Meridian MCP
by LuuOW
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | HTTP bind address (HTTP mode only). | 0.0.0.0 |
| PORT | No | HTTP port (HTTP mode only). | 3333 |
| GITHUB_TOKEN | No | Fallback for MERIDIAN_GITHUB_TOKEN if the latter is not set. | |
| MERIDIAN_MODEL | No | GitHub Models chat model to use. | meta/llama-3.3-70b-instruct |
| MERIDIAN_HTTP_PATH | No | HTTP endpoint path (HTTP mode only). | /mcp |
| MERIDIAN_CANDIDATES | No | Number of candidates generated per call. | 5 |
| MERIDIAN_TIMEOUT_MS | No | Abort fetch after this many milliseconds. | 90000 |
| MERIDIAN_GITHUB_TOKEN | No | GitHub Personal Access Token with 'Models: read' scope. Required unless GITHUB_TOKEN is provided. | |
| MERIDIAN_GATEWAY_TOKEN | No | If set, switches HTTP mode auth from pass-through to shared-key gateway. | |
| MERIDIAN_MODELS_ENDPOINT | No | Override for self-hosted gateways. | https://models.github.ai/inference/chat/completions |
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 |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityInactive
ResponsivenessUnresponsive