meshes
MCP server for Meshes — emit events, manage workspaces, create rules, and inspect deliveries from any MCP-compatible client.
claude mcp add --transport stdio mesheshq-meshes-mcp-server npx -y @mesheshq/mcp-server \ --env MESHES_ORG_ID="your_organization_uuid" \ --env MESHES_API_URL="https://api.meshes.io" \ --env MESHES_ACCESS_KEY="your_access_key" \ --env MESHES_SECRET_KEY="your_secret_key" \ --env MESHES_ORGANIZATION_ID="your_organization_uuid"
How to use
This MCP server implements the Meshes integration layer for emitting product events, managing workspaces, and configuring routing rules and connections. It exposes a suite of CLI-like tools (via the MCP interface) for interacting with a Meshes organization, including emitting events, listing and managing workspaces, creating and updating connections, and managing routing rules. Typical workflows include configuring your MCP server in your environment, authenticating with the provided Meshes keys, and using the available tools to push events and inspect deliveries. For example, you can emit events to drive routing and delivery retries, manage multi-tenant workspaces, and inspect event delivery status across your organization.
How to install
Prerequisites:
- Node.js installed on your machine (recommended LTS version)
- Access to a Meshes account with API keys (MESHES_ACCESS_KEY, MESHES_SECRET_KEY, MESHES_ORG_ID)
Installation steps:
-
Install dependencies and build (if you’re contributing): git clone https://github.com/mesheshq/meshes-mcp-server.git cd meshes-mcp-server npm install npm run build
-
Run the MCP server locally using npx (as shown in the README example): claude mcp add meshes
-e MESHES_ACCESS_KEY=your_access_key
-e MESHES_SECRET_KEY=your_secret_key
-e MESHES_ORG_ID=your_organization_uuid
-- npx -y @mesheshq/mcp-server -
Alternatively, configure via Cursor or Windsurf using the provided JSON examples in the documentation. Ensure your environment variables are set (MESHES_ACCESS_KEY, MESHES_SECRET_KEY, MESHES_ORG_ID) and optionally MESHES_API_URL if you’re using a non-default API endpoint.
Additional notes
Security note: MCP config files contain your secret keys. They should be kept secure and not committed to version control. They typically live in a user’s home directory configuration (e.g., ~/.cursor/mcp.json). Verify that you’re using the appropriate environment variables in your deployment environment. If migrating from MESHES_ORG_ID to MESHES_ORGANIZATION_ID, ensure only one is set. The available tools cover a broad range of operations—from emitting events (meshes_emit_event, meshes_emit_bulk_events) to workspace and connection management (meshes_list_workspaces, meshes_create_workspace, meshes_get_connection, etc.). If you encounter authentication failures, double-check keys and API URL (MESHES_API_URL) if you’re using a custom Meshes deployment.
Related MCP Servers
mongo
MCP server that provide tools to LLMs such as claude in cursor to interact with MongoDB
cc-session-search
MCP server for searching and analyzing Claude Code conversation history
claude-code-memory
A Claude Code plugin that gives Claude fully automatic, per-project cognitive memory with hybrid search, session lifecycle hooks, and local embeddings.
mcpman
The package manager for MCP servers — install, manage & monitor across Claude Desktop, Cursor, VS Code, Windsurf
hive-memory
Cross-project memory for AI coding agents. MCP server that maintains context, decisions, and knowledge across workspaces. Fully local.
code-guardian
Code Guardian Studio – AI-powered code refactor engine for large repositories, built on Claude Code + MCP.