Persistent memory for AI assistants. Store, search, and recall across sessions.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
The first cognitive memory server for AI assistants. Not a vector database wrapper β a full reasoning layer that gives your AI persistent memory, a knowledge graph, identity awareness, contradiction detection, and belief tracking across every session.
Works with any Model Context Protocol client: Claude Desktop, Kiro, Cursor, Windsurf, Continue.dev, or custom hosts.
Every AI assistant starts from zero every conversation. Velixar fixes that β but not by just storing and retrieving text. The MCP server gives your assistant the ability to:
40 tools. 5 live resources. 19 workflow prompts. One npm install.
Get an API key at velixarai.com/settings/api-keys, then add to your MCP client:
Restart your assistant. Done.
| Tool | What it does |
|---|---|
velixar_store | Store a memory with tags, tier, and type |
velixar_search | Semantic search across all memories |
velixar_list | Browse with pagination and filtering |
velixar_update | Edit content or tags on an existing memory |
velixar_delete | Remove a memory |
| Tool | What it does |
|---|---|
velixar_context | Synthesized workspace briefing β orientation in one call |
velixar_identity | Get, store, or update the user's profile, preferences, and expertise |
velixar_contradictions | Surface conflicting facts or beliefs with resolution guidance |
velixar_timeline | How a topic or belief evolved over time |
velixar_patterns | Recurring problem/solution motifs across your history |
velixar_inspect | Deep inspection of a specific memory with full provenance chain |
velixar_graph_traverse | Walk entity relationships β "what connects to X?" |
velixar_distill | Extract durable memories from session content with deduplication |
| Tool | What it does |
|---|---|
velixar_session_save | Save a session summary for later recall |
velixar_session_recall | Restore context from a previous session |
velixar_batch_store | Store up to 20 memories in one call |
velixar_batch_search | Run up to 10 search queries simultaneously |
velixar_consolidate | Merge related memories into a single durable memory |
velixar_retag | Bulk update tags across memories |
velixar_export | Export memories as JSON or Markdown, optionally with graph data |
velixar_import | Bulk import from JSON, Markdown, Notion, or Obsidian exports |
| Tool | What it does |
|---|---|
velixar_health | Backend connectivity, latency, workspace status |
velixar_debug | Cache state, circuit breaker, API timings |
velixar_capabilities | Feature list, tool inventory, resource URIs |
velixar_security | Get or set content scanning mode |
Resources are injected into your assistant's context automatically β no tool call needed.
| Resource | What it provides |
|---|---|
velixar://system/constitution | Behavioral rules and cognitive modes for the assistant |
velixar://identity/current | Your persistent user profile |
velixar://memories/recent | Most recent memories (compact) |
velixar://memories/relevant | Contextually relevant memories based on current activity |
velixar://domains/{domain}/shadow_graph | Knowledge graph view for a specific domain |
16 built-in prompts that guide multi-step reasoning workflows:
Memories are scoped to workspaces. Your personal project never bleeds into work.
| Priority | Source | How |
|---|---|---|
| 1 | VELIXAR_WORKSPACE_ID env var | Explicit |
| 2 | .velixar.json in project root | { "workspace_id": "my-project" } |
| 3 | Git root directory name | Automatic |
| Host | Tools | Resources | Prompts |
|---|---|---|---|
| Kiro CLI | β | β | β |
| Claude Desktop | β | β | β |
| Cursor | β | β οΈ | β |
| Windsurf | β | β οΈ | β |
| Continue.dev | β | β | β |
When a host doesn't support resources or prompts, the server degrades gracefully β all tools still work independently.
| Variable | Required | Description |
|---|---|---|
VELIXAR_API_KEY | Yes | Your API key (starts with vlx_) |
VELIXAR_WORKSPACE_ID | No | Explicit workspace scope |
VELIXAR_API_URL | No | Custom API endpoint |
VELIXAR_USER_ID | No | Explicit end-user identity. Leave unset (recommended): the API derives scope from your key β you see your own memories, same as the dashboard. Set it only when one key serves multiple named end users |
VELIXAR_DEBUG | No | true for verbose logging |
VELIXAR_LOG_FORMAT | No | json for structured Datadog/CloudWatch logging |
VELIXAR_HEALTH_PORT | No | Port for HTTP health check endpoint |
Use Velixar directly from code:
POST /webhook/ci β generic CI event ingestionMIT
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/memory-6)<a href="https://allmcps.com/mcp/memory-6"><img src="https://allmcps.com/api/badge/memory-6?style=directory" alt="Memory on AllMCPs" /></a>