All servers / Memory / DeerDawn MCP server
DeerDawn MCP server
MCP server for DeerDawn — AI session memory that briefs every new AI session
Tested by ConnectATDScore 83 out of 100. Tested 2026-11-19 on package version 1.0.61. Package: @deerdawn/mcp-server · source
Score breakdown
| Runs | 18 / 20 | |
|---|---|---|
| Tool descriptions | 17 / 20 | |
| Package safety | 20 / 20 | |
| Maintenance | 20 / 20 | |
| Adoption | 8 / 20 |
What we saw
- Starts and answers the MCP handshake: yes (4.4 seconds including download)
- Tools offered: 10
- Last published: 2026-11-17
- Weekly downloads (npm): 776
- License: MIT · Direct dependencies: 3
Want this server set up for your team?
ConnectATD builds AI automation and wires up MCP servers like this one. Tell us what you are trying to do.
Talk to ConnectATDTools and how they are described
Agents choose tools from these descriptions. Under each name you can see how many of its parameters are explained.
get_auth_statusno parametersCheck DeerDawn authentication during initial setup or when a tool reports that sign-in needs attention. If authentication is missing, this may clear stale pending sign-in state and start a device flow that returns a sign-in URL for the user.
get_setup_statusno parametersCheck DeerDawn local setup status for authentication, global instruction files, and MCP-capable tool configs. Use this when an agent needs to know how well DeerDawn is connected on this machine.
apply_setup0 of 2 parameters describedSafely configure or repair DeerDawn setup for a supported local surface. Normally called automatically on first authenticated startup via complete_setup — only call this manually if auto-setup failed or you need to repair a specific surface. Creates a backup before writing config files and can restore the latest backup.
complete_setup1 of 3 parameters describedRun DeerDawn setup in one call: check auth, apply local surface setup, and preview then import local context files (CLAUDE.md, AGENTS.md, .cursorrules) when they are found.
recall11 of 11 parameters describedRetrieve DeerDawn memory through one tool. Action portfolio reads across every project at once, for what recurs in more than one. Some retrieval actions update selection counters, and every invocation records usage telemetry.
manage_projects2 of 5 parameters describedManage projects and subprojects through one tool. Actions can create, select, rename, move, archive, or restore a project. Archive hides a project from normal use, while rename and move replace its current name or hierarchy.
manage_memory8 of 25 parameters describedWrite or close out DeerDawn memory through one tool. Update the brief, import local context, record paths or findings, upsert entities, confirm or resolve stored knowledge, finish the current task, or move a project between machines as a Trail archive (export_trail writes a private .dawn file — pass kind:"pack" when it is knowledge for other people's projects; import_trail merges one in, from a URL, a path or raw contents, without overwriting existing context). Some actions overwrite fields or permanently clear finished task state. Exported Trails are unscanned and private — this tool cannot publish one.
manage_tasks4 of 6 parameters describedManage the active project task board. List cards, add new work, move cards between phases, mark work complete, or permanently remove a mistaken card after explicit confirmation. A listing marks cards carrying detail with +body; name those cards in todos with action list to open them in full.
start_session1 of 1 parameter describedStart a DeerDawn session and load the active project brief. The call replaces session markers, records a durable session load, may replace generated context files, and records usage telemetry.
build_subagent_brief8 of 8 parameters describedBuild a compact, task-scoped prompt for a worker agent. Call once per delegated subtask, then pass only the returned brief using the host's isolated/no-history mode when available. The brief includes the objective, success criteria, relevant project facts and paths, watch-outs, and verification under a bounded token target.
Tested in a sandbox with an empty environment: no API keys, a throwaway folder, nothing from a real account. A passing test shows the server runs and responds. It is not a security audit.