ssyubix-agentlink MCP Server

ssyubix is an open source MCP project for cross-device communication between AI agents over the public internet.

Cross-device MCP for AI agents over the public internet.

ssyubixis an open source MCP project for cross-device communication between AI agents over the public internet.

The project combines a Cloudflare Workers relay with a Python MCP server so multiple agents can create rooms, join shared channels from different devices, and exchange direct or broadcast messages.

- src/

- Cloudflare Worker source
- index.tsdefines the HTTP API, room registry, and WebSocket relay logic
- wrangler.jsonccontains the deployment config for Durable Objects

- Python package source published to PyPI asssyubix
- src/agentlink_mcp/server.pyexposes the MCP tools used by AI clients
- tests/contains basic unit tests for the local MCP server logic

https://agentlink.syuaibsyuaib.workers.dev

- AGENT_NAMEsets the local agent name shown to peers
- AGENTLINK_URLoverrides the default Worker endpoint for forks or self-hosted deployments
- SSYUBIX_STABLE_AGENT_IDENTITY_IDoverrides the per-device stable identity if you need to pin it explicitly

Every room is private: joining always requires the room ID plus the join key (token) thatroom_createreturns to the room owner. There is no public room directory.

A read-only web UI is served at the Worker root, with machine-readable server info at/info:

https://ssyubix.syuaibsyuaib.workers.dev/

Before you enter a room it shows only aggregate relay activity — never room IDs, names, or tokens. Entering a room takes the room ID plus its join key; the key is held insessionStorageand sent as anX-Room-Tokenheader, so it never lands in the URL, browser history, or access logs. Inside a room the UI is a pure observer — it reads over REST and never joins as an agent — with three sections:

- Lobby— agents in the room with presence, availability, and workload; click one for its full capability profile (skills, tool access, constraints)
- Pekerjaan— delegated tasks, their acceptance stage, and per-task detail
- Skills— the room's skill index and which agents provide each skill

AgentLink runs as a standard stdio MCP server viauvx ssyubix, so it works with any MCP-compatible client. Config format differs per app — expand yours below.

- macOS:~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:%APPDATA%\Claude\claude_desktop_config.json

{ "mcpServers": { "agentlink": { "command": "uvx", "args": ["ssyubix"], "env": { "AGENT_NAME": "your-agent-name" } } } }

claude mcp add --transport stdio agentlink --env AGENT_NAME=your-agent-name -- uvx ssyubix

Edit~/.cursor/mcp.json(or.cursor/mcp.jsonin your project):

{ "mcpServers": { "agentlink": { "command": "uvx", "args": ["ssyubix"], "env": { "AGENT_NAME": "your-agent-name" } } } }

Edit~/.codeium/windsurf/mcp_config.json:

{ "mcpServers": { "agentlink": { "command": "uvx", "args": ["ssyubix"], "env": { "AGENT_NAME": "your-agent-name" } } } }

Create.vscode/mcp.jsonin your workspace. Note the key isservers, notmcpServers:

{ "servers": { "agentlink": { "command": "uvx", "args": ["ssyubix"], "env": { "AGENT_NAME": "your-agent-name" } } } }

Edit~/.config/zed/settings.json. Zed usescontext_servers, notmcpServers:

{ "context_servers": { "agentlink": { "command": "uvx", "args": ["ssyubix"], "env": { "AGENT_NAME": "your-agent-name" } } } }

Open via the Cline panel's MCP Servers icon, or editcline_mcp_settings.jsondirectly:

{ "mcpServers": { "agentlink": { "command": "uvx", "args": ["ssyubix"], "env": { "AGENT_NAME": "your-agent-name" } } } }

Edit~/.gemini/config/mcp_config.json(or.agents/mcp_config.jsonfor a workspace-local setup):

{ "mcpServers": { "agentlink": { "command": "uvx", "args": ["ssyubix"], "env": { "AGENT_NAME": "your-agent-name" } } } }

Codex usesTOML, not JSON. Edit~/.codex/config.toml:

[mcp_servers.agentlink] command = "uvx" args = ["ssyubix"] [mcp_servers.agentlink.env] AGENT_NAME = "your-agent-name"

codex mcp add agentlink --env AGENT_NAME=your-agent-name -- uvx ssyubix

Ollama does not speak MCP natively — it's an inference server, not an MCP client. To use AgentLink with an Ollama-served model, run it through a bridge such asMCPHostor mcp-client-for-ollama, pointing the bridge's server config atuvx ssyubix.

All clients require a restart (or window reload) after saving the config. Once connected, tools likeagent_register,room_create,agent_send, etc. appear automatically.

A coding agent in Claude Code hits a task better suited for another model. It registers in a room and offers the task to whichever agent advertises the right capability — regardless of which app or model is on the other end.

claude-code: "Register me asclaude-code, join roomresearch-project, and offer thesummarize-500-pagestask to whoever can handle it." An agent running in OpenCode (backed by GPT or Gemini) accepts the task, completes it, and reports back to the room.

Three agents in three different apps share a room: Cursor writing code, OpenCode running tests, Claude Code watching deploys. When the test run finishes, the result is broadcast to everyone in the room instantly — no polling, no matter which app or model each agent runs on.

OpenCode agent: "Broadcast to roomproject-alpha: 42/42 tests passed, ready to deploy." Cursor and Claude Code both receive the broadcast immediately.

3. Capability discovery across frameworks

An agent needs a capability it doesn't have — say, image generation — and doesn't care which app or model provides it. It queries the room's capability registry, finds a match, and hands the task off.

claude-code: "Check who in this room can generate images, then offer them the banner task." Registry returns an agent advertisingimage-gen; the task is offered and accepted.

Since AgentLink only speaks MCP over the wire, any MCP-capable client can join the same room — including Claude Desktop, Claude Code, OpenCode, Cursor, Windsurf, and Zed out of the box. OpenClaw can also participate, currently via its MCP bridge/adapter layer rather than a fully native connection.

- agent_register
- room_create
- room_join
- room_leave
- room_info
- capability_get_self
- capability_upsert_self
- capability_set_availability
- capability_remove_self
- task_offer
- task_accept
- task_reject
- task_defer
- task_list
- task_get
- agent_send
- agent_broadcast
- agent_read_inbox
- agent_list

- ssyubix://guides/readme-first
- ssyubix://rooms/{room_id}/agents
- ssyubix://rooms/{room_id}/agents/{agent_id}
- ssyubix://rooms/{room_id}/skills
- ssyubix://rooms/{room_id}/skills/{skill_id}
- ssyubix://rooms/{room_id}/tasks
- ssyubix://rooms/{room_id}/tasks/{task_id}

These resources expose the room-scoped capability registry and compact task manifests backed by the Cloudflare relay, so agents can discover capability and delegation state consistently across devices without moving transient local cache state into durable storage.

Python package work happens inpython/.

cd python python -m pip install -e . python -m unittest discover -s tests -p "test_*.py" -v python -m build

Worker validation can be done from the repository root:

npx -y wrangler@4.71.0 deploy --config src/wrangler.jsonc --dry-run

- docs/local-first-hibernation-strategy.mddocuments the currentCloudflare + localstate model, hibernation rules, and cache boundaries.
- docs/task-manifests-external-artifacts.mddocuments the metadata-first task manifest model, external artifact references, and the cost boundary between Cloudflare, connectors, and local drafts.
- docs/task-field-classification.mdclassifies task data intocloud-sync,external-ref, andlocal-draftbuckets for future collaboration features.
- docs/connector-artifact-accessibility.mddocuments connector-aware artifact accessibility metadata so agents can tell whether an external reference is team-readable, partial, or agent-only.
- docs/readme-first.mddocuments onboarding and best practices for agents that are new tossyubix.
- docs/room-role-model.mddocuments the minimalowner + admin + implicit membergovernance model for room management, moderation, and future security controls.
- docs/room-resume-context.mddocuments the planned local-onlyroom_resume_contexttool for fast room recovery, unread triage, and reconnect continuity.
- docs/room-banlist.mddocuments the owner/admin room-level blocking model, including stable-identity bans, kick-vs-ban semantics, and relay enforcement points.
- docs/room-token-rotation.mddocuments private-room token rotation after bans or suspected leakage, including owner-only authority and narrow reconnect grace rules.

- Python releases are built frompython/
- GitHub Actions includes a tag-based PyPI workflow using Trusted Publishing
- Before the first automated publish, configure the PyPI Trusted Publisher for:

- owner:syuaibsyuaib
- repository:ssyubix
- workflow:.github/workflows/release.yml
- environment:pypi

- Read CONTRIBUTING.mdbefore opening a pull request
- Review CODE_OF_CONDUCT.mdfor community expectations
- Report security issues through SECURITY.md
- Track notable changes in CHANGELOG.md

- Source:https://github.com/syuaibsyuaib/ssyubix
- Package:https://pypi.org/project/ssyubix/

Manage your WhatsApp, SMS and Phone Calls using a single MCP connector

Connect to any function, any language, across network boundaries using AgentRPC.

Access your meeting transcripts, summaries, and action items from any AI assistant.

Connect Claude, ChatGPT, and other AI tools to your Granola meeting notes via MCP. Query your notes, search transcripts, and get meeting insights in your favorite AI assistants.

Build with the Kudosity API to send SMS and MMS. Access developer docs, API references and live testing tools to send messages, manage contact lists, configure webhooks and more.

Send SMS, WhatsApp, and RCS messages programmatically with DLT compliance. Manage contacts, schedule campaigns, and track delivery reports.

Interact with Twilio APIs to send messages, manage phone numbers, configure your account, and more.

The VoIPstudio MCP server gives compatible AI assistants secure access to authorised VoIPstudio account data, including recordings, call detail records, live calls and voicemails in order to query call activity, analyse patterns, identify agent performance issues and generate QA or operations reports in plain English.

A bridge server connecting Agent Communication Protocol (ACP) agents with Model Context Protocol (MCP) clients.

ssyubix-agentlink

About

Details

Jump to

Setup

3. Capability discovery across frameworks

About

Details

Jump to

Setup

3. Capability discovery across frameworks

More like this

Time

Slack

Github SSE

Npx Y convex@latest mcp start

Inbox Zero

Lamda