Claude Code AI Collaboration MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NODE_ENV | No | Environment mode (e.g., development, production). | production |
| LOG_LEVEL | No | Logging level for the application. | info |
| O3_API_KEY | No | Optional O3 API key (defaults to OPENAI_API_KEY if not provided). | |
| MCP_PROTOCOL | No | Transport protocol to use for the server. | stdio |
| OPENAI_API_KEY | No | Optional OpenAI API key for GPT models integration. | |
| DEEPSEEK_API_KEY | Yes | DeepSeek API key required for the primary AI provider. | |
| ANTHROPIC_API_KEY | No | Optional Anthropic API key for Claude models support. | |
| MCP_DISABLE_CACHING | No | Whether to disable the memory and Redis-compatible caching system. | false |
| MCP_DISABLE_METRICS | No | Whether to disable performance monitoring and OpenTelemetry metrics. | false |
| MCP_DEFAULT_PROVIDER | No | Default AI provider to use for requests. | deepseek |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {
"level": "info"
} |
| resources | {
"subscribe": true,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| collaborateC | Collaborate with multiple AI providers to solve complex problems |
| reviewC | Get comprehensive reviews of content from multiple AI perspectives |
| compareC | Compare multiple items using AI analysis across various dimensions |
| refineC | Iteratively refine and improve content through AI-powered analysis and enhancement |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Collaboration History | Access to collaboration session history |
| Performance Metrics | Server performance and usage metrics |
| Search Index | Full-text search capabilities |
TDQS
Scored across 4 tools
The tools have distinct primary purposes: collaboration, comparison, refinement, and review. However, there is some conceptual overlap between 'refine' (iterative improvement) and 'review' (comprehensive analysis), which could cause mild confusion in tool selection for certain tasks.
All tool names follow a consistent verb-only pattern (collaborate, compare, refine, review), with no mixing of conventions or styles. This makes the tool set predictable and easy to navigate.
With only 4 tools, the server feels slightly thin for its broad purpose of 'AI collaboration and analysis.' While each tool covers a distinct function, the scope suggests more granular operations (e.g., specific analysis types or collaboration modes) might be missing, making it borderline appropriate.
The tools cover high-level AI collaboration and analysis functions, but there are notable gaps in the surface. For example, there are no tools for managing collaboration sessions, saving/loading analyses, or handling specific data types, which limits workflow completeness for the domain.