Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
create_threadA

Open a thread on this project's board (one per finding/question/note). body supports Markdown (incl. tables). tags are freestyle marker badges. actions are tailored quick-reply buttons (default ["Fix","Approve"]).

add_messageA

Append an agent message to a thread (Markdown). Start with a one-line summary of what the user asked. Optionally refresh actions/tags. Adding a message to a resolved thread reopens it.

resolve_threadA

Mark a thread resolved (only small/clear-cut items — leave heavy/uncertain changes open for the user).

reopen_threadA

Reopen a resolved thread to continue it.

defer_threadA

Park a thread as "deferred": it drops into a Deferred lane below Waiting-on-agent and is excluded from the review counts and the "needs your attention" set, so the user can ignore it for now. Use for real work that is not a good time to tackle yet (blocked, out of scope for this pass, better done after X). Optionally pass a short reason (posted as a note on the thread).

resume_threadA

Un-defer a parked thread AND post a message recommending the user pick it up now — message must explain WHY now is a good time (e.g. the blocker is cleared, the prerequisite landed). This brings the thread back to the top of "Needs your attention" as unread.

list_threadsC

List threads on this board (id, title, tags, status, work-state, message count).

set_summaryA

Pin an overall TL;DR (Markdown) at the top of the board. Empty string clears it.

get_board_urlA

Return this project's stable board URL. Share it with the user.

wait_for_feedbackA

Block until the user submits their batched replies/notes on the board, then return them. ONE long call (default ~55 min) — do not poll in a loop; it returns instantly on submit and sends progress so it will not time out. Automatically flips the board to "your turn" (title + sound) while blocking and back to idle on return. Survives a daemon restart mid-wait (reconnects and keeps waiting); only if reconnection keeps failing does it return with a hint to call it once more. Create the threads BEFORE calling this.

get_notesA

Return ALL free-form "other notes" the user submitted on this board (durable; each submission a separate entry).

start_workingC

Tell the UI you started acting on the feedback (shows a working indicator).

finish_workingC

Tell the UI the whole batch is done (title highlights, optional sound).

work_on_threadB

Tell the UI you are now working on a specific thread (highlighted as in-progress).

mark_thread_done

Mark that you finished working on a specific thread (counts toward the progress bar).

list_boards

List all boards on the daemon (id, label, key, thread counts, URL).

use_board

Switch THIS session to an existing board by id (e.g. to recover stranded threads). Reverts to the stable per-project board on the next restart unless switched again.

import_threads

Copy threads (with full message history) from another board into THIS board. mode "append" (default) or "replace".

export_board

Export the full JSON of THIS board (all threads + messages + summary).

backup_boardA

Write a timestamped backup file of THIS board to the daemon's backups/ folder. Returns the path.

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/gweiermann/mcp-session-threads'

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