novara-context
Uses Cloudflare Tunnel to expose the MCP server as a remote HTTP server with OAuth 2.1 for secure access.
Retrieves conventions for the Notion domain via the get_conventions tool.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@novara-context Remember that Stephen Ellington founded Novara in 2023."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
novara-context MCP Server
Persistent memory, identity, and context for Claude sessions — works with Claude Code, Claude.ai, and OpenClaw.
Tools
Tool | Description |
| Search the memory graph by query |
| Add or update an entity in the memory graph |
| Create a relation between two entities |
| Remove a specific observation from an entity |
| Returns SOUL.md + MEMORY.md context |
| Returns conventions by domain (notion, repo, linkedin, aws, etc.) |
| Store a decision with title, content, and tags |
| Full graph maintenance: dedupe, prune stale observations, promote new facts from daily logs |
Related MCP server: Fuzzy Memory MCP Server
Setup
npm install
npm run buildUsage in Claude Code (stdio)
Add to ~/.config/claude/claude_desktop_config.json:
{
"mcpServers": {
"novara-context": {
"command": "node",
"args": ["/path/to/novara-context/dist/index.js"]
}
}
}Usage as Remote Server (HTTP + Cloudflare Tunnel)
# Set required env vars
export MCP_MODE=http
export PORT=3099
export MCP_CLIENT_ID=novara-context-client
export MCP_CLIENT_SECRET=your-secret-here
# Start server
node dist/index.js &
# Expose via Cloudflare Tunnel
cloudflared tunnel --url http://localhost:3099The server implements full OAuth 2.1 with PKCE and Dynamic Client Registration (RFC 7591) for Claude.ai connector compatibility.
Environment Variables
Variable | Default | Description |
|
|
|
|
| HTTP port |
|
| OAuth client ID |
| — | OAuth client secret (required for HTTP mode) |
|
| Memory graph data file |
Memory Graph Format
The graph is stored as JSONL — one JSON object per line:
{"type":"entity","name":"Stephen Ellington","entityType":"Person","observations":["Founder of Novara"]}
{"type":"relation","from":"Stephen Ellington","to":"Novara","relationType":"FOUNDED"}Available Tools
8 toolsconsolidateB
Full memory graph maintenance: finds duplicate entities, promotes facts from daily memory files, prunes stale observations, and writes a maintenance report.
Inputs: dryRun.
forgetB
Remove a specific observation from an entity in the memory graph.
Inputs: entityName (required), observation (required).
get_conventionsB
Returns all Convention entities from the memory graph, optionally filtered by domain keyword.
Inputs: domain.
get_identityA
Returns the agent's identity (SOUL.md) and the first 3000 characters of MEMORY.md. Use at the start of a session to establish context.
Inputs: no named parameters.
linkA
Add a relation between two entities in the memory graph. Duplicate relations are skipped.
Inputs: to (required), from (required), relationType (required).
recallA
Search the memory graph for entities matching a query. Returns matching entities with their observations and relations.
Inputs: query (required), limit.
rememberA
Upsert an entity in the memory graph. If the entity already exists and upsert is true (default), observations are merged. If upsert is false, the entity is overwritten.
Inputs: name (required), entityType (required), observations (required), upsert.
store_decisionC
Store an important decision in the memory graph as a Decision entity with a dated observation.
Inputs: tags (required), title (required), content (required), importance.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool has a clearly distinct purpose: recall searches, remember upserts, link adds relations, forget removes observations, get_identity retrieves context, get_conventions fetches convention entities, store_decision stores decisions, and consolidate performs maintenance. No overlap.
Tool names mix single verbs (recall, remember, link, forget, consolidate) with verb_noun patterns (get_identity, get_conventions, store_decision). While readable, the lack of a uniform convention reduces predictability.
With 8 tools, the set covers core memory graph operations without being bloated. The count feels well-scoped for the server's purpose of managing an agent's memory.
The tool set covers basic CRUD (create/read/update via remember, recall, link) and maintenance (consolidate), but lacks a dedicated tool to delete entire entities or list all entities. Minor gaps like these could hinder agent workflows.
Maintenance
Related MCP Connectors
Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
Persistent memory for AI agents across Claude, ChatGPT and any MCP client.
Persistent, portable memory for AI assistants — your private memory graph, from any MCP client.
Persistent memory shared across Claude, ChatGPT, Grok and other MCP clients.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables Claude to remember information about users across conversations by storing and retrieving data as entities, relations, and observations in a persistent local knowledge graph.MIT
- AlicenseAqualityDmaintenanceEnables Claude to maintain persistent memory across conversations using a local knowledge graph with fuzzy search capabilities, allowing it to remember and recall information about users, relationships, and context.9MIT
- AlicenseNot gradedqualityDmaintenanceProvides persistent memory for Claude by implementing a local knowledge graph to store and retrieve entities, relations, and observations. This enables long-term information retention and personalization across different chat sessions.MIT

SAE4U Memoryofficial
AlicenseAqualityCmaintenanceProvides persistent memory for Claude with hierarchical categorization, cross-corpus recall, session journals, and customizable persona, enabling memory continuity across sessions.7MIT