Orchestrator MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_TOKEN | No | GitHub Personal Access Token for GitHub server integration | |
| SLACK_APP_TOKEN | No | Slack App Token for Slack integration (if enabled) | |
| SLACK_BOT_TOKEN | No | Slack Bot Token for Slack integration (if enabled) | |
| SEMGREP_APP_TOKEN | No | Semgrep App Token for enhanced security scanning | |
| OPENROUTER_API_KEY | Yes | Your OpenRouter API key (required for AI features) | |
| OPENROUTER_MAX_TOKENS | No | Maximum tokens per request | 2000 |
| OPENROUTER_TEMPERATURE | No | Temperature for AI responses | 0.7 |
| OPENROUTER_DEFAULT_MODEL | No | Default model to use on OpenRouter | anthropic/claude-3.5-sonnet |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ai_processA | Primary AI orchestration interface - intelligently processes complex requests by automatically selecting and coordinating multiple tools. Handles file operations, git management, web search, web fetching, browser automation, security analysis, and more. Describe your goal naturally - the AI will determine the best approach and execute multi-step workflows. |
| get_infoA | System introspection - discover available capabilities, connected servers, and tool inventory. Use this to understand what the orchestrator can do before making complex requests. |
| ai_statusA | Health monitoring - check AI orchestration system status, model configuration, and capability testing results. Useful for debugging or verifying system readiness. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose with no overlap: ai_process handles orchestration and execution, ai_status focuses on health monitoring, and get_info provides system introspection. An agent can easily tell them apart based on their specific functions.
The naming is mostly consistent with a clear pattern: ai_process and ai_status use a consistent 'ai_' prefix, while get_info deviates slightly with a 'get_' prefix. The tools are readable and follow a logical structure, though not perfectly uniform.
With only 3 tools, the count feels thin for an 'orchestrator' server that claims to handle complex multi-step workflows across domains like file operations and web automation. This may limit functionality or require over-reliance on the ai_process tool.
There are significant gaps in the tool surface for an orchestrator domain: no tools for managing workflows (e.g., list, pause, cancel), no configuration or logging tools, and no way to interact with specific subdomains directly. This could cause agent failures when needing fine-grained control.