Multi-MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AZURE_API_KEY | No | Azure OpenAI API key | |
| DEFAULT_MODEL | No | Default model to use | |
| AZURE_API_BASE | No | Azure OpenAI endpoint | |
| GEMINI_API_KEY | No | Google Gemini API key | |
| OPENAI_API_KEY | No | OpenAI API key | |
| AWS_REGION_NAME | No | AWS region for Bedrock | |
| ANTHROPIC_API_KEY | No | Anthropic API key | |
| AWS_ACCESS_KEY_ID | No | AWS access key ID for Bedrock | |
| DEFAULT_MODEL_LIST | No | Default model list | |
| OPENROUTER_API_KEY | No | OpenRouter API key | |
| AWS_SECRET_ACCESS_KEY | No | AWS secret access key for Bedrock |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| codereviewB | Systematic code review using external models. Covers quality, security, performance, and architecture. |
| chatC | General chat with AI assistant. Supports multi-turn conversations with project context and file inclusion. |
| compareA | Compare responses from multiple AI models. Runs the same content against all specified models in parallel. Supports multi-turn conversations with project context and file inclusion. |
| debateA | Multi-model debate: Step 1 (independent answers) + Step 2 (debate/critique). Each model provides independent answer, then reviews all responses and votes. |
| versionA | Get server version, configuration details, and list of available tools. |
| modelsA | List available AI models. Returns model names, aliases, provider, and configuration. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| codereview | Perform systematic code review |
| chat | Chat with AI assistant |
| compare | Compare responses from multiple AI models |
| debate | Multi-model debate with critique and voting |
| models | List available AI models |
| version | Get server version and info |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/religa/multi_mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server