Which integrations are available for this server?

Provides tools for inter-agent communication via RabbitMQ, enabling agents to ask questions routed by topic.

How do I use agent-mesh-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@agent-mesh-mcp ask backend agent about deployment status" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

agent-mesh-mcp

by openbiocure

Overview Schema Source Related Servers Discussions Admin

JavaScript

Remote

agent-mesh-mcp

MCP server for a distributed AI agent mesh. Agents communicate via RabbitMQ, persist state in Postgres, and are managed through MCP tools.

Part of the Agent Mesh ecosystem:

Repo	What	Language
agent-mesh-mcp	MCP server — tools, events, webhooks, channels	JavaScript
agent-mesh-worker	Worker daemon — warm sessions, scheduling, RabbitMQ	Python
agent-mesh-lib	Shared library — identity, guardrails, memory, hooks	Python
agent-mesh-hooks	CLI hooks for Claude Code — auto-inject prompts + memory	Python
agent-mesh-memory	Temporal knowledge graph memory (Graphiti + FalkorDB)	Python

Architecture

PlantUML source — regenerate with plantuml docs/architecture.puml

Related MCP server: gptqueue

Agent Addressing

Agents use a slug@repo:scope address format:

devops-engineer                        # unique role, no repo needed
js-engineer@obc-connectors             # same role, different repos
js-engineer@obc-platform
architect@obc-datalake:landing         # same role + repo, different scopes
architect@obc-datalake:warehouse

Each address produces a deterministic UUID (v5) — identical in Python and JS. No DB lookup needed to know an agent's ID.

Transports

stdio (index.mjs) — for local Claude Code / Cursor
HTTP (server.mjs) — remote access via Streamable HTTP + Keycloak OAuth

Install

npm install -g agent-mesh-mcp

Tools

Agents

Tool	Description
`create_agent`	Create agent with slug, prompt, model, config
`update_agent`	Update prompt (bumps version), model, config
`get_agent`	Full details: prompt, guardrails, online workers
`list_agents`	All registered + online agents
`ask_agent`	Send a message to another agent via RabbitMQ
`get_task_result`	Poll async task result
`cancel_agent`	Cancel a running task
`tail_agent`	Live activity feed from a running agent

Guardrails

Pre-execution tool call validation. Three layers (fast to slow):

regex — pattern match on tool input (microseconds)
validator — Guardrails AI (DetectPII, ToxicLanguage, etc.)
llm_judge — LLM evaluates criteria before allowing

Tool	Description
`create_guardrail`	Create a guardrail rule (global or per-agent)
`list_guardrails`	List all rules, filter by agent
`delete_guardrail`	Remove a rule

# Block git push to prod for all agents
create_guardrail(tool="Bash", pattern="git push.*prod", action="block")

# PII detection on all tool inputs for a specific agent
create_guardrail(tool="*", type="validator", agent="js-engineer@obc-connectors",
                 config={"validator":"DetectPII","params":["EMAIL_ADDRESS"]})

Scheduling

Tool	Description
`create_schedule`	Cron or interval schedule for an agent
`list_schedules`	All schedules with run history
`delete_schedule`	Remove a schedule
`run_schedule`	Fire a schedule immediately

Incidents

Tool	Description
`create_incident`	Track a P1/P2/P3 incident
`list_incidents`	Filter by severity/status
`update_incident`	Change status, assign agent, link PR
`resolve_incident`	Mark as resolved

Releases

Tool	Description
`create_release`	Track a deployment with steps + rollback
`list_releases`	All releases by status
`get_release`	Full release details
`update_release`	Update status (with transition validation)
`close_release`	Mark deployed/rolled back

Approvals

Tool	Description
`request_approval`	Request human approval (notifies via Telegram)
`get_approval`	Check approval status
`list_approvals`	All pending/approved/rejected
`approve` / `reject`	Respond to an approval
`comment_approval`	Add context to an approval

Other

Tool	Description
`create_feature`	Track a feature request
`list_features`	All features by status
`update_feature`	Change status/priority
`report_mesh_bug`	Report a bug in the mesh itself
`list_mesh_bugs`	All mesh bugs
`update_mesh_bug`	Fix/close a mesh bug
`search_conversations`	Search agent conversation history
`notify`	Send a notification via Telegram
`get_setting` / `set_setting` / `list_settings`	Mesh configuration

Events

Domain events are emitted on state changes and published to RabbitMQ:

incident.created → notifies Telegram (P1/P2), publishes to event.incident.created
release.status_changed → notifies subscribers, triggers deploy queue
approval.requested → sends Telegram buttons, publishes event
feature.created → publishes event
mesh.shutdown → all workers stop consuming
mesh.resume → workers restart

Workers can bind to event topics in their worker.json:

{
  "event_topics": ["event.incident.*", "event.release.*"]
}

Kill Switch

POST /mesh/shutdown   → MESH_ENABLED=false, pauses schedules, broadcasts event
POST /mesh/resume     → MESH_ENABLED=true, resumes schedules
GET  /mesh/status     → current state

Also available via Telegram: /shutdown, /resume, /meshstatus

Status Transitions

YAML-based validation stored in mesh_settings. Prevents invalid state changes:

incident:
  open: [investigating]
  investigating: [fix_submitted, resolved]
  fix_submitted: [resolved, investigating]

release:
  ready: [approved, cancelled]
  approved: [deploying]
  deploying: [deployed, rolled_back]

Worker (agent-mesh-worker)

The worker is a separate Python package: agent-mesh-worker

worker.json:

{
  "slug": "js-engineer",
  "cwd": "/path/to/repo",
  "scope": "hotfix",
  "prompt_file": ".claude/agents/js-engineer.md"
}

Repo is derived from basename(cwd). Override with "repo": "obc-connectors-core" when the directory name doesn't match.

Environment Variables

Variable	Default	Description
`RABBITMQ_URL`	`amqp://guest:guest@localhost:5672/`	RabbitMQ connection
`RABBITMQ_MGMT_URL`	`http://localhost:15672`	RabbitMQ management API
`EXCHANGE_NAME`	`agents`	RabbitMQ exchange
`AGENT_NAME`	`unknown`	Calling agent's address (set by worker)
`AGENT_ID`	—	Calling agent's UUID (set by worker)
`WORKER_ID`	—	Worker instance UUID (set by worker)
`ASK_TIMEOUT`	`900`	Reply timeout in seconds
`MCP_PORT`	`3100`	HTTP server port
`KEYCLOAK_URL`	`http://localhost:8080`	Keycloak base URL
`KEYCLOAK_REALM`	`master`	Keycloak realm
`KEYCLOAK_CLIENT_ID`	`agent-mesh`	OAuth client ID
`KEYCLOAK_CLIENT_SECRET`	—	OAuth client secret
`DATABASE_URL`	—	Postgres connection (Prisma)

License

MIT

This server cannot be deployed

Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Maintenance

ActivityActive

ResponsivenessSyncing

Resources

Related MCP Connectors

AgenTruxOAuth
com.agentrux
Authenticated event topics for agent-to-agent messaging with per-agent credentials and audit logs.
Agent Orchestration Communication Security
1
https://api.agentrux.com/mcp
AgentDM: Agent to Agent Communication PlatformOAuth
ai.agentdm
Agent communication platform for agent to agent messaging via MCP. Messages, channels, skills.
Autonomous Agents Communication Agent Orchestration
2
https://api.agentdm.ai/mcp/v1/grid
kinform.net — Agent Cooperation Network B
net.kinform
Cooperation network for AI agents: help requests, forum and direct messages over MCP.
Agent Orchestration Communication
161
https://mcp.kinform.net/mcp
AgentsX A
com.emmanuelbenami.www
AgentsX is a public exchange network for AI agents. Search short posts and longer discussions, publish a question or finding, reply in persistent threads, and retrieve replies through a durable inbox. Connect through remote MCP with OAuth or a scoped API key. Six tools cover search, reading, publishing, replying, inbox retrieval, and explicit retrieval acknowledgement. Public participation requires the operator’s authorization. Humans can apply for manual admission. Replies persist between runs; AgentsX does not restart agents or require an always-on connection. Quickstart: https://www.emmanuelbenami.com/agentsx/quickstart
AI & Machine Learning Communication Research & Data
161
https://www.emmanuelbenami.com/agentsx/mcp

Related MCP Servers

Agent Communication MCP Server
Communication Agent Orchestration Autonomous Agents
mkXultra
A
license
Not graded
quality
A
maintenance
Enables AI agents to communicate with each other through Slack-like room-based channels with messaging, mentions, presence management, and long-polling for real-time collaboration.
Updated 14 days ago (2026-10-16 10:35 UTC)
258 npm
5
MIT
gptqueue
Communication Agent Orchestration
rahulrajaram
A
license
Not graded
quality
B
maintenance
Enables AI agents to discover each other and exchange typed messages through a Redis-backed queue via MCP tool calls, with support for registration, heartbeat, and queue management.
Updated a month ago (2026-10-03 18:13 UTC)
2
MIT
agent-room-mcp
Communication Agent Orchestration
umbecanessa
A
license
Not graded
quality
D
maintenance
Enables Cursor agents to communicate via a shared chat room, allowing them to ask questions, share status, and warn about conflicts while collaborating on the same repo.
Updated 5 months ago (2026-06-12 14:17 UTC)
42 npm
MIT
rabbitmq-mcp
Networking & Infrastructure Developer Tools
stackblaze
A
license
Not graded
quality
B
maintenance
Enables LLM agents to manage RabbitMQ queues, exchanges, and shovels via MCP tools, with restricted mode for production environments.
Updated 5 months ago (2026-06-14 15:53 UTC)
Apache 2.0

agent-mesh-mcp

Architecture

Agent Addressing

Transports

Install

Tools

Agents

Guardrails

Scheduling

Incidents

Releases

Approvals

Other

Events

Kill Switch

Status Transitions

Worker (agent-mesh-worker)

Environment Variables

License

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Agent Communication MCP Server

gptqueue

agent-room-mcp

rabbitmq-mcp