Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_SSE_HOSTNoListen host for SSE/remote MCP. Default: 0.0.0.0
MCP_SSE_PORTNoListen port for SSE/remote MCP. Default: 3100. Also settable via PORT.
MCP_AUTH_TOKENNoBearer token required for remote MCP clients.
MCP_CORS_ORIGINNoCORS origin for remote MCP. Defaults to * when MCP_AUTH_TOKEN is set, otherwise no CORS.
READING_HTTP_PORTNoPort for the reader HTTP server. Default: 8787 (when using http.js)
MCP_MAX_BODY_BYTESNoMax JSON-RPC POST body size. Default: 25000000
READING_MCP_DATA_DIRNoDirectory for storing books, annotations, progress, and cards. Default: ./data
READING_IMPORT_MAX_BYTESNoMax EPUB/TXT upload size. Default: 25000000
READING_TRASH_RETENTION_DAYSNoDays to retain trashed books. Default: 30

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
reading_list_booksB

List imported books with progress and annotation counts.

reading_list_chunksA

List chunks for a book in reading order.

reading_read_chunkC

Read one book chunk and return prevId/nextId.

reading_continueA

Continue reading from the next unread chunk. If bookId is omitted, use the most recently read book.

reading_search_chunksC

Search book chunks by keyword.

reading_import_bookB

Import one EPUB or TXT file from base64 content into the reading library. Use this for files small enough for one MCP request.

reading_import_beginB

Start a chunked EPUB/TXT import. Use this when the file is too large for one reading_import_book request.

reading_import_partC

Append one base64 file part to an active chunked import.

reading_import_finishB

Finish a chunked import and add the uploaded EPUB/TXT to the reading library.

reading_import_cancelA

Cancel a chunked import and delete its temporary upload file.

reading_delete_bookA

Delete a book from the active library and archive its book folder plus related progress, annotations, submissions, and cards under data/trash. Requires confirm: true.

reading_annotate_passageA

Write a Claude margin annotation anchored to a quote in a chunk. Human private notes should be created through the HTTP reader API, not this MCP tool.

reading_list_annotationsA

List annotations, optionally filtered by book, chunk, kind, or author.

reading_submit_user_notesA

Submit open user notes for Claude review. By default, include each chunk's full text once per session and mark notes submitted so they are not sent again.

reading_list_submissionsB

List human note submission batches that have been shared with Claude.

reading_read_submissionB

Read one human note submission batch including notes and context.

reading_reply_to_annotationC

Attach a Claude reply under an existing user or Claude annotation.

reading_mark_readC

Mark a chunk as read and update last-read progress.

reading_card_inboxC

Show unread collected reading-card prompts, like a small bookmark inbox.

reading_card_collectionC

Browse collected reading cards as a paginated collection without opening every image.

reading_open_cardA

Open one collected reading card and return it as an image for Claude to view.

reading_save_cardC

Render one collected reading card to a local image file and return its absolute path.

reading_dismiss_cardB

Dismiss one collected reading card from the card inbox without deleting it.

reading_list_cardsC

List collected ritual reading cards/bookmarks for completed sections or shared margin moments.

reading_collect_cardC

Collect a small ritual reading card/bookmark so it can be revisited later.

reading_get_progressA

Get reading progress for one book or all books.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/idleprocesscc/co-reading-mcp'

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