広告掲載
MCP.so
ログイン
D

Dejaview MCP Server

@JakeC77

リポジトリ

基本情報

カテゴリ

メモリとナレッジ

トランスポート

stdio

作者

JakeC77

投稿者

JakeC77

Dejaview MCP Server について

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.

Dejaview MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

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

Dejaview MCP Server のツール

11

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 Use to correct wrong or outdated facts.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.

概要

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

よくある質問

1

How do I install Dejaview Mcp?

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

2

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.

3

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`.

4

Where is my data stored?

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

5

Which MCP hosts can I use Dejaview Mcp with?

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

コメント

「メモリとナレッジ」の他のコンテンツ

UmmahAPI

Yousuf Kazmi

Islamic source data for assistants: Quran, hadith, tafsir, duas, prayer times and qibla. Answers come from real sources with citations instead of recalled text, so verses and hadith are not hallucinated. 36,000+ hadiths

agentleFS

agentleFS

One permissioned folder your team and your AI agents both log into.

Sensefold

SenseFold Labs

Personal context for every AI: search, read, and write back to your private Markdown library of articles, threads, PDFs, notes, and captured ChatGPT/Claude/Gemini/Grok conversations. Remote server, OAuth 2.1 paste-and-au

OpenLore

aakarim

Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab

66

AOCI-CODE

aoci-spec

Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.

1.7K
広告掲載