localvibecode
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PYTHONPATH | Yes | Path to the localVibeCode src directory so the MCP server module can be located. |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| localvibecode_build_graphB | Build/refresh the deterministic AST Code Knowledge Graph (Graphify) with 0 LLM tokens. Returns Architectural God Nodes, import/call dependencies, and public signatures. |
| localvibecode_blast_radiusB | Extract the Surgical Context (< 4,000 tokens) for a target file: includes target code, 1-hop outbound signatures (bodies stripped), and 1-hop inbound callers. |
| localvibecode_verifyB | Run Zero-Token Deterministic Verification (AST syntax check, Enterprise Security SAST, and Unit Tests). |
| localvibecode_pev_runC | Execute an Enterprise Local Vibe Coding task using the Deterministic PEV (Plan -> Execute -> Verify) pipeline with Fresh Context isolation on 1 Local Ollama Model. |
| aisdlc_pev_runC | Legacy alias for localvibecode_pev_run. |
| aisdlc_blast_radiusC | Legacy alias for localvibecode_blast_radius. |
| aisdlc_build_graphD | Legacy alias for localvibecode_build_graph. |
| aisdlc_verifyC | Legacy alias for localvibecode_verify. |
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
The four localvibecode_ tools are distinct in purpose (graph build, context extraction, verification, pipeline run), but each has an exact aisdlc_ duplicate. Descriptions explicitly mark these as aliases, which mitigates but does not eliminate misselection risk.
Within each prefix, names follow a clear verb_noun pattern (build_graph, blast_radius, verify, pev_run), but the set mixes two different namespace prefixes (localvibecode_ vs aisdlc_), which is inconsistent across the surface.
The server registers 8 tools, but 4 are pure legacy aliases, so the real functional surface is only 4. The count is inflated by duplication rather than reflecting genuine capability.
The four real tools cover the core workflow—graph construction, surgical context extraction, deterministic verification, and the PEV execution pipeline. Minor gaps like graph inspection/reset or model management exist but are workable around.