mesh_agent_status
Check status of spawned agents. Returns progress, completion status, and time estimates.
LABSCO SUMMARY
Several Claude Code agents on one problem at once, each with its own context window.
The value is context, not just speed: work that would fill a single session gets split so each agent carries only its own slice. Plan and execute are separable — you can get the task breakdown, dependencies and estimates back without anything running yet. Note what it needs before you commit: the agents launch the Claude CLI with permissions bypassed, which is a decision to make deliberately.
What it is
An orchestration layer over the Claude Code CLI. It breaks a problem into tasks, runs them across parallel agents with dependencies respected, and aggregates the results.
What you get
- A problem decomposed into a structured task breakdown before anything runs
- A plan you can read first — tasks, dependencies and time estimates — returned without executing it
- Parallel execution across the mesh with dependency management and result aggregation, bounded by a concurrency limit you set
- End-to-end solving in one call, where the analysis and the execution happen together for a chosen approach and agent count
- Single specialized agents spawned for one task with a named role, returning an agent ID immediately
- Progress, completion status and time estimates for the agents in a session, and results collected per agent when they finish
- Network status: which agents are active, what has completed, and the performance metrics behind it
Requirements
The Claude Code CLI installed and already authorized: run claude --dangerously-skip-permissions once by hand, log in and accept the terms, or the server's agents cannot start. That flag is how the spawned agents run, so they execute without permission prompts. Node.js v20 or newer. Clone the repository, npm install and npm run build, then point your client at dist/mesh-server.js; the npm package is @thomaswalichiewicz/meshseeks-mcp-server, currently 1.1.1, with binaries meshseeks and meshseeks-server. CLAUDE_CLI_PATH sets a custom path to the Claude CLI. On macOS the first run may fail while the OS asks for folder permissions.
Setup effort
One command — npx -y @thomaswalichiewicz/meshseeks-mcp-server
USE CASES
01
Seeing how a big change would be broken up before committing to it
Get the task breakdown, its dependencies and time estimates back without any agent starting work.
02
Building out a feature that has independent parts
Decompose it, then run the tasks in parallel with a concurrency limit and let the results be merged.
03
Handing over a whole problem and coming back to the answer
One call that analyzes and executes, with the approach and agent count set up front.
04
Putting one specialist on one job
Spawn a single agent with a named role for that task; it returns an ID immediately and you collect the result later.
05
Checking a long run has not stalled
Read which agents are active and what they have finished, with progress and time estimates.
8 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
mesh_analyze_problem
Analyze a complex coding problem and create a task decomposition plan for the agent mesh network. Returns a structured breakdown of tasks for parallel execution.
mesh_collect_result
Collect results from completed agents.
mesh_execute_tasks
Execute a set of tasks across the agent mesh network with parallel processing, dependency management, and result aggregation.
mesh_plan
Create a task execution plan without running it. Returns immediately with task breakdown, dependencies, and time estimates.
mesh_solve_problem
End-to-end problem solving using the agent mesh network. Combines problem analysis and task execution in a single operation.
mesh_spawn_agent
Spawn a single specialized agent for a specific task. Returns immediately with agent ID.
mesh_status
Get the current status of the agent mesh network, including active agents, completed tasks, and performance metrics.
BEFORE YOU INSTALL
What to know first
Tools you get
8 tools when we connected. The configs run the mesh server and its 8 mesh tools; the documented claude_code, health and convert_task_markdown belong to a different server and are not available here.
Requires
Node.js v20+
Where it runs
All 3 documented clients run the server on your machine.
CONTEXT COST
Light Standing cost
Rated by the size of the 8 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
Build from source
TERMINAL
# Clone and build
git clone https://github.com/twalichiewicz/meshseeks.git
cd meshseeks
npm install
npm run build
# Add to your MCP config (see paths below)npx
TERMINAL
npx -y @thomaswalichiewicz/meshseeks-mcp-serverMCP Clients
Claude Desktop, Cursor, Windsurf
JSON
{
"mcpServers": {
"meshseeks": {
"command": "node",
"args": [
"<YOUR_PATH_TO_MESHSEEKS>/dist/mesh-server.js"
],
"env": {
"MCP_MESH_MAX_AGENTS": "5",
"MESHSEEKS_CATCHPHRASE": "true"
}
}
}
}
