Schema | SnapRef

SnapRef

Describes the environment variables required to run the server.

Name	Required	Description
`SNAPREF_HOME`	No	Session, profile, recording, and telemetry root (default `~/.snapref/browser`)
`SNAPREF_DEBUG`	No	Chrome stderr
`SNAPREF_CHROME`	No	Explicit external Chromium path; never a personal-browser search
`SNAPREF_SKILLS`	No	Skill directory (default `~/.snapref/skills`)
`NDEV_JSONL_MAX_BYTES`	No	Compatibility alias for `SNAPREF_JSONL_MAX_BYTES` (host adapters)
`SNAPREF_JSONL_MAX_BYTES`	No	Hot telemetry rotate threshold (default 64KiB; `0` disables)
`SNAPREF_MCP_ALLOW_DRIVE`	No	MCP actuation
`SNAPREF_MCP_ALLOW_ORIGINS`	No	MCP navigate/fetch allowlist
`SNAPREF_MCP_ALLOW_HOST_READ`	No	MCP caller-selected playbook reads
`SNAPREF_BROWSER_IDLE_TIMEOUT`	No	Named-session idle lease (default `10m`)
`SNAPREF_MCP_ALLOW_HOST_WRITE`	No	MCP caller-selected screenshot/pack paths

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/nstranquist/snapref'

If you have feedback or need assistance with the MCP directory API, please join our Discord server