OrchestratorSAFE
small MCP server for orchestrating tasks across LLM instances
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](CHANGELOG.md) [](https://smithery.ai/server/orchestrator-server)
The MCP Orchestrator Server provides task management and coordination capabilities across MCP enabled LLM instances like Claude Desktop or Cline. In simpler terms it allows for AI agents to create, share and execute tasks across instances
Features
Version 1.1.0
- Task Updates: Modify pending tasks
- Safe Deletion: Delete tasks with dependency checks
- Cycle Detection: Prevent dependency cycles
- Tool Listing: Comprehensive tool documentation
- Enhanced State Management: Improved task state transitions
Core Features
- Task creation with dependencies
- Multi-instance coordination
- Persistent task storage
- Dependency enforcement
- Task status tracking
Installation
Installing via Smithery
To install Orchestrator Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install orchestrator-server --client claude
Manual Installation
npm install npm run build
Usage
Create a Task
await create_task({
id: 'setup',
description: 'Initial setup'
});Get Next Task
const task = await get_next_task({
instance_id: 'worker-1'
});Complete Task
await complete_task({
task_id: 'setup',
instance_id: 'worker-1',
result: 'System initialized'
});Documentation
- API Reference
- Quick Start Guide
- Changelog
Roadmap
Version 1.2.0
- Task priorities
- Timeouts
- Instance management
Version 1.3.0
- Task g
45a2a64e7571OBSERVED · 2026-10-09Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add orchestrator-server-tests -- npx -y [email protected]
{
"mcpServers": {
"orchestrator-server-tests": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (7)
4 read · 2 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
complete_task | read | Mark a task as completed |
create_task | write | Create a new task |
delete_task | destructive | Delete a task if it has no dependents |
get_next_task | read | Get the next available task |
get_task_details | read | Get details of a specific task |
get_task_status | read | Get status of all tasks |
update_task | write | Update an existing pending task |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
delete_task
@modelcontextprotocol/sdk, @types/node, typescript, tsc-watch
Gates applied: no_behavioural_pass.
45a2a64e7571full audit observations/trust-audit/mcp-server/mokafari__orchestrator.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | 45a2a64e7571 | SAFE | B | 89 | first audit |
Questions
What is the Orchestrator MCP server?
small MCP server for orchestrating tasks across LLM instances
What tools does Orchestrator expose?
7 in total: 4 read-only, 2 that write, and 1 that can delete or overwrite (delete_task). Every one is listed on this page with its risk.
Is Orchestrator safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Orchestrator need?
No credential environment variables were found in its source, so it appears to need none.
How does Orchestrator run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as orchestrator-server-tests at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (45a2a64e7571), read on 2026-10-09. The repository is watched and re-audited when it changes.