Schema | claude-second-opinion-mcp

claude-second-opinion-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`CLAUDE_SECOND_OPINION_DEBUG`	No	Set to 1 for bounded Claude diagnostics on failures
`CLAUDE_SECOND_OPINION_MODEL`	No	Primary model or selector	best
`CLAUDE_SECOND_OPINION_SAFE_MODE`	No	Disable Claude customizations for workspace reviews	true
`CLAUDE_SECOND_OPINION_CLAUDE_BIN`	No	Claude Code executable	claude
`CLAUDE_SECOND_OPINION_ENV_POLICY`	No	Reviewed operational/network allowlist or explicit inherit	clean
`CLAUDE_SECOND_OPINION_TIMEOUT_MS`	No	Review timeout, 90 minutes	5400000
`CLAUDE_SECOND_OPINION_AUTH_POLICY`	No	max, first_party, or any	max
`CLAUDE_SECOND_OPINION_FALLBACK_MODEL`	No	Native and zero-work capacity fallback model	opus
`CLAUDE_SECOND_OPINION_MAX_BUDGET_USD`	No	Claude print-mode budget ceiling when applicable	2
`CLAUDE_SECOND_OPINION_MAX_INPUT_BYTES`	No	Maximum serialized review packet size	140000
`CLAUDE_SECOND_OPINION_PERMISSION_MODE`	No	Valid Claude Code permission mode or dangerous alias	plan
`CLAUDE_SECOND_OPINION_ALLOWED_TOOLS_JSON`	No	JSON array passed as Claude allowed-tool rules	[]
`CLAUDE_SECOND_OPINION_WORKSPACE_ROOTS_JSON`	No	JSON array of trusted absolute workspace roots	[]
`CLAUDE_SECOND_OPINION_DISALLOWED_TOOLS_JSON`	No	JSON array passed as Claude denied-tool rules	[]

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

This server cannot be deployed

ActivityStale

ResponsivenessNo issues