LEX AI
Guides, workflows, and technical references for the LEX AI MCP server.
AK
By Atakan Kaya·45 articlesStart
OverviewLEX AI is a local MCP server that gives your IDE assistant ten purpose-built workflow modes, exposing one tool surface at a time.
4 min readSetup and dashboardHow lex setup-with-ai wires the MCP server into a project and its coding tools, and what to confirm before starting an assistant request.
4 min readAI dashboardWhat lex ai-dashboard shows in its four panels, what pressing Save actually changes, and a pre-flight routine to run before every assistant request.
3 min readChoose the right pathHow to pick one of the ten LEX AI modes from your intent, with disambiguation rules, worked examples, and the two cases where a mode redirects you.
3 min readSupported coding toolsThe seven agentic coding environments LEX AI supports, where each keeps its MCP config, how the agent payload is rendered per tool, and what setup writes or leaves alone.
3 min readModes
Mode chooserThe ten LEX AI modes side by side, what each one is for, which of them touch git, and how to switch between them.
5 min readForwardForward mode builds a Lex app end to end across 20 steps on its own GitHub run branch, starting either from a project contract or from a prose description.
3 min readBackwardBackward mode reverse-documents an existing Lex codebase across 18 steps, pausing once for the discovery questionnaire, and writes every output to the working tree without touching git.
3 min readEditHow edit mode makes one focused change to an existing Lex app: the 22-task catalog, the sustainability checks the server injects, and when another mode fits better.
4 min readReviewHow review mode runs flat, idempotent audits of an existing project: the convention and business review types, what is recorded, and where the reports land.
3 min readMVP workflowsThe two MVP modes: the capped six-checkpoint generator with its boot-check gate and local-only git, and MVP completion, which runs forward steps 9 to 19 to reach full product scope.
4 min readBriefBrief mode interviews you one question at a time and writes the project contract that every other LEX AI mode builds against.
3 min readDeployDeploy mode gets an existing Lex app running in a target environment using steps served by the remote Lex handbook, and never records a secret value.
3 min readView all 10 articlesSystem
Execution modelHow the coordinator-agent loop drives all ten LEX AI modes, where step briefs come from, and why the server owns the ordering, the gates and the error handling.
4 min readTool surfacesWhat each of the ten LEX AI mode surfaces exposes, the five tools present in every mode, and why a stale tool list returns a structured payload instead of an error.
4 min readAgents and promptsThe eleven slash commands, the agents each of the ten modes ships, and how the one canonical .github payload is translated for every supported coding tool.
3 min readMode switchingHow switch_to_mode swaps the visible tool surface in place across all ten modes, what decides the mode at boot, and how the stale-tool guard behaves.
3 min readOutputs and artifactsWhere each of the ten modes writes its files, which artifacts get committed and pushed, and why the contract, plans and technical map outlive a single chat session.
12 min readFiles and questionsThe four tools every LEX AI mode shares: reading customer data files as markdown, rasterizing PDF pages with no text layer, and putting a question to the user with the answer's origin recorded.
3 min readUse it
LEX AI commandsReference for the LEX AI command line: lex setup-with-ai, ai-dashboard, ai-verify, ai-update, ai-faq and ai-issue-report, with their flags and what each one actually touches.
3 min readStarter promptsHow to open a LEX AI run: the eleven slash commands, what a good outcome-focused description contains, and worked examples per mode.
3 min readDuring a runWhat a LEX AI run looks like while it is happening: the four workflow shapes, when to answer or intervene, what not to touch, and how finalize behaves.
3 min readUpdatesHow to move a project to a newer LEX AI build: what lex ai-update migrates, when re-running setup is actually needed, and how to reload each of the seven supported environments.
3 min readHandoffWhy a LEX AI run survives leaving the chat session: the durable artifacts each mode writes, the read-only status tools, and how to resume in every mode.
3 min readParallel workRunning more than one LEX AI chat on the same project: when you get your own checkout, when you are asked to wait, and why.
5 min readOperations
Git and GitHubWhich of the ten modes touch git and how, forward-style branch naming and commit rhythm, deterministic git repair, and how credentials are kept out of the repository history.
4 min readTroubleshootingSymptom-by-symptom fixes for stale tool lists, wrong project or mode, git failures, refused interview answers, blocked test runs, rejected completions, unreachable deployment steps, and MVP caps.
4 min readWhat we can diagnoseThe signals available when a run goes wrong: structured error payloads, per-mode status tools, mode-switch diffs, on-disk run records, analytics events, and the redacted issue-report bundle.
4 min readFAQShort answers to the most common LEX AI questions: getting started, choosing among the ten modes, supported coding tools, model choice, git behaviour, reading data files, resuming, and updating.
4 min readModel compatibilityHow the LEX Compatibility Score rates models against LEX AI: the probe and benchmark halves, the twenty-three fidelity checks, the four tiers and hard gates, and where to read current scores.
4 min readLEX AI OverviewWhat LEX AI is, the ten workflow modes it exposes, which one to choose for a given job, and how to get started with lex setup-with-ai.
2 min readLEX AI Execution ModelHow the coordinator-agent loop runs, the universal rules every mode follows, the loop shape per mode, and where the server enforces its gates.
2 min readLEX AI Behavior MapThe routes a LEX AI session actually takes, from starting with a rough idea through new builds, edits, documentation, tests, input changes, and deployment.
3 min readLEX AI Architecture SnapshotThe components of the installed LEX AI package: the unified server, ten mode surfaces, the payload model across seven environments, resilience, and persistence.
2 min readLEX AI Product WelcomeThe LEX AI product promise, a three-step quickstart, the ten dashboard mode cards and their keys, and the supported coding environments.
2 min readLEX AI Docs Hub: Setup and NavigationHow the docs hub is organised, the six-step setup flow from lex setup-with-ai to picking a mode, and the intent-first routing principle.
1 min readLEX AI Docs Hub: Mode ReferenceThe ten canonical LEX AI mode keys, intent-to-mode selection rules, the kickstart and finalize tool for each mode, and how the non-step-loop shapes differ.
2 min readLEX AI Command ReferenceThe five lex ai-* commands and their purpose, the hyphenated setup command, why ai-verify runs silently, and what the issue-report bundle contains.
2 min readLEX AI Operations and TroubleshootingWhat each mode does to your repository, the mandatory halt-on-error procedure, stale-tool recovery, the secrets rule, and what support can diagnose.
2 min readLEX AI Artifacts and HandoffThe files LEX AI writes into a downstream project, the consolidated report per mode, and what to include when handing a run over.
2 min readLEX AI Missing Knowledge RoadmapWhat the public LEX AI documentation still lacks, which questions have since been settled, and how to close a gap without reintroducing stale facts.
2 min readLEX Docs Topic Map for LEX AI UsersHow the shipped docs/lex_topics reference is organised, how to retrieve from it efficiently, and why the shipped topics override a model's prior knowledge.
2 min readLEX AI Analytics Guidelines SummaryThe analytics contract in summary: transport, backend architecture, safety rules, run identity, the canonical event envelope, and current event coverage.
2 min read