com.deerdawn/deerdawn
NPM · @DEERDAWN/MCP-SERVER · 2 COMPONENTS · SCANNED SEP 25
AI session memory: the brief your AI reads before every session so no session starts cold.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 34 of 108 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 3 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability76
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1988 tokens (~165/item across 12 items; 10 tools + 2 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management13
- Stability check failed: the tool surface changed between 1.0.41 and 1.0.53: 24 tool removals, 0 breaking changes, 4 additions. See how to fix → Fail
Tool Coverage88
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 57% of tool parameters carry a description.Partial
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the com.deerdawn/deerdawn MCP server?
com.deerdawn/deerdawn runs locally as an npm package, launched with npx -y @deerdawn/mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @deerdawn/mcp-server
claude mcp add com-deerdawn-deerdawn -- npx -y @deerdawn/mcp-server
{
"mcpServers": {
"com-deerdawn-deerdawn": {
"command": "npx",
"args": [
"-y",
"@deerdawn/mcp-server"
]
}
}
} {
"servers": {
"com-deerdawn-deerdawn": {
"command": "npx",
"args": [
"-y",
"@deerdawn/mcp-server"
]
}
}
} codex mcp add com-deerdawn-deerdawn -- npx -y @deerdawn/mcp-server
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"com-deerdawn-deerdawn": {
"type": "local",
"command": [
"npx",
"-y",
"@deerdawn/mcp-server"
],
"enabled": true
}
}
} openclaw mcp add com-deerdawn-deerdawn --command npx --arg -y --arg @deerdawn/mcp-server
mcp_servers:
com-deerdawn-deerdawn:
command: "npx"
args: ["-y", "@deerdawn/mcp-server"] {
"McpServers": {
"com-deerdawn-deerdawn": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"@deerdawn/mcp-server"
]
}
}
} assistant mcp add com-deerdawn-deerdawn -t stdio -c npx -a -y @deerdawn/mcp-server
{
"mcpServers": {
"com-deerdawn-deerdawn": {
"command": "npx",
"args": [
"-y",
"@deerdawn/mcp-server"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 24 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 7 to 10.
- 22 Sept 26 +16
- Malware scan: unverified → pass ▲ security
- 21 Sept 26 −15
- Malware scan: pass → unverified ▼ security
- Package version: 1.0.52 → 1.0.53 functional
- 20 Sept 26 −3
No change was recorded against any check on this day. Stability & Change Management went from 20 to 0.
- 19 Sept 26 0
- Tool safety: pass → unverified ▼ security
- Stability: fail → unverified ▼ security
- Tool coverage: 100 → unverified ▼ functional
- Capabilities: pass → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- Package version: 1.0.51 → 1.0.52 functional
- 18 Sept 26 +1
- Package version: 1.0.50 → 1.0.51 functional
- 17 Sept 26 0
- Tool safety: pass → unverified ▼ security
- Stability: fail → unverified ▼ security
- Schema quality: 100 → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Capabilities: pass → unverified ▼ functional
- Package version: 1.0.49 → 1.0.50 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 25 Sept 2026 · Analysed npm/@deerdawn/mcp-server@1.0.53
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 108 packages
| Packages resolved | 108 |
|---|---|
| Stale | 34 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
apply_setup ~80
Safely 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.
| Name | Type | Req | Description |
|---|---|---|---|
| mode | string | – | – |
| surface | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
build_subagent_brief ~211
Build 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.
| Name | Type | Req | Description |
|---|---|---|---|
| acceptance_criteria | array | – | Explicit success and scope conditions. |
| deliverable | string | – | The exact result the worker should return. |
| focus_paths | array | – | Known files or folders the worker should prioritize. |
| max_tokens | number | – | Approximate brief token target (default 250). |
| project_id | string | – | Optional project override. Omit to use the active project for this codebase. |
| role | string | – | Optional worker role, such as researcher, implementer, reviewer, or tester. |
| task | string | yes | The concrete, bounded objective delegated to the worker. |
| verification | array | – | Commands or checks the worker should perform. |
Structured output declared, but exposes no named fields.
No examples provided.
complete_setup ~90
Run 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.
| Name | Type | Req | Description |
|---|---|---|---|
| mode | string | – | – |
| path | string | – | Optional override path for the local context import (defaults to auto-detect in cwd). |
| surface | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
get_auth_status ~56
Check 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.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
get_setup_status ~49
Check 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.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
manage_memory ~523
Write 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.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | resolve closes a stored workspace entity; resolve_question answers ONE open question in the brief and leaves the rest of it alone. |
| answer | string | – | For resolve_question: what the question was decided to be. Recorded as a decision. |
| ask_questions | boolean | – | – |
| claim | string | – | – |
| commands | array | – | – |
| complete_task | boolean | – | – |
| confirm_complete | boolean | – | – |
| confirmed | boolean | – | – |
| dry_run | boolean | – | – |
| entities | array | – | – |
| entity_type | string | – | – |
| items | array | – | – |
| kind | string | – | For export_trail: 'pack' marks the Trail as curated knowledge meant for OTHER projects, so importing it skips this project's task state, goals and board. Default 'project'. |
| new_project_name | string | – | – |
| notes | string | – | – |
| output_path | string | – | For export_trail: where to write the .dawn file. Defaults to the project root. |
| path | string | – | – |
| paths | array | – | – |
| project_id | string | – | Project id or exact name. Omit to use the active project. The one exception is action="export_trail", which needs it explicitly and will not guess which project to archive. |
| question | string | – | For resolve_question: the exact, complete open question from the brief. A query matching several resolves none and lists them. |
| relations | array | – | – |
| summary | string | – | – |
| task | string | – | For update: set the brief's current task directly. Extraction cannot change this field, so pass it explicitly whenever the headline of the brief should change. |
| title | string | – | – |
| trail | string | – | For import_trail: an https URL to a .dawn file, a path to one, or the file contents. |
Structured output declared, but exposes no named fields.
No examples provided.
manage_projects ~148
Manage 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.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | – |
| description | string | – | – |
| parent_project_id | string | – | Project id (project_1a2b3c4d-...) or the project's exact name. Omit to use the active project. |
| project_id | string | – | Project id (project_1a2b3c4d-...) or the project's exact name. Omit to use the active project. |
| project_name | string | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
manage_tasks ~216
Manage 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.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | – |
| cards | array | – | For add: cards with detail. Use instead of todos when a card needs a body. Re-adding an existing title with a body sets that card's body. |
| confirm_destructive | boolean | – | Required for remove, after reviewing the exact cards that will be permanently deleted. Removal is a hard delete with no undo. |
| phase | string | – | – |
| project_id | string | – | Project id (project_1a2b3c4d-...) or the project's exact name. Omit to use the active project. |
| todos | array | – | Card titles for add, card IDs or title phrases for other actions, or the cards to open in full for list. |
Structured output declared, but exposes no named fields.
No examples provided.
recall ~258
Retrieve 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.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | The kind of memory to retrieve. Use portfolio for what is shared across projects. |
| limit | number | – | Maximum number of matches. |
| mode | string | – | Overview mode for action=overview. |
| project_id | string | – | Project id (project_1a2b3c4d-...) or the project's exact name. Omit to use the active project. |
| query | string | – | Topic or path query for search, paths, entities, or portfolio. |
| scope | string | – | Entity scope for action=entities. workspace looks across ALL of this account's projects, which is how you find a service, person, or decision appearing in more than one; project stays inside a single… |
| sections | array | – | Project brief sections for action=context. |
| status | string | – | Optional entity status filter. |
| surface | string | – | Optional entity surface filter. |
| types | array | – | Entity types for action=entities. |
| verbosity | string | – | Amount of detail to return. |
Structured output declared, but exposes no named fields.
No examples provided.
start_session ~62
Start 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.
| Name | Type | Req | Description |
|---|---|---|---|
| verbosity | string | – | How much detail for the active project. Default: standard. |
Structured output declared, but exposes no named fields.
No examples provided.
What is the com.deerdawn/deerdawn MCP server?
com.deerdawn/deerdawn is an MCP server listed in the public MCP registry as com.deerdawn/deerdawn. AI session memory: the brief your AI reads before every session so no session starts cold. This page covers its npm package (@deerdawn/mcp-server).
Is the com.deerdawn/deerdawn MCP server safe to use?
com.deerdawn/deerdawn scores 71 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 25 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the com.deerdawn/deerdawn MCP server expose?
com.deerdawn/deerdawn exposes 10 tools: get_auth_status, get_setup_status, apply_setup, complete_setup, recall, and 5 more. Their descriptions and schemas cost roughly 1,693 tokens of context every time the server is loaded.
Is the com.deerdawn/deerdawn MCP server still maintained?
com.deerdawn/deerdawn is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the com.deerdawn/deerdawn MCP server under?
com.deerdawn/deerdawn declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.