Manufacturing Inference Advisor MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DOCKER_MCP_CLIENT | No | Set DOCKER_MCP_CLIENT to another supported Docker MCP client or 'none'. |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| validate_requirements_toolB | Validate and normalize project requirements; reports gaps and contradictions without inventing values. |
| analyze_inference_project_toolB | Estimate a transparent capacity envelope from the model, context, concurrency and growth inputs. |
| assess_existing_infrastructure_toolB | Compare declared infrastructure with the planning envelope and identify reuse and gaps. |
| recommend_architecture_toolB | Compare integration patterns and return a reasoned classification, alternatives and risks. |
| generate_hardware_spec_toolC | Generate a vendor-neutral compute, memory, storage, network, power, cooling and security specification. |
| generate_bom_toolA | Generate a specification-first BOM; product, price and origin fields remain unknown without evidence. |
| screen_bom_for_compliance_toolC | Apply a configurable sourcing workflow; unknown origin cannot pass a policy requiring evidence. |
| compare_bom_options_toolA | Compare BOM evidence completeness and known costs without fabricating a winner. |
| generate_deployment_plan_toolB | Produce a staged deployment, verification, approval and rollback plan. |
| save_project_artifactsA | Persist generated non-secret project artifacts and return a content hash and resource URI. |
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 10 tools
Each tool targets a distinct stage of the advisory workflow, from requirements validation through deployment planning and artifact persistence. Even the related BOM tools are clearly separated by workflow boundaries: specification-first generation, compliance screening, and evidence/cost comparison. No two tools appear interchangeable.
Nine of ten tools follow a consistent verb_noun_tool pattern with clear, action-oriented names. The outlier is save_project_artifacts, which drops the _tool suffix, creating a minor inconsistency that is still easy to read and predict.
Ten tools is well within the ideal range and each tool earns its place in the pipeline. The count matches the server's end-to-end advisory purpose without redundancy or bloat.
The tool set covers the full advisory lifecycle: validate requirements, analyze capacity, assess infrastructure, recommend architecture, generate hardware spec, build and screen BOMs, compare options, generate deployment plan, and persist artifacts. There are no obvious dead ends or missing operations for the stated domain.