synapse
Candidate MCP tool surface derived one-to-one from the SynapseDevice gRPC service. Science Corporation does not publish a hosted/remote MCP server; this is a proposed local (stdio) wrapper over synapsectl / the Synapse Python client so an agent can drive a neural interface device. Not an official Science Corporation server.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Descriptor
Candidate descriptor · transport stdio
Tools
discover_devices— Discover Synapse devices on the local network.get_device_info— Get device information, peripherals, and current configuration.configure_device— Write a signal-chain configuration (nodes + connections) to the device.start_device— Start the device or a deployed application.stop_device— Stop the device or a deployed application.query_device— Execute a query on the device.stream_query— Open a streaming query against the device.list_apps— List applications deployed to the device.deploy_app— Deploy an application package to the device.list_files— List files stored on the device.read_file— Read a file from the device (streamed).get_logs— Query device logs.update_device_settings— Update persistent device settings.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.