Memory
This is a persistent memory layer for AI assistants that goes beyond vector search. It gives you 25 tools including semantic search, identity tracking, contradiction detection, and knowledge graph traversal. The `velixar_context` tool synthesizes workspace briefings in one call, while `velixar_distill` extracts durable memories from sessions with automatic deduplication. It ships with 16 workflow prompts for orientation and conflict resolution, plus 5 live resources that inject recent and relevant memories into context without explicit tool calls. Memories are workspace-scoped (via git root, env var, or config file), and it includes circuit breakers and cache fallback for reliability. Reach for this when you need your assistant to remember preferences, track evolving beliefs, or maintain continuity across sessions without rebuilding context manually.
- GitHub stars
- 1
- tools
- 25
- auth
- Secret needed
- transport
- STDIO
- env var
- 1
- last updated
- Feb 28, 2026
Tools
25 toolsPublic tool metadata for what this MCP can expose to an agent.
velixar_storeStore a memory with tags, tier, and type
Store a memory with tags, tier, and type
No parameter schema in public metadata yet.
velixar_searchSemantic search across all memories
Semantic search across all memories
No parameter schema in public metadata yet.
velixar_listBrowse with pagination and filtering
Browse with pagination and filtering
No parameter schema in public metadata yet.
velixar_updateEdit content or tags on an existing memory
Edit content or tags on an existing memory
No parameter schema in public metadata yet.
velixar_deleteRemove a memory
Remove a memory
No parameter schema in public metadata yet.
velixar_contextSynthesized workspace briefing — orientation in one call
Synthesized workspace briefing — orientation in one call
No parameter schema in public metadata yet.
velixar_identityGet, store, or update the user's profile, preferences, and expertise
Get, store, or update the user's profile, preferences, and expertise
No parameter schema in public metadata yet.
velixar_contradictionsSurface conflicting facts or beliefs with resolution guidance
Surface conflicting facts or beliefs with resolution guidance
No parameter schema in public metadata yet.
velixar_timelineHow a topic or belief evolved over time
How a topic or belief evolved over time
No parameter schema in public metadata yet.
velixar_patternsRecurring problem/solution motifs across your history
Recurring problem/solution motifs across your history
No parameter schema in public metadata yet.
velixar_inspectDeep inspection of a specific memory with full provenance chain
Deep inspection of a specific memory with full provenance chain
No parameter schema in public metadata yet.
velixar_graph_traverseWalk entity relationships — "what connects to X?"
Walk entity relationships — "what connects to X?"
No parameter schema in public metadata yet.
velixar_distillExtract durable memories from session content with deduplication
Extract durable memories from session content with deduplication
No parameter schema in public metadata yet.
velixar_session_saveSave a session summary for later recall
Save a session summary for later recall
No parameter schema in public metadata yet.
velixar_session_recallRestore context from a previous session
Restore context from a previous session
No parameter schema in public metadata yet.
velixar_batch_storeStore up to 20 memories in one call
Store up to 20 memories in one call
No parameter schema in public metadata yet.
velixar_batch_searchRun up to 10 search queries simultaneously
Run up to 10 search queries simultaneously
No parameter schema in public metadata yet.
velixar_consolidateMerge related memories into a single durable memory
Merge related memories into a single durable memory
No parameter schema in public metadata yet.
velixar_retagBulk update tags across memories
Bulk update tags across memories
No parameter schema in public metadata yet.
velixar_exportExport memories as JSON or Markdown, optionally with graph data
Export memories as JSON or Markdown, optionally with graph data
No parameter schema in public metadata yet.
velixar_importBulk import from JSON, Markdown, Notion, or Obsidian exports
Bulk import from JSON, Markdown, Notion, or Obsidian exports
No parameter schema in public metadata yet.
velixar_healthBackend connectivity, latency, workspace status
Backend connectivity, latency, workspace status
No parameter schema in public metadata yet.
velixar_debugCache state, circuit breaker, API timings
Cache state, circuit breaker, API timings
No parameter schema in public metadata yet.
velixar_capabilitiesFeature list, tool inventory, resource URIs
Feature list, tool inventory, resource URIs
No parameter schema in public metadata yet.
velixar_securityGet or set content scanning mode
Get or set content scanning mode
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
VELIXAR_API_KEY*secretYour Velixar API key (get one free at velixarai.com)
Readme
Velixar MCP Server
The 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.
Works with any Model Context Protocol client: Claude Desktop, Kiro, Cursor, Windsurf, Continue.dev, or custom hosts.
Why This Exists
Every 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:
Details
- Repository
- github.com/velixarai/velixar-mcp-server
- Categories
- AI & LLM Tools, Search & Web Crawling
- Package
velixar-mcp-server- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Project Memory Mcpkaaustubh/project-memory-mcpPersistent memory for AI coding agents — past bugs, decisions, and your corrections, in your repo.1stars
Memory OS AIromainsantoli-web/memory-os-aiAdaptive memory for AI agents — FAISS search, chat extraction, cross-project linking1stars
Agent Arena Registryagentarena/agent-arenaOn-chain ERC-8004 agent registry. Search, register, and check reputation across 16 chains.0stars
Gemini Mcpchrischall/gemini-mcpGenerate and edit images with Google Gemini (Nano Banana / Nano Banana Pro) image models.0stars
Aibooma - AI Agent Registrysairaj-reddy/aiboomaAI agent registry — search, discover, register, and connect agents via MCP.0stars