nexus-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NEXUS_CODEX_MODEL | No | Default model for the Codex runner | |
| NEXUS_CLAUDE_MODEL | No | Default model for the Claude runner | |
| NEXUS_CODEX_MODELS | No | Comma-separated model list for the Codex runner | |
| NEXUS_GEMINI_MODEL | No | Default model for the Gemini runner | |
| NEXUS_CLAUDE_MODELS | No | Comma-separated model list for the Claude runner | |
| NEXUS_GEMINI_MODELS | No | Comma-separated model list for the Gemini runner | |
| NEXUS_EXECUTION_MODE | No | Global execution mode (default or yolo) | default |
| NEXUS_OPENCODE_MODEL | No | Default model for the OpenCode runner | |
| NEXUS_OPENCODE_MODELS | No | Comma-separated model list for the OpenCode runner | |
| NEXUS_RETRY_MAX_DELAY | No | Maximum seconds to wait between retries | 60.0 |
| NEXUS_TIMEOUT_SECONDS | No | Subprocess timeout in seconds (10 minutes) | 600 |
| NEXUS_RETRY_BASE_DELAY | No | Base seconds for exponential backoff | 2.0 |
| NEXUS_OUTPUT_LIMIT_BYTES | No | Max output size in bytes before temp-file spillover | 50000 |
| NEXUS_RETRY_MAX_ATTEMPTS | No | Max attempts including the first (set to 1 to disable retries) | 3 |
| NEXUS_TOOL_TIMEOUT_SECONDS | No | Tool-level timeout in seconds (15 minutes); set to 0 to disable | 900 |
| NEXUS_CLI_DETECTION_TIMEOUT | No | Timeout in seconds for CLI binary version detection at startup | 30 |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
},
"prompts": {
"get": {}
},
"resources": {
"read": {}
}
}
} |
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| batch_promptA | Send multiple prompts to CLI runners in parallel (primary tool). Fans out tasks server-side with asyncio.gather and a semaphore, enabling true parallel runner execution within a single MCP call. Single-task usage is perfectly valid — use prompt for convenience when sending one task. |
| promptA | Send a prompt to a CLI runner as a background task. Returns immediately with a task ID. Client polls for results. This prevents timeouts for long operations (YOLO mode: 2-5 minutes). |
| set_preferencesA | Set persistent preferences that apply to subsequent prompt/batch_prompt calls. Preferences persist across MCP sessions. Call again to update, or use clear_preferences to reset all fields at once. To clear a single field while keeping others, pass the corresponding clear_* flag: set_preferences(clear_model=True) # clears model, keeps execution_mode |
| clear_preferencesA | Clear all persistent preferences, reverting to per-call defaults. Returns: Confirmation string. |
| set_model_tiersA | Save model tier classifications. Client sends sampling/benchmark results; server persists to backing store. Overwrites any previously saved tiers entirely. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| code_review | Review code for issues with structured findings by severity. |
| debug | Systematic diagnosis: reproduce, isolate, root cause, fix. |
| quick_triage | Fast assessment: what's wrong, severity, next step. |
| research | Structured research with source citations. |
| second_opinion | Independent review of another AI's output. |
| implement_feature | Generate feature implementation with quality checklist. |
| refactor | Restructure code while preserving behavior. |
| bulk_generate | Expand a template across variable sets for batch generation. |
| write_tests | Generate tests for existing code with configurable coverage approach. |
| compare_models | Compare outputs from multiple AI models. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| get_all_runners | Return all registered CLI runners with full details. Resource URI: nexus://runners |
| get_config | Return resolved operational config defaults. Resource URI: nexus://config Returns the fully merged defaults (hardcoded + env var overrides). Excludes execution_mode and model (exposed via nexus://preferences). |
| get_preferences_resource | Return current session preferences with config fallback. Resource URI: nexus://preferences If ctx is available and session preferences can be read, returns them with source='session'. Otherwise falls back to resolved config defaults with source='defaults'. |
| get_tiers_resource | Return saved model tier classifications. Resource URI: nexus://tiers Returns all persisted tier classifications as a JSON object. Returns an empty dict if no tiers have been saved yet. |
| get_opencode_status | Return OpenCode server integration status. Resource URI: nexus://opencode Always registered — reports configured=false when server is not set up, so client agents can understand why OpenCode tools are absent. |
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/j7an/nexus-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server