# Dakera

> Use this tool when you need to manage and retrieve AI agent memories efficiently, solving problems related to knowledge storage, recall, and search. Dakera provides a comprehensive set of 83 MCP tools across various categories, accepting input data and outputting relevant information through a self-hosted Rust binary interface. Ideal for use cases requiring robust memory management, such as hybrid retrieval and knowledge graph construction, deployable via Docker, Kubernetes, or Helm.

Canonical page: https://skillsregistry.net/skills/dakera  
JSON: https://api.skillsregistry.net/v1/skills/dakera

## Description

Dakera is the official MCP server for the Dakera AI agent memory platform. Provides 83 MCP tools across 15 categories covering memory storage, recall, vector search, hybrid retrieval, knowledge graph construction, and full-text indexing. The Dakera backend is a single self-hosted Rust binary deployable via Docker, Kubernetes, or Helm with decay-weighted storage that ages memories over time. Achieves 87.6% on the LoCoMo memory evaluation benchmark.

## Trust

- **Trust score (0–1):** 0.63
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/dakera)
- **Repository:** <https://github.com/dakera-ai/dakera-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "dakera"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/dakera` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/dakera/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt