aiida-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@aiida-mcplist my AiiDA projects and worker status"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AiiDA MCP
aiida-mcp is a generic, read-only AiiDA runtime interface for AI/MCP clients.
It has no project registry, project_ref, campaign, Group-scope policy, or
Manager web page.
Start one instance for one human-selected runtime:
AIIDA_MCP_PYTHON=/path/to/project/.venv/bin/python \
AIIDA_MCP_PROFILE=silicon \
AIIDA_MCP_WORKSPACE=/path/to/project \
uv run aiida-mcp serveThe selected Python and profile are fixed when the server starts; tools cannot
supply either value. The server listens at 127.0.0.1:8043 by default.
/mcpprovides generic read-only MCP tools./apiprovides the matching local generic transport foraiida-project.
The private aiida_mcp.worker subprocess executes in the selected Python
environment and is the only code that imports AiiDA or queries its ORM.
Project scope belongs to aiida-project, which reads project.yaml, resolves
its declared Group policy, and calls this generic runtime. The Manager UI is
owned by aiida-manager.
process.workgraph is the process-structure API. It returns the actual call
graph; there is deliberately no process.tree alias.
The generic read-only surface also includes direct Node/Link and bounded
provenance traversal. node.compare is implemented inside the worker: it
recursively compares attributes, ports, links, arrays, and repository content
without importing aiida-analyser.
archive.inspect reads a native AiiDA archive without importing it. Its path
must be relative to the configured workspace, so it cannot become an arbitrary
local-file reader.
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP-first control plane for ProAgentStore agents and private instances.
Project management shared by people and AI agents, with persistent project state through MCP.
151Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Remote MCP server to run your Atako AI agents: chat, projects, files, integrations and channels.
Related MCP Servers
FlicenseNot gradedqualityDmaintenanceMCP server that wraps the Picsellia Python SDK, giving AI assistants access to computer vision platform capabilities such as datasets, experiments, models, deployments, and monitoring.-- AlicenseAqualityBmaintenanceMCP server for the Partiri Cloud PaaS platform. Enables AI agents to manage workspaces, projects, services, deployments, and metrics.231MIT
- AlicenseBqualityBmaintenanceMCP server that initializes, manages, and operates traceable agentic infrastructure across your digital ecosystem, serving as a control plane to know project states, health, and initialize missing setups.371MIT
- AlicenseNot gradedqualityBmaintenanceA durable MCP control plane for starting, observing, steering, continuing, cancelling, and handing off long-running coding agents, with bounded MCP calls and persistent worktrees.4 npmMIT