Dejaview Mcp

@JakeC77

About Dejaview Mcp

DejaView is a persistent knowledge graph memory layer for AI agents. It gives every MCP-compatible AI host shared, queryable memory of people, projects, decisions, and relationships — stored in a graph that grows smarter over time.

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "dejaview": {
      "type": "streamable-http",
      "url": "https://api.dejaview.io/mcp",
      "headers": {
        "Authorization": "Bearer dv_your_key_here"
      }
    }
  }
}

Tools

Get a full context summary of your knowledge graph. Returns entity counts, most-connected entities, and recent activity. Call this at the start of every conversation to bootstrap your memory.

Store a fact as subject -> predicate -> object in the knowledge graph. Use for any relationship, preference, decision, or event worth keeping across sessions. Examples: remember("Alice", "works_at", "Orbit Labs") remember("Project Atlas", "has_status", "in progress", "As of Q1 2026")

Store multiple facts at once. More efficient than looping remember(). Each fact needs: subject, predicate, object. Optional: context.

Get everything known about an entity — all relationships in and out. Use for full context on a person, project, org, concept, or any entity.

Search for entities in the graph by name (partial match). Use this to discover what's in the graph before calling recall(). Returns names, types, and connection counts.

Ask a natural language question about your knowledge graph. Returns a synthesized answer backed by cited graph facts — no hallucination. Every claim traces to a real stored fact with a timestamp.

Get recent facts in reverse chronological order. Use at session start alongside agent_context() to see what was recently remembered.

Get a high-level summary of the knowledge graph. Returns entity count, entity types, relationship count, and relationship types.

Create a public shareable link for any entity's subgraph. Returns a URL anyone can open — no account needed. Shows an interactive visual graph of the entity and its connections.

Remove a specific fact from the knowledge graph. Deletes the relationship between subject and object but leaves both entities intact. Use to correct wrong or outdated facts.

Remove an entity AND all its relationships from the knowledge graph. Use with care — this permanently wipes the node and every edge connected to it. Good for removing entirely wrong or duplicate entities.

Overview

What is Dejaview Mcp?

Dejaview Mcp is a persistent knowledge graph memory layer for AI agents. It gives every MCP-compatible AI host shared, queryable memory of people, projects, decisions, and relationships — stored in a graph that grows smarter over time.

How to use Dejaview Mcp?

Install with pip install dejaview-mcp, then add a dejaview entry to your MCP server configuration with the DEJAVIEW_API_KEY environment variable. The server exposes 12 tools for storing, recalling, searching, and managing graph memories; call agent_context at the start of every conversation to load a full memory summary.

Key features of Dejaview Mcp

Knowledge graph with typed relationships between any entities
Natural language Q&A with answers cited from stored facts
Public sharing of entity subgraphs as interactive visual graphs
Works with Claude Desktop, Cursor, Windsurf, and any MCP host
Tools for storing, recalling, searching, and forgetting facts
Timeline and graph statistics tools for memory overview

Use cases of Dejaview Mcp

Load a full memory summary at the start of every conversation to maintain context
Store facts about decisions, relationships, preferences, and events as they occur
Ask natural language questions about stored knowledge and get cited answers
Share interactive graph links for any entity and its connections with others

FAQ from Dejaview Mcp

How do I install Dejaview Mcp?

Run pip install dejaview-mcp to install the package.

How do I configure Dejaview Mcp for my MCP host?

Add a dejaview entry to your mcpServers configuration with the command dejaview-mcp and the environment variable DEJAVIEW_API_KEY set to your API key from https://dejaview.io.

What tools does Dejaview Mcp provide?

It provides 12 tools including agent_context, remember, remember_many, recall, search, ask, timeline, graph_stats, share, forget, and forget_entity.

Where is my data stored?

Data is stored on the DejaView cloud service, accessed via your API key.

Which MCP hosts can I use Dejaview Mcp with?

It works with Claude Desktop, Cursor, Windsurf, and any other MCP-compatible host.

Frequently asked questions

How do I install Dejaview Mcp?

Run `pip install dejaview-mcp` to install the package.

How do I configure Dejaview Mcp for my MCP host?

Add a `dejaview` entry to your `mcpServers` configuration with the command `dejaview-mcp` and the environment variable `DEJAVIEW_API_KEY` set to your API key from https://dejaview.io.

What tools does Dejaview Mcp provide?

It provides 12 tools including `agent_context`, `remember`, `remember_many`, `recall`, `search`, `ask`, `timeline`, `graph_stats`, `share`, `forget`, and `forget_entity`.

Where is my data stored?

Data is stored on the DejaView cloud service, accessed via your API key.

Which MCP hosts can I use Dejaview Mcp with?

It works with Claude Desktop, Cursor, Windsurf, and any other MCP-compatible host.

Comments

Basic information

More Memory & Knowledge MCP servers

Memory Bank MCP Server

alioshr

A Model Context Protocol (MCP) server implementation for remote memory bank management, inspired by Cline Memory Bank.

913

Ultimate Google Docs & Drive MCP Server

a-bonus

The Ultimate Google Docs, Sheets, Drive, Gmail, & Google Calendar MCP Server. This MCP (primarily for use in Claude Desktop) gains full access to your google suite and lets claude do its thing.

605

Notion MCP Server

makenotion

Official Notion MCP Server

4.5K

Basic Memory

basicmachines-co

AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN

3.4K

Rust Docs MCP Server

Govcraft

🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, uses embeddings/LLMs, and provides accurate context via a tool call.

286