Decay-weighted vector memory for AI agents — 83 MCP tools: store, recall, search, knowledge graphs.
Connect Dakera to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Decay-weighted vector memory for AI agents — 83 MCP tools: store, recall, search, knowledge graphs. The dakera mcp server is what makes that connection.
MCP server for Dakera AI. Gives any MCP-compatible AI agent persistent, queryable memory — with smart token management built in.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
Cargo — The Cargo tool exposed by this serverConfiguration is passed through the environment: DAKERA_API_URL, DAKERA_API_KEY, DAKERA_MCP_PROFILE, DAKERA_ROOT_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.
This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Dakera's toolset — Cargo — is a fair guide to whether it matches your workflow. It is maintained by Dakera-AI; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Dakera's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Cargo | The Cargo tool exposed by this server. |
{
"mcpServers": {
"dakera": {
"command": "dakera-mcp",
"env": {
"DAKERA_API_URL": "http://localhost:3300",
"DAKERA_API_KEY": "your-key"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| DAKERA_API_URL | Endpoint or connection string the server talks to. | Yes |
| DAKERA_API_KEY | Credential the server authenticates with. | Yes |
| DAKERA_MCP_PROFILE | Configuration value read at startup. | Optional |
| DAKERA_ROOT_API_KEY | Credential the server authenticates with. | Yes |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.