# deerdawn MCP server

AI session memory: the brief your AI reads before every session so no session starts cold.

## Links
- Registry page: https://www.getdrio.com/mcp/com-deerdawn-deerdawn
- Website: https://deerdawn.com

## Install
- Command: `npx -y @deerdawn/mcp-server`
- Endpoint: https://api.deerdawn.com/api/v1/mcp
- Auth: Not captured

## Setup notes
- Package: Npm @deerdawn/mcp-server v1.0.37
- Environment variable: DEERDAWN_API_URL (default https://api.deerdawn.com)
- Remote endpoint: https://api.deerdawn.com/api/v1/mcp

## Tools
- start_session - Call at the start of every session. Returns your active project context — current task, recent decisions, open questions — so you can resume without re-explaining the project. Endpoint: https://api.deerdawn.com/api/v1/mcp
- list_projects - List all your DeerDawn projects with their current task and project ID. Endpoint: https://api.deerdawn.com/api/v1/mcp
- create_project - Create a new DeerDawn project to track a codebase, feature, or initiative. Pass parent_project_id to create it as a subproject under an umbrella (e.g. a workstream of a larger product) — subprojects keep their own task and board. Endpoint: https://api.deerdawn.com/api/v1/mcp
- switch_subproject - Set which subproject is active for this codebase, so start_session, update_context, and manage_todos target it by default. The choice is remembered per workspace until you switch again. Keyed to the codebase (workspace_key), which the Claude Code / Cursor MCP sends automatically. Endpoint: https://api.deerdawn.com/api/v1/mcp
- archive_project - Archive a dead or finished project so it stops cluttering list_projects and never auto-resolves as the active project. Preserves all history. Pass unarchive:true to restore it. Refuses to archive an umbrella that still has live subprojects. Endpoint: https://api.deerdawn.com/api/v1/mcp
- set_project_parent - Re-parent an existing project: nest it under a top-level umbrella by passing parent_project_id, or promote it back to top-level by omitting parent_project_id. Use this to organize related projects into one umbrella after the fact. One level deep; the umbrella must be top-level and the project being moved must have no subprojects of its own. Endpoint: https://api.deerdawn.com/api/v1/mcp
- rename_project - Rename a project (umbrella or subproject). Use to tidy inconsistent, unclear, or shouty project names — the change is immediate and flows into every future brief. Junk names (file paths, "Untitled") are rejected. Endpoint: https://api.deerdawn.com/api/v1/mcp
- get_context - Get the current context for a specific project — task, status, decisions, goals, and open questions. If you have not called start_session yet this session, call it first. Call list_projects if you don't have a project_id. Endpoint: https://api.deerdawn.com/api/v1/mcp
- update_context - Update the context for a project. Call this after a decision is made, a task changes, or a feature ships. Endpoint: https://api.deerdawn.com/api/v1/mcp
- manage_todos - Manage the active project's task board — a scrum-style board where every task is a card that moves across phase columns: Backlog → Blocked → In Progress → Integration → Testing → Done. Actions: add (new cards, default to Backlog or a named phase), move (re-column a card), complete (shorthand for → Done), remove (delete a mistaken card), list (show the board grouped by column). The single task tracker for the project. Endpoint: https://api.deerdawn.com/api/v1/mcp
- search_context - Search across all your DeerDawn projects by keyword or topic. If you have not called start_session yet this session, call it first — it may already answer the question without a search. Endpoint: https://api.deerdawn.com/api/v1/mcp
- get_workspace_overview - Get a full overview of your workspace — all projects, durable knowledge, and capabilities. Endpoint: https://api.deerdawn.com/api/v1/mcp
- get_project_map - Return the durable project map: hot paths, entrypoints, named surfaces, and recent debugging notes. Call this BEFORE searching the codebase — the file may already be known. Omit project_id to use the active project. Endpoint: https://api.deerdawn.com/api/v1/mcp
- find_known_paths - Search durable path memory (hot paths, surfaces, debugging notes) before doing a repo-wide search. Use a path-oriented query like "auth modal" or "signup route". Endpoint: https://api.deerdawn.com/api/v1/mcp
- get_workspace_entities - Query typed workspace knowledge — services, capabilities, patterns, environments, and workflows — for architecture-level orientation. Endpoint: https://api.deerdawn.com/api/v1/mcp
- record_hot_paths - Record durable file/folder hot paths AFTER you discover them, so future sessions find them before searching. Append nodes — do not restate the whole tree. Endpoint: https://api.deerdawn.com/api/v1/mcp
- upsert_workspace_entities - Create or update typed workspace entities (services, capabilities, patterns) and relationships. Use for durable architecture knowledge that should persist beyond a single project note. Endpoint: https://api.deerdawn.com/api/v1/mcp
- record_debug_finding - Record a durable debugging finding, optionally tied to file paths and a commit/diff ref, after diagnosing a bug or tracing a non-obvious handoff. Endpoint: https://api.deerdawn.com/api/v1/mcp
- mark_resolved - Mark a knowledge or decision entity as resolved so it stops appearing in normal context loads. Resolved entries are still retrievable via get_workspace_entities({ status: "resolved" }). Use when a decision has been implemented, a known issue has been fixed, or a knowledge entry is no longer relevant. Endpoint: https://api.deerdawn.com/api/v1/mcp
- get_next_best_context - Return the most relevant next context to fetch or use for the current task/session, including open questions and pending decisions ranked for relevance and token efficiency. Endpoint: https://api.deerdawn.com/api/v1/mcp
- cleanup_context - Clean up task context at handoff/finish time. Marks the finished task as completed, clears open-task command history, and returns unresolved questions that still need answers. Endpoint: https://api.deerdawn.com/api/v1/mcp
- list_skills - List available shared skills (name + description, no body). Use on web tools (ChatGPT, Claude.ai) that cannot read skill files from disk. Endpoint: https://api.deerdawn.com/api/v1/mcp
- get_skill - Fetch one shared skill in full (including markdown body) by slug. Call after list_skills when a skill is relevant to the current task. Endpoint: https://api.deerdawn.com/api/v1/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: com.deerdawn
- Version: 1.0.37
- Runtime: Npm
- Transports: STDIO, HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 22, 2026
- Source: https://registry.modelcontextprotocol.io