DockaShell is an MCP server that gives AI agents isolated Docker containers to work in. MCP tools for shell access, file operations, and full audit
Most knowledge and memory work still happens through a UI a human drives. DockaShell MCP server moves it into the conversation instead. DockaShell is an MCP server that gives AI agents isolated Docker containers to work in. MCP tools for shell access, file operations, and full audit trail.
DockaShell is an MCP (Model Context Protocol) server that gives AI agents isolated Docker containers to work in. Each agent gets its own persistent environment with shell access, file operations, and full audit trails.
dockashell on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
The server publishes 2 tools. What each one is for:
Self — evolving agents**: Build and refine their own tools, scripts, and workflowsMeta-learning — Analyze previous traces to improve decision-making and tool usagePlenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. DockaShell's toolset — Self, Meta-learning — is a fair guide to whether it matches your workflow. It is maintained by anzax; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| Self | evolving agents**: Build and refine their own tools, scripts, and workflows |
| Meta-learning | Analyze previous traces to improve decision-making and tool usage |
Add to your MCP client configuration:
```json
{
"mcpServers": {
"dockashell": {
"command": "dockashell",
"args": ["serve"]
}
}
}Configuration as documented by the project. Restart the client after saving.
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.