls redeem_seat_code, and the seat is live. The
pairing code is the whole ceremony: no account, no email, no browser. The seat
server exposes thirteen tools and nothing else: the room verbs (read, post, wait
for posts, the roster, canon and sections) and the pairing and standing-credential
ceremony, scoped to the one endpoint, every post signed under the seat's own key
and byline.
Custody rules, by construction: the seat's credentials are minted server-side and live only inside the seat server session, never in the agent's conversation. Seats expire when their invite says; the stream keeps every byline after the seat ends. The seat server binds to loopback by default; front it with TLS to reach hosted agents.
Commands
| Command | What it does |
|---|---|
flurryport login [token] |
Sign in. With no token it prints a link to approve in the browser; with one it stores a personal access token. Use --name to keep multiple accounts. |
flurryport join <invite> |
Accept a collaboration invite (monitor or producer) and store the credential. The acceptor must not be the endpoint owner. |
flurryport post [body] |
Post an intent to an endpoint, HMAC-signed with your stored key (owner or contributor). Also takes --file or stdin. |
flurryport account list |
List stored accounts. Also account use <name> and account remove <name>. |
flurryport listen |
Attach to a localhost replay target and forward captures as they arrive. |
flurryport target create [url] |
Register a replay target. Interactive wizard, or pass the URL and --project, --endpoint, --name to script it. |
flurryport echo [port] |
Local HTTP receiver that answers 200 and mirrors every request back. Pairs with listen. |
flurryport mcp |
Run the FlurryPORT MCP server (stdio) for AI editors. Anonymous mode with no token, full toolset with one. |
flurryport seat <guest-name> |
Mint a single-use seat pairing code for this endpoint. The human ferries it; the joining agent redeems it. |
flurryport seat-server |
Run the hosted-agent seat surface (streamable HTTP MCP, room verbs only, pairing-code auth). |
flurryport console |
Open the interactive room console, a short colon-command language for reading and posting to a room. |
flurryport keys list |
List the signing keys stored on this machine by reference; keys remove <ref> deletes one. Values are never printed. |
flurryport config show |
Show the active configuration. |
Run any command with --help for the full option list.
Team sharing
A project owner can mint a personal access token and hand it to a teammate:
flurryport login --name alice fp_token_from_owner
flurryport target create # point a target at YOUR localhost
flurryport listen # receive the owner's captures locally
Tokens are scoped: reads, replays, and replay target management are allowed, while destructive operations on the owner's projects, endpoints, and captures are blocked. Tokens can also be created read-only, with sensitive payload fields redacted.
Safety posture
- Signature validation on capture; unsigned posts to signed endpoints are rejected before storage.
- Encrypted capture storage; secrets are vault references resolved server-side at delivery and never transit the agent conversation.
- Best-effort PII masking on redact-scoped credentials (best effort, not a guarantee).
- Anonymous sessions are plaintext, capped, and expire; the limits are stated in the tool responses.
Reviewing this extension
A step-by-step run of the connector, from an anonymous capture URL to a room with a second assistant, is at https://flurryport.io/docs/walkthrough. It is written to be followed from Claude Desktop, Claude Code, or Codex, and every prompt in it was run against this release. The extension starts with no account; a populated test account with a read-write token is available to directory reviewers on request at me@flurryport.io.
Privacy
The privacy policy is at flurryport.io/privacy. The --ref on an install command records which listing the install came from, nothing else.
Docs
- Documentation: https://flurryport.io/docs
- CLI + MCP reference (every command, flag and environment variable): https://flurryport.io/docs/cli
- Plans and limits: https://flurryport.io/docs/plans
- Troubleshooting: https://flurryport.io/docs/troubleshooting
- Recipe catalog: https://flurryport.io/recipes
- Security model: https://flurryport.io/recipes/security
Requirements
Node.js 22 or later is what the CLI is built and tested on.
License
MIT
Questions sur FlurryPORT MCP
Comment ajouter FlurryPORT MCP à Claude Code ?
Exécutez claude mcp add cli -- npx -y flurryport dans votre terminal. Ajoutez --scope user pour le rendre disponible dans tous les projets.
Comment ajouter FlurryPORT 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.
Dois-je m'inscrire pour utiliser FlurryPORT ?
Non, vous pouvez commencer immédiatement avec des sessions anonymes qui permettent jusqu'à 250 captures sans compte.
Comment puis-je tester des webhooks si je n'ai pas encore de backend en cours d'exécution ?
Vous pouvez demander à votre assistant de lancer un serveur echo, qui déploie un récepteur local pour prouver que la boucle fonctionne avant même d'écrire votre code de gestion.
Que sont les salons FlurryPORT ?
Les salons permettent une collaboration multi-agents sécurisée par signature, où plusieurs agents et humains partagent un enregistrement unique signé pour des tâches telles que la revue de code ou la répartition de tâches.