{
  "markdown": "# Velixar MCP Server\n\n[![npm](https://img.shields.io/npm/v/velixar-mcp-server)](https://www.npmjs.com/package/velixar-mcp-server)\n[![License](https://img.shields.io/github/license/VelixarAi/velixar-mcp-server)](LICENSE)\n\nThe first cognitive memory server for AI assistants. Not a vector database wrapper — a full reasoning layer that gives your AI persistent memory, a knowledge graph, identity awareness, contradiction detection, and belief tracking across every session.\n\nWorks with any [Model Context Protocol](https://modelcontextprotocol.io) client: Claude Desktop, Kiro, Cursor, Windsurf, Continue.dev, or custom hosts.\n\n## Why This Exists\n\nEvery AI assistant starts from zero every conversation. Velixar fixes that — but not by just storing and retrieving text. The MCP server gives your assistant the ability to:\n\n- **Orient itself** in a workspace with a single call — no manual context assembly\n- **Track how beliefs evolve** over time and surface when they contradict\n- **Build and traverse a knowledge graph** of entities and relationships it discovers\n- **Maintain a persistent identity model** of who you are, what you prefer, and how you work\n- **Distill sessions** into durable memories automatically, with deduplication\n- **Import and export** your entire memory corpus for backup or migration\n\n40 tools. 5 live resources. 19 workflow prompts. One `npm install`.\n\n## Quick Start\n\n```bash\nnpm install -g velixar-mcp-server\n```\n\nGet an API key at [velixarai.com/settings/api-keys](https://velixarai.com/settings/api-keys), then add to your MCP client:\n\n```json\n{\n  \"mcpServers\": {\n    \"velixar\": {\n      \"command\": \"velixar-mcp-server\",\n      \"env\": {\n        \"VELIXAR_API_KEY\": \"vlx_your_key_here\"\n      }\n    }\n  }\n}\n```\n\nRestart your assistant. Done.\n\n## Tool Surface\n\n### Memory\n\n| Tool | What it does |\n|------|-------------|\n| `velixar_store` | Store a memory with tags, tier, and type |\n| `velixar_search` | Semantic search across all memories |\n| `velixar_list` | Browse with pagination and filtering |\n| `velixar_update` | Edit content or tags on an existing memory |\n| `velixar_delete` | Remove a memory |\n\n### Cognitive\n\n| Tool | What it does |\n|------|-------------|\n| `velixar_context` | Synthesized workspace briefing — orientation in one call |\n| `velixar_identity` | Get, store, or update the user's profile, preferences, and expertise |\n| `velixar_contradictions` | Surface conflicting facts or beliefs with resolution guidance |\n| `velixar_timeline` | How a topic or belief evolved over time |\n| `velixar_patterns` | Recurring problem/solution motifs across your history |\n| `velixar_inspect` | Deep inspection of a specific memory with full provenance chain |\n| `velixar_graph_traverse` | Walk entity relationships — \"what connects to X?\" |\n| `velixar_distill` | Extract durable memories from session content with deduplication |\n\n### Lifecycle\n\n| Tool | What it does |\n|------|-------------|\n| `velixar_session_save` | Save a session summary for later recall |\n| `velixar_session_recall` | Restore context from a previous session |\n| `velixar_batch_store` | Store up to 20 memories in one call |\n| `velixar_batch_search` | Run up to 10 search queries simultaneously |\n| `velixar_consolidate` | Merge related memories into a single durable memory |\n| `velixar_retag` | Bulk update tags across memories |\n| `velixar_export` | Export memories as JSON or Markdown, optionally with graph data |\n| `velixar_import` | Bulk import from JSON, Markdown, Notion, or Obsidian exports |\n\n### System\n\n| Tool | What it does |\n|------|-------------|\n| `velixar_health` | Backend connectivity, latency, workspace status |\n| `velixar_debug` | Cache state, circuit breaker, API timings |\n| `velixar_capabilities` | Feature list, tool inventory, resource URIs |\n| `velixar_security` | Get or set content scanning mode |\n\n## Live Resources\n\nResources are injected into your assistant's context automatically — no tool call needed.\n\n| Resource | What it provides |\n|----------|-----------------|\n| `velixar://system/constitution` | Behavioral rules and cognitive modes for the assistant |\n| `velixar://identity/current` | Your persistent user profile |\n| `velixar://memories/recent` | Most recent memories (compact) |\n| `velixar://memories/relevant` | Contextually relevant memories based on current activity |\n| `velixar://domains/{domain}/shadow_graph` | Knowledge graph view for a specific domain |\n\n## Workflow Prompts\n\n16 built-in prompts that guide multi-step reasoning workflows:\n\n- **Orientation** — recall prior reasoning, build project context, profile an entity, orient-then-narrow\n- **Conflict** — resolve contradictions, identify knowledge gaps\n- **Continuity** — trace belief evolution, resume sessions, reconstruct decision paths\n- **Lifecycle** — distill sessions, consolidate topic memory, retag recent memories\n- **Identity** — summarize user identity, detect preference shifts, align response style\n- **Enterprise** — evaluate enterprise fit for a domain\n\n## Workspace Isolation\n\nMemories are scoped to workspaces. Your personal project never bleeds into work.\n\n| Priority | Source | How |\n|----------|--------|-----|\n| 1 | `VELIXAR_WORKSPACE_ID` env var | Explicit |\n| 2 | `.velixar.json` in project root | `{ \"workspace_id\": \"my-project\" }` |\n| 3 | Git root directory name | Automatic |\n\n## Host Compatibility\n\n| Host | Tools | Resources | Prompts |\n|------|-------|-----------|---------|\n| Kiro CLI | ✅ | ✅ | ✅ |\n| Claude Desktop | ✅ | ✅ | ✅ |\n| Cursor | ✅ | ⚠️ | — |\n| Windsurf | ✅ | ⚠️ | — |\n| Continue.dev | ✅ | ✅ | ✅ |\n\nWhen a host doesn't support resources or prompts, the server degrades gracefully — all tools still work independently.\n\n## Environment Variables\n\n| Variable | Required | Description |\n|----------|----------|-------------|\n| `VELIXAR_API_KEY` | Yes | Your API key (starts with `vlx_`) |\n| `VELIXAR_WORKSPACE_ID` | No | Explicit workspace scope |\n| `VELIXAR_API_URL` | No | Custom API endpoint |\n| `VELIXAR_USER_ID` | No | Explicit end-user identity. Leave unset (recommended): the API derives scope from your key — you see your own memories, same as the dashboard. Set it only when one key serves multiple named end users |\n| `VELIXAR_DEBUG` | No | `true` for verbose logging |\n| `VELIXAR_LOG_FORMAT` | No | `json` for structured Datadog/CloudWatch logging |\n| `VELIXAR_HEALTH_PORT` | No | Port for HTTP health check endpoint |\n\n## Reliability\n\n- Automatic retry with exponential backoff (3 attempts)\n- Circuit breaker — opens after sustained failures, auto-recovers\n- Cache fallback — serves stale data during outages rather than failing\n- Structured logging compatible with Datadog and CloudWatch\n\n## SDKs\n\nUse Velixar directly from code:\n\n- **JavaScript/TypeScript**: `npm install velixar` — [docs](https://docs.velixarai.com/sdks/javascript)\n- **Python**: `pip install velixar` — [docs](https://docs.velixarai.com/sdks/python)\n\n## CI/CD Integration\n\n- **GitHub Actions**: [velixar-memory-sync](github-actions/velixar-memory-sync) — distill PR merges into memories\n- **GitHub Actions**: [velixar-decision-capture](github-actions/velixar-decision-capture) — store issue resolutions as decisions\n- **Webhook**: `POST /webhook/ci` — generic CI event ingestion\n\n## License\n\nMIT\n",
  "bytes": 7235,
  "sha": "20bcaad2942b18b748c2655f7ed2e6502bee7c30a8779ce073be3e32d45f99f2",
  "repo_slug": "velixarai/velixar-mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_velixarai_memory_827ca6d9/readme"
}