Skip to Content
ConfigurationMCP servers

MCP servers

An MCP server (Model Context Protocol) extends your AI tools with external capabilities. cnfgr stores a single definition and writes it into each tool that supports MCP.

Anatomy of an MCP server

FieldMeaning
idStable identifier for the server.
nameDisplay name.
transportHow the tool talks to the server (e.g. stdio or HTTP).
command / urlThe command to launch (stdio) or the endpoint URL (HTTP).
argsArguments passed to the command.
envEnvironment variables — secret values held as placeholder references.
headersRequest headers — secret values held as placeholder references.
trustTrust setting for the server.
timeoutRequest timeout.

Secrets stay local

MCP servers often need an API key or token. cnfgr never syncs those values: in env and headers, secrets are stored as placeholder references (${secret:<id>}) and re-hydrated from each device’s local secret store when the config is written. See Secrets & privacy.

Editing an MCP server

Open the MCP tab and select or create a server. Enter the transport, command/URL, args, env, and headers. Secret values you enter are kept on the device and replaced with placeholders everywhere they’d otherwise travel.

Fidelity across tools

Tools vary in their MCP support. cnfgr projects the definition into each tool’s format; see the tool support matrix.