How do I install vision-memory-mcp?

Its own README gives this command: npm install -g @putervision/vision-memory-mcp. Run it where your MCP client can launch the server, and check the README for any settings it asks for.

Is vision-memory-mcp official and is it maintained?

We found nothing naming it as a vendor’s official server. Its repository has 39 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-10-08.

What licence does vision-memory-mcp use?

The repository declares the NOASSERTION licence.

InfratoApp / Resources / MCP servers / vision-memory-mcp

vision-memory-mcp

vision-memory-mcp is an MCP server, listed under memory & vectors. Its repository has 39 GitHub stars and is licensed under NOASSERTION; we last read it on 2026-10-24.

Stores persistent visual caches for LLM-driven software development using perceptual hashing, vector search, and AX trees to reduce token overhead and prevent visual hallucinations.

Install

Read from vision-memory-mcp’s own README, close to verbatim -- not written by us, and not guessed.

npm install -g @putervision/vision-memory-mcp

View in vision-memory-mcp’s own README ↗

What it reaches, and what it needs

Reaches

○ not recognised

Credential

○ none found

Maintenance

Stars

State

listed

Licence

NOASSERTION

From the repository

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.

View on GitHub ↗2026-10-24

What vision-memory-mcp can do

15 tools documented in its README. An AI client calls these by name.

analyze_screenshot: L1/L2 perceptual dHash & AX tree parsing, single/batch
recall_memory: text & image semantic vector search
get_session_context: aggregated cache hit metrics, recent states, and sub-1KB compact_slice export
predict_next_action: deterministic CSS selectors & bounding coordinates
record_outcome: UI action transitions & visual blockers
get_navigation_paths: BFS shortest-path planner
wait_for_visual_state: polling for target UI state
manage_video: WebM/MP4 keyframe ingestion, timeline search
compare_states: visual layout diffs & video trajectory comparison
create_evidence_pack: cryptographic audit proof linking video keyframes to state-memory DAGs
export_trajectories: multimodal fine-tuning datasets
manage_visual_spec: mockup baseline contracts & regression checks
manage_snapshot: checkpoints, export, restore
undo_visual_mutation: revert state ingestion
forget_state: privacy & PII purging

Read from the README; names are kept only if the README contains them.