Visual Memory MCP

Local visual UI cache for AI agents using perceptual hashing, CLIP, and 3D spatial grounding.

Connector by putervision · GitHub account verified by the MCP Registry

IndexedLicense unknownLocal (stdio)★ 39

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/putervision-vision-memory-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Local visual UI cache for AI agents using perceptual hashing, CLIP, and 3D spatial grounding.

Use cases: agent-memory, testing

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools: 19 read · 13 write · 3 delete
Secrets: None asked for
Install scripts: None found
Runs as: Node.js package

Tools by what they do 35

Read from the source code; the running server may list different tools.

Read 19 · Look things up without changing anything.

app_version
batch_analyze_screenshots
compare_states
compare_video_trajectories
diff_visual_snapshots
export_snapshot
export_trajectories
get_metrics
get_navigation_paths
get_session_context
get_version
get_video_timeline

Show 7 more tools

get_visual_diff
list_visual_specs
predict_next_action
recall_memory
search_video_memory
verify_visual_spec
wait_for_visual_state

Write 13 · Create, change, send or run things.

analyze_screenshot
create_evidence_pack
create_visual_blocker
export_joint_trajectories
export_visual_trajectories
ingest_video
manage_video
manage_visual_spec
record_outcome
restore_snapshot
save_visual_snapshot
set_visual_spec

Show 1 more tools

undo_last_visual_mutation

Delete 3 · Delete, drop, revoke or wipe things.

forget_state
manage_snapshot
undo_visual_mutation

Files it touches

/usr/local/opt/nvm/nvm.sh
Your home directory (~)
Any path the agent passes to its tools

Tools (35)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

analyze_screenshotAnalyze & Cache Screenshot
Ingest screenshot(s) via base64 or file path, check the visual state cache, and return state details. On cache miss, generates perceptual hashes (dHash/aHash), CLIP embeddings, and persists a new visual state entry. Use this tool AFTER capturing a screenshot and BEFORE invoking vision LLMs to avoid redundant token spend. Use analyze_screenshot instead of recall_memory when ingesting, indexing, and caching a visual capture rather than performing read-only search over historical states. For batch ingestion, pass an `items` array instead of a single screenshot/file_path. Returns visual state ID,…
app_version[Deprecated] app_version
[DEPRECATED in vision-memory-mcp v1.0] Legacy alias for get_session_context. Please migrate to get_session_context.
batch_analyze_screenshots[Deprecated] batch_analyze_screenshots
[DEPRECATED in vision-memory-mcp v1.0] Legacy alias for analyze_screenshot. Please migrate to analyze_screenshot.
compare_statesCompare Visual States or Video Trajectoriesread-only
Compare two visual states structurally (dHash, CLIP vector, JSON diff, layout delta) or two video trajectories (keyframe similarity, divergence point). Provide state_a_id/state_b_id for state comparison, or video_a_id/video_b_id for video trajectory comparison. Use compare_states instead of manage_snapshot when computing direct visual/structural deltas between two states rather than saving or restoring checkpoints. Returns Hamming hash distance, cosine vector similarity, structural layout diff, and layout change flag.
compare_video_trajectories[Deprecated] compare_video_trajectories
[DEPRECATED in vision-memory-mcp v1.0] Legacy alias for compare_states. Please migrate to compare_states.
create_evidence_packCreate Evidence Pack
Package keyframe IDs, dHash/CLIP fingerprints, OCR snippets, and linked state-memory node IDs into an immutable, cryptographically hashable evidence pack for compliance and audit trails. Use create_evidence_pack instead of export_trajectories when generating tamper-proof cryptographic audit proofs for compliance rather than dumping training trajectories. Returns cryptographic evidence pack with SHA-256 payload hash, keyframe fingerprints, and state-memory links.
create_visual_blocker[Deprecated] create_visual_blocker
[DEPRECATED in vision-memory-mcp v1.0] Legacy alias for record_outcome. Please migrate to record_outcome.
diff_visual_snapshots[Deprecated] diff_visual_snapshots
[DEPRECATED in vision-memory-mcp v1.0] Legacy alias for manage_snapshot. Please migrate to manage_snapshot.
export_joint_trajectories[Deprecated] export_joint_trajectories
[DEPRECATED in vision-memory-mcp v1.0] Legacy alias for export_trajectories. Please migrate to export_trajectories.
export_snapshot[Deprecated] export_snapshot
[DEPRECATED in vision-memory-mcp v1.0] Legacy alias for manage_snapshot. Please migrate to manage_snapshot.
export_trajectoriesExport Visual Trajectoriesread-only
Export visual state transition trajectories (formats: json, llava, qwen2_vl, joint). Formats: "json" (raw state steps), "llava" / "qwen2_vl" (VLM fine-tuning datasets), "joint" (interleaved workflow events correlated by session/trace ID for state-memory-mcp). Use export_trajectories instead of create_evidence_pack when exporting training data or cross-server event logs rather than cryptographic compliance packs. Returns exported trajectory array, formatted VLM training records, or joint event stream.
export_visual_trajectories[Deprecated] export_visual_trajectories
[DEPRECATED in vision-memory-mcp v1.0] Legacy alias for export_trajectories. Please migrate to export_trajectories.
forget_stateForget Visual Statecan change or delete data
Purge a specific visual state, its vector embeddings, and perceptual hashes from storage for privacy or memory reset. Use forget_state instead of undo_visual_mutation when permanently purging specific sensitive or obsolete states by ID rather than reverting the most recent action. Returns purge confirmation and deleted state ID.
get_metrics[Deprecated] get_metrics
[DEPRECATED in vision-memory-mcp v1.0] Legacy alias for get_session_context. Please migrate to get_session_context.
get_navigation_pathsFind UI Navigation Pathread-only
Trace historical pathways from current state to a target state or state matching description via BFS over the transition graph. Use get_navigation_paths instead of predict_next_action when planning multi-step navigation routes across known states rather than choosing the immediate next interaction. Returns shortest path state sequence, intermediate actions, and cumulative transition confidence.

Show 20 more tools

get_session_contextGet Session Contextread-only
Fetch aggregated visual context: recent states, frequently accessed states, active transitions, and memory stats. Call this at session start to orient before performing UI actions. Use get_session_context instead of recall_memory when initializing session awareness rather than searching for specific visual targets. Returns recent states list, frequent states, active transitions, cache hit telemetry, and database sizing.
get_version[Deprecated] get_version
[DEPRECATED in vision-memory-mcp v1.0] Legacy alias for get_session_context. Please migrate to get_session_context.
get_video_timeline[Deprecated] get_video_timeline
[DEPRECATED in vision-memory-mcp v1.0] Legacy alias for manage_video. Please migrate to manage_video.
get_visual_diff[Deprecated] get_visual_diff
[DEPRECATED in vision-memory-mcp v1.0] Legacy alias for compare_states. Please migrate to compare_states.
ingest_video[Deprecated] ingest_video
[DEPRECATED in vision-memory-mcp v1.0] Legacy alias for manage_video. Please migrate to manage_video.
list_visual_specs[Deprecated] list_visual_specs
[DEPRECATED in vision-memory-mcp v1.0] Legacy alias for manage_visual_spec. Please migrate to manage_visual_spec.
manage_snapshotManage Visual Snapshotscan change or delete data
Manage visual memory snapshots (actions: save, diff, export, restore). "save" creates a named checkpoint of current states; "diff" compares two snapshots for visual drift/regression; "export" serializes a snapshot to a portable JSON archive; "restore" imports a snapshot from an exported archive. Use manage_snapshot instead of undo_visual_mutation when creating or restoring named point-in-time visual checkpoints rather than rolling back the immediate previous mutation. Returns snapshot metadata, comparison diff, export archive, or restore confirmation.
manage_videoManage Video Memory
Manage WebM, MP4, and GIF video recordings in visual memory (actions: ingest, search, timeline). "ingest" extracts keyframes, deduplicates, and builds sequence transitions; "search" queries stored video recordings by keyword/category/tags; "timeline" retrieves the chronological keyframe timeline for a specific video_id. Use manage_video instead of analyze_screenshot when processing full video recordings and extracting temporal keyframes rather than single screenshots. Returns ingested video metadata, keyframe indices, search matches, or timeline sequence.
manage_visual_specManage Visual Specs
Manage Visual Spec baseline contracts for visual SDD (actions: set, verify, list). "set" registers a screenshot or design mockup as baseline; "verify" tests a live UI screenshot against a baseline; "list" returns all registered visual specs. Use manage_visual_spec instead of compare_states when verifying UI against approved design contracts rather than ad-hoc state comparisons. Returns baseline registration confirmation, visual verification score, or registered spec list.
predict_next_actionPredict Next UI Actionread-only
Predict the best next UI action from the current visual state based on transition success rates, goal alignment, and grounded AX tree element targeting. Use predict_next_action instead of get_navigation_paths when selecting the immediate next optimal UI interaction rather than computing full path routes. Returns recommended action, target element selector, coordinates, and confidence score.
recall_memorySearch Visual Memoryread-only
Search visual state memory by screenshot image, text query, or accessibility tree. Read-only — never creates or modifies states. Use recall_memory instead of analyze_screenshot when searching historical states by visual similarity or semantic text query without persisting new database records. Returns matching visual state records, similarity scores, layout descriptions, and grounded elements.
record_outcomeRecord Action Outcome
Log an action transition between two visual states or log a visual blocker (action_type: click, type, navigate, scroll, custom, blocker). Call this after every UI interaction to update transition statistics and success rates. When action_type is "blocker", generates a structured visual blocker payload for state-memory-mcp instead of recording a transition (from_state_id becomes the visual_state_id of the blocker). Use record_outcome instead of predict_next_action when persisting actual interaction results rather than predicting recommended next steps. Returns transition record, updated edge w…
restore_snapshot[Deprecated] restore_snapshot
[DEPRECATED in vision-memory-mcp v1.0] Legacy alias for manage_snapshot. Please migrate to manage_snapshot.
save_visual_snapshot[Deprecated] save_visual_snapshot
[DEPRECATED in vision-memory-mcp v1.0] Legacy alias for manage_snapshot. Please migrate to manage_snapshot.
search_video_memory[Deprecated] search_video_memory
[DEPRECATED in vision-memory-mcp v1.0] Legacy alias for manage_video. Please migrate to manage_video.
set_visual_spec[Deprecated] set_visual_spec
[DEPRECATED in vision-memory-mcp v1.0] Legacy alias for manage_visual_spec. Please migrate to manage_visual_spec.
undo_last_visual_mutation[Deprecated] undo_last_visual_mutation
[DEPRECATED in vision-memory-mcp v1.0] Legacy alias for undo_visual_mutation. Please migrate to undo_visual_mutation.
undo_visual_mutationUndo Visual Mutationcan change or delete data
Revert the most recent visual state ingestion or transition edge addition on the current git branch (types: state, transition, any). Use undo_visual_mutation instead of manage_snapshot when rolling back the immediate previous mutation rather than restoring an entire snapshot. Returns reverted mutation type, deleted state/edge ID, and rollback status.
verify_visual_spec[Deprecated] verify_visual_spec
[DEPRECATED in vision-memory-mcp v1.0] Legacy alias for manage_visual_spec. Please migrate to manage_visual_spec.
wait_for_visual_stateWait For Visual Stateread-only
Poll for a target visual state ID until it exists in memory or timeout occurs. Use this to avoid agent spin-loops when waiting for asynchronous screenshots. Use wait_for_visual_state instead of get_session_context when synchronizing with an asynchronous capture rather than inspecting existing memory state. Returns target visual state record or timeout error.