Schema | lotor-mcp

lotor-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`LOTOR_HOME`	No	Override the default receipts store path (~/.lotor). Keep this on local disk.

Features and capabilities supported by this server

Capability	Details
`tools`	{}

Functions exposed to the LLM to take actions

Name	Description
query_receiptsA	Query receipt summaries from the persisted chain (most recent first). Never returns full file contents.
verify_chain	Verify the integrity of the receipt chain using the stored public key. Returns ok, brokenAt, reason, and entryCount.
lotor_status	Report Lotor runtime status: home path, receipt count, chain integrity, current herding mode (herded \| grazing \| loose \| custom), whether the human-signature gate is set up, and whether the hooks that actually record and gate are registered in Claude Code settings. Call this at the start of a session or whenever the user asks about Lotor. If gateInitialized is false, walk the user through running `npm run setup` in a terminal to set their signing passphrase (this needs a real terminal; you cannot do it for them). If hooksRegistered.preToolUse is false, nothing is gated regardless of gateInitialized: point the user at the README install steps. Always tell the user the home path so they can see where the runtime lives.
gated_action	Execute a gated action with approval token. FAILS CLOSED: without a valid approval token, returns decision:denied.

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/githubscum/lotor'

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