ssyubix-agentlink
ssyubix is an open source MCP project for cross-device communication between AI agents over the public internet.
ssyubix
Cross-device MCP for AI agents over the public internet.
ssyubix is 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.
Components
src/- Cloudflare Worker source
index.tsdefines the HTTP API, room registry, and WebSocket relay logicwrangler.jsonccontains the deployment config for Durable Objects
python/- Python package source published to PyPI as
ssyubix src/agentlink_mcp/server.pyexposes the MCP tools used by AI clientstests/contains basic unit tests for the local MCP server logic
- Python package source published to PyPI as
Quick Start
Install the MCP server package:
uvx ssyubix
Default public Worker endpoint:
https://agentlink.syuaibsyuaib.workers.dev
Optional environment variables:
AGENT_NAMEsets the local agent name shown to peersAGENTLINK_URLoverrides the default Worker endpoint for forks or self-hosted deploymentsSSYUBIX_STABLE_AGENT_IDENTITY_IDoverrides the per-device stable identity if you need to pin it explicitly
Available MCP Tools
agent_registerroom_createroom_joinroom_leaveroom_listroom_infocapability_get_selfcapability_upsert_selfcapability_set_availabilitycapability_remove_selftask_offertask_accepttask_rejecttask_defertask_listtask_getagent_sendagent_broadcastagent_read_inboxagent_list
Available MCP Resources
ssyubix://guides/readme-firstssyubix://rooms/{room_id}/agentsssyubix://rooms/{room_id}/agents/{agent_id}ssyubix://rooms/{room_id}/skillsssyubix://rooms/{room_id}/skills/{skill_id}ssyubix://rooms/{room_id}/tasksssyubix://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.
Available MCP Prompts
ssyubix_readme_first
Development
Python package work happens in python/.
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 [email protected] deploy --config src/wrangler.jsonc --dry-run
Architecture Notes
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.
Releases
- Python releases are built from
python/ - 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
- owner:
Open Source Workflow
- 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
Repository
- Source:
https://github.com/syuaibsyuaib/ssyubix - Package:
https://pypi.org/project/ssyubix/
相關伺服器
Wassenger
Wassenger MCP server to chat, send messages and automate WhatsApp from any AI model client (free trial available).
Unichat
A unified interface for various chat AI models including OpenAI, MistralAI, Anthropic, and Google AI, requiring vendor API keys.
Vapi MCP Server
A server for integrating with Vapi's voice AI APIs using function calls.
Gmail
Tools for common Gmail operations, such as sending emails.
Unipile
Access and manage messages from multiple platforms using the Unipile API.
aiogram-mcp
MCP server for Telegram bots built with aiogram. 30 tools, 7 resources, 3 prompts — messaging, rich media, moderation, interactive keyboards, real-time event streaming, rate limiting, permissions, and audit logging.
Deepseek R1
An MCP server for the Deepseek R1 model, using the Deepseek API.
Slack Notification
Send notifications to Slack channels using webhook URLs.
Beeper
A server for interacting with the Beeper communication network.
User Feedback
Simple MCP Server to enable a human-in-the-loop workflow in tools like Cline and Cursor.