mcpserver.lol
registry/memi
Connection check local install

memi

Memi is the design layer for agentic AI.

Tools 50
GitHub stars 40
Installs / wk 276
Licence MIT
Transport stdio
Last checked never

Tools & capabilities

50 tools

Read from the published package source — this server runs locally, so there is no endpoint to query. Names are taken from the code, not observed at runtime, and descriptions are often absent.

analyze_design from source
audit_interface_craft from source
Audit interface design craft from local app-quality evidence or a screenshot artifact. Returns: InterfaceCraftReport JSON \u2014 score, critique, dimensions, findings, topOpportun…
audit_ux_tenets_traps from source
capture_screenshot from source
Capture a screenshot of a Figma node (or the current page) as image data. Prereq: bridge + plugin connected (check_bridge_health); node IDs from get_selection or get_page_tree. Re…
check_bridge_health from source
Check health of the Figma WebSocket bridge. Works with no plugin connected; never throws. Returns: { status:
check_skill_compliance from source
compose from source
Run the agent orchestrator on a natural-language design intent \u2014 classifies, builds a multi-step plan, executes it. Prereq: Figma bridge only for Figma-touching intents. Retu…
create_spec from source
Create or overwrite a spec in the registry (Zod-validated). Same-name specs are silently overwritten \u2014 check get_specs first. Returns: \
design_doc from source
design_systems_context from source
Normalize design-systems-mcp corpus data into compact, deterministic agent context. This read-only tool validates caller-supplied JSON and never fetches URLs, reads files, writes…
diagnose_app_quality from source
Diagnose UI quality for an existing shadcn/Tailwind app from code or a public URL. Returns on success: App-quality diagnosis V2 with scores, issues, evidence locations, affected f…
generate_code from source
generate_health_report from source
get_ai_usage from source
AI token usage and estimated cost for this MCP session (in-memory tracker; never throws; unknown when provider pricing is not configured). Returns: { calls, inputTokens, outputTok…
get_page_tree from source
Get the hierarchical node tree of the current Figma file. Prereq: bridge + plugin connected. Returns: array of pages { id, name, type:
get_registry_item from source
Return one shadcn registry-item.json-compatible item from the workspace. Returns: files, targets, dependencies, cssVars, and Atomic Design metadata. Errors: isError if the item is…
get_research from source
Load and return the project\
get_selection from source
get_shadcn_registry from source
Build a shadcn registry.json-compatible index from the workspace (component specs; tokens map to a registry:theme item when present). Returns: { $schema, name, homepage, items[] }…
get_spec from source
Fetch the full body of one spec by name. Returns: full spec JSON \u2014 ComponentSpec: atomicLevel, props, variants, composesSpecs, codeConnect, WCAG fields; PageSpec: sections, m…
get_specs from source
List all saved specs (cheap summary operation). Returns: [{ name, type:
get_tokens from source
Get design tokens from the local registry, optionally filtered. Prereq: none \u2014 local read; run pull_design_system if empty. Returns: [{ name, type:
measure_text from source
mermaid_jam_export from source
Write Mermaid Jam-ready FigJam source artifacts from research or a simulation run. This is source + open friendly: it writes .mmd/.md files under .memoire/mermaid-jam and returns…
plan_ui_fixes from source
Build a dry-run UI fix plan from diagnosis evidence and app graph data. Returns on success: { patches[], summary, caveats[] } where every patch includes risk, confidence, affected…
prepare_apple_design_brief from source
Prepare a compact, local-first Apple-platform design and verification brief. Returns: mission, skill triggers, availability policy, Xcode preflight, design checks, build/test comm…
prepare_design_agent_brief from source
pull_design_system from source
Pull the full design system from Figma (tokens, components, styles) into the local registry. Prereq: Figma bridge running + plugin connected \u2014 verify with check_bridge_health…
pull_design_system_rest from source
Pull the design system from Figma via REST API \u2014 no plugin or bridge required. Prereq: FIGMA_TOKEN and FIGMA_FILE_KEY env vars. Returns: { tokens, components, styles, lastSyn…
research_design_package from source
Preview a research-backed vibe design package from ResearchStore V2 plus an optional simulation run. Returns on success: { package } with brief, Atomic Design specs, evidence ids,…
research_generate_specs from source
Write research-backed Atomic Design specs generated from ResearchStore V2. Prerequisites: Call research_design_package first to preview. This tool requires approved=true to make t…
run_audit from source
Run a deterministic design-system audit (WCAG contrast, token completeness, spec accessibility) and return structured findings. Prereq: none \u2014 token/spec level, no Figma, no…
scaffold_agent_design_files from source
Preview or write a spec-first Atomic Design scaffold for agent-created files. Default is non-mutating: approved=false returns a dry-run JSON plan with the exact spec path, guardra…
scaffold_swiftui_files from source
Preview or write a deterministic SwiftUI feature scaffold. Default approved=false is non-mutating and returns every planned path and file body: Memi iOS spec, SwiftUI view, option…
simulation_compare from source
Compare completed simulation runs by adoption, confidence, evidence coverage, risk, and cost.
simulation_costs from source
Summarize token and cost usage for a simulation run.
simulation_export_spec from source
Convert a simulation report into a product-spec impact artifact that agents can paste into specs or handoff docs.
simulation_generate_agents from source
Generate a 20-60 agent model-swarm cohort from Memoire research evidence without starting a run.
simulation_interview from source
Interview a simulated product stakeholder from a completed local or model-swarm run.
simulation_list_runs from source
List persisted simulation runs with lightweight summaries. Use this to discover runIds for simulation_status, simulation_stream, simulation_transcript, simulation_costs, simulation…
simulation_models from source
List Codex-first model profiles available to Memoire model-swarm simulations. Live model execution is opt-in; unavailable providers automatically fall back to deterministic clean-r…
simulation_plan from source
Create a clean-room product simulation scenario from Memoire research evidence. Prereq: research/store.v2.json or a ResearchStore JSON string. Local TypeScript simulation core onl…
simulation_report from source
Export a simulation report with recommendations, risks, assumptions, events, interviews, and evidenceFindingIds.
simulation_run from source
Run a prepared local or model-swarm product simulation scenario. Prerequisites: Call simulation_plan first and pass the returned scenario.id. Returns on success: SimulationRun wi…
simulation_run_matrix from source
Plan and run multiple model-swarm hypotheses, then compare outcomes for product-spec decision work.
simulation_status from source
Read a local simulation run status from .memoire/simulations/runs.
simulation_stream from source
Read persisted simulation events in stream order. Paginated \u2014 use offset/limit to page through long runs instead of materializing the full event log.
simulation_transcript from source
Read model-swarm transcript memory for a run.
sync_design_tokens from source
Map registry tokens to a Tailwind theme.extend object; optionally import a W3C DTCG token file first. Prereq: tokens in the registry (pull_design_system first) \u2014 or pass dtcg…
update_token from source