vibe-blueprint
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FOUNDATION_LLM_MODEL | No | Exact model ID; never silently replaced. | gpt-5.6-sol |
| FOUNDATION_LLM_API_KEY | No | Highest-priority credential; prefer `vibe-blueprint auth set` on a workstation. | none |
| FOUNDATION_CODE_SHARING | No | Maximum repository context: `none`, `summary`, or `diff`. | none |
| FOUNDATION_LLM_BASE_URL | No | Responses-compatible base URL. | https://api.inferenvoy.com |
| FOUNDATION_ALLOWED_ROOTS | No | Platform-delimited roots under which `project_root` may resolve. | server working directory |
| FOUNDATION_LLM_RESPONSES_PATH | No | Explicit path override; otherwise `/responses`, then `/v1/responses` only after 404/405. | discovered |
| FOUNDATION_LLM_REASONING_EFFORT | No | Responses reasoning effort. | xhigh |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| foundation_doctorA | Check non-secret model configuration, credential presence, allowed-root access, model connectivity, project Foundation state, and protection coverage. |
| foundation_analyze_projectB | Use the MCP's internal model plus deterministic activity-risk, minimum-invariant, and order-independent route checks to propose or deliberately abstain from a project Foundation. Additive traces explain activity evidence and route elimination. Does not write project state. |
| foundation_answer_questionA | Apply the user's answer to the one returned material-reality or financial-scope question, then re-run classification and the internal model recommendation. |
| foundation_commitA | Atomically commit a validated, user-confirmed analysis proposal to Foundation artifacts. Never modifies application source. |
| foundation_getA | Read the authoritative Foundation JSON, readable Markdown, or compact Session Brief. |
| foundation_assess_changeA | Compare a new requirement with committed Foundation state and reanalyze only affected capabilities. Does not commit changes. |
| foundation_scan_changesB | Scan Git changes, dependencies, migrations, environment names, and structure for combined Foundation boundary signals. |
| foundation_verifyA | Preview or run one explicitly registered, allowlisted Foundation evidence check with no shell. |
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 8 tools
Each tool targets a distinct phase of the Foundation workflow: health check (doctor), proposal (analyze_project), user interaction (answer_question), reading (get), writing (commit), re-evaluation (assess_change), scanning (scan_changes), and verification (verify). There is no meaningful overlap between any two tools.
All tools share the fixed prefix 'foundation_' followed by a clear verb_noun pattern (e.g., analyze_project, answer_question, scan_changes). This provides a predictable and systematic naming scheme across the entire set.
With 8 tools, the set is well-scoped for the Foundation domain. Each tool serves a necessary function and none feel redundant or superfluous, fitting comfortably within the ideal 3-15 tool range.
The toolset covers the full lifecycle: analysis, user interaction, commit, change assessment, scanning, verification, and health checks. There are no obvious dead ends or missing core operations for the stated purpose of managing project Foundation state.