Schema | corpus-mcp

corpus-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`CORPUS_DB`	No	Index file (derived; can be rebuilt)	/var/lib/corpus-mcp/corpus.db
`CORPUS_HOST`	No	HTTP listen address	0.0.0.0
`CORPUS_PORT`	No	HTTP listen port	8000
`CORPUS_DATA_DB`	No	Primary data such as pinned citekeys (never rebuilt)	/var/lib/corpus-mcp/data.db
`CORPUS_LIBRARIES`	No	Comma-separated library folders to index	main
`CORPUS_ACCESS_AUD`	No	Cloudflare Access audience (AUD) used to verify identities for admin writes
`CORPUS_BACKUP_DIR`	No	Where corpus-mcp backup writes daily copies of data.db (14 kept)	/var/lib/corpus-mcp/backups
`CORPUS_BOOKS_ROOT`	No	Directory containing one folder per Calibre library	/srv/corpus/books
`CORPUS_VOCABULARY`	No	Path to the vocabulary JSON file (corpus-vocabulary/1) that the server reads and reloads when it changes	/var/lib/corpus-mcp/vocabulary.json
`CORPUS_EXCLUDE_TAGS`	No	Calibre tags that keep a book out of the index	private
`CORPUS_CITEKEY_PRESET`	No	Preset used to build proposed citekeys; author-year-word (the default) or bbt-default	author-year-word
`CORPUS_ACCESS_TEAM_DOMAIN`	No	Cloudflare Access team domain used to verify identities for admin writes

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

ActivityMaintained

ResponsivenessNo issues