Dakera Mcp
by Dakera-AIcommunityv0.10.4
7
MCP server that connects AI agents to a Dakera memory server, providing persistent queryable memory and token-efficient tool loading. It supports core memory operations like store, recall, search, session grouping, forgetting, and on-demand discovery/loading of additional tools.
From the registry: Decay-weighted vector memory for AI agents — 86+ MCP tools via tiered profiles
Install & configure
Prerequisites
- requiredRun a Dakera memory serverThe MCP server connects to a Dakera memory server, so you need a Dakera instance running first.
https://github.com/Dakera-AI/dakera-deploy$ docker run -d --name dakera -p 3300:3300 -e DAKERA_ROOT_API_KEY=<your-api-key> ghcr.io/dakera-ai/dakera:latest - required
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `dakera-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Run a Dakera memory server** — The MCP server connects to a Dakera memory server, so you need a Dakera instance running first. Run: `docker run -d --name dakera -p 3300:3300 -e DAKERA_ROOT_API_KEY=<your-api-key> ghcr.io/dakera-ai/dakera:latest` (https://github.com/Dakera-AI/dakera-deploy)
- **Install Node.js 18+** — Required for the recommended npx install/run path. (https://nodejs.org/)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@dakera-ai/dakera-mcp"]
- required environment variables:
- `DAKERA_API_URL`: Base URL of your Dakera memory server. (example: `<your-dakera-api-url>`)
- `DAKERA_API_KEY`: API key used to authenticate to the Dakera memory server. (example: `<your-api-key>`)
- optional environment variables:
- `DAKERA_MCP_PROFILE`: Tool exposure profile. Defaults to core. Supported values described in the README include core, admin, power, and all. (example: `<profile>`)
Note: README also shows installed binary usage via command `dakera-mcp`, but the simplest portable path is `npx @dakera-ai/dakera-mcp`. The README examples use a local Dakera server, commonly at localhost:3300.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: README also shows installed binary usage via command `dakera-mcp`, but the simplest portable path is `npx @dakera-ai/dakera-mcp`. The README examples use a local Dakera server, commonly at localhost:3300.
Tools (14)
dakera_store
Store a memory with importance, tags, and type
dakera_recall
Semantic recall by query text
dakera_search
Advanced memory search with tag/type filters
dakera_session_start
Start a session to group related memories
dakera_session_end
End a session with optional summary
dakera_batch_recall
Bulk filter-based recall by tags, importance, or time
dakera_forget
Delete specific memories by ID
dakera_hybrid_search
Combined vector + BM25 search
dakera_fulltext_search
BM25 full-text search
dakera_knowledge_graph
Build a knowledge graph from a seed memory
dakera_extract
Extract entities and structure from free-form text
dakera_batch_forget
Bulk delete by tags, type, or time range
dakera_discover_tools
Search the full tool catalog by keyword or tier
dakera_load_tools
Environment variables
DAKERA_API_KEYrequiredAPI key used to authenticate with the Dakera memory serverDAKERA_API_URLrequiredBase URL of the Dakera memory server the MCP server connects toPrerequisites
- • Node.js 18+
Packages
ghcr.io/dakera-ai/dakera-mcp:0.10.4
ocitransport: stdio
Details
- Language
- Rust
- License
- NOASSERTION
- Released
- May 18, 2026
- Last commit
- Jul 16, 2026
- Registry name
- io.github.Dakera-AI/dakera-mcp
Categories
Related Servers
Claude Flow
AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
66.0k
Codebase Memory Mcp
Persistent codebase knowledge graph. Survives session restarts and context compaction.
35.4k
Serena
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.
26.9k