I'm MeshSeeks, look at me! 🟦 A multi-agent mesh network for parallel AI task completion
If you want an AI assistant working directly with Meshseeks, the meshseeks mcp server is the bridge. I'm MeshSeeks, look at me! 🟦 A multi-agent mesh network for parallel AI task completion.
MeshSeeks spawns specialized AI agents that work in parallel to solve complex coding problems. Like the helpful blue creatures that inspired our name, each agent exists for a single purpose: complete their assigned task and help you succeed. Originally forked from claude-code-mcp-enhanced, now with distributed intelligence inspired by Claude Research.
Once connected, the assistant can call these 7 tools directly:
mesh_analyze_problem — Decompose complex problems into agent tasksmesh_execute_tasks — Execute tasks with dependency managementmesh_solve_problem — End-to-end problem solving with multiple strategiesmesh_status — Monitor network performance and agent metricsPrerequisites — 1. Node.js v20+ - Install via nvm or fnm 2. Claude CLI - Install and run once withCursor — Cursor uses mcp.json. - macOS: ~/.cursor/mcp.json - Windows: %APPDATA%\Cursor\mcp.json - Linux: ~/.config/cursor/mcp.jsonWindsurf — Windsurf users use mcp_config.json - macOS: ~/.codeium/windsurf/mcp_config.json - Windows: %APPDATA%\Codeium\windsurf\mcp_config.json - Linux:The server is distributed via npm as node, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.
The server reads 5 environment variables: MCP_MESH_MAX_AGENTS, MESHSEEKS_CATCHPHRASE, MCP_USE_ROOMODES, MCP_WATCH_ROOMODES, MCP_CLAUDE_DEBUG. Keep credentials in your client's env block or a secrets manager rather than committing them.
Developer-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. Meshseeks sits in that group, and the shape of its toolset — mesh_analyze_problem, mesh_execute_tasks, mesh_solve_problem among others — tells you what it is really for. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| mesh_analyze_problem | Decompose complex problems into agent tasks |
| mesh_execute_tasks | Execute tasks with dependency management |
| mesh_solve_problem | End-to-end problem solving with multiple strategies |
| mesh_status | Monitor network performance and agent metrics |
| Prerequisites | 1. **Node.js v20+** - Install via [nvm](https://github.com/nvm-sh/nvm) or [fnm](https://github.com/Schniz/fnm) 2. **Claude CLI** - Install and run once with permissions: bash npm install -g @anthropic-ai/claude-code clau |
| Cursor | Cursor uses mcp.json. - **macOS:** ~/.cursor/mcp.json - **Windows:** %APPDATA%\\Cursor\\mcp.json - **Linux:** ~/.config/cursor/mcp.json |
| Windsurf | Windsurf users use mcp_config.json - **macOS:** ~/.codeium/windsurf/mcp_config.json - **Windows:** %APPDATA%\\Codeium\\windsurf\\mcp_config.json - **Linux:** ~/.config/.codeium/windsurf/mcp_config.json |
{
"mcpServers": {
"Local MCP Server": {
"type": "stdio",
"command": "node",
"args": [
"dist/server.js"
],
"env": {
"MCP_USE_ROOMODES": "true",
"MCP_WATCH_ROOMODES": "true",
"MCP_CLAUDE_DEBUG": "false"
}
},
"other-services": {
// Your other MCP services here
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| MCP_MESH_MAX_AGENTS | Configuration value read at startup. | Optional |
| MESHSEEKS_CATCHPHRASE | Configuration value read at startup. | Optional |
| MCP_USE_ROOMODES | Configuration value read at startup. | Optional |
| MCP_WATCH_ROOMODES | Configuration value read at startup. | Optional |
| MCP_CLAUDE_DEBUG | Configuration value read at startup. | Optional |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.