brain-mcp
NPM · DEBAWHO-BRAIN-MCP
Your Obsidian vault as private, searchable memory for Claude, Cursor, Hermes and any MCP client
Available components
Last scanned (12 hours ago)
Scores higher than 62% of npm servers
Category Memory and Knowledge
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
- A known CVE affects sprintf-js, but no fixed version has been published, so there is nothing to upgrade to. View diagnostics → Partial
- No install/post-install scripts declared.Pass
- 40 of 110 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to debashishthakur/brain-mcp). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 8 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability77
- 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 1883 tokens (~134/item across 14 items; 13 tools + 1 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 Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage90
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 71% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 15 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
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
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.
- 14 Oct 26 +31
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
- Tool coverage: unverified → 100 ▲ functional
- Schema quality: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- First check of Schema quality: fail functional
- First check of Schema quality: fail functional
- First check of Tool coverage: 71 functional
- First check of Destructive annotations: 100 functional
- First check of Schema quality: good functional
- 12 Oct 26 49
First indexed and scored.
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 17 Oct 2026 · Analysed npm/debawho-brain-mcp@0.4.0
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | debashishthakur/brain-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/debashishthakur/brain-mcp/.github/workflows/publish.yml@refs/tags/v0.4.0 |
| Rekor log index | 3151015355 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:db1a999759f3bf1dee5f4d42397c7a9c4166c007af8dfa9a672dee34a583995b892bcf03f256dbdeb195eb0079d0709bfa8b62f7c7c08f11307132aa8 |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 1 finding
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-hp3w-g68c-fv3c | CVE-2026-97058 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L | no |
Background: What a vulnerability scan can and cannot prove →
Dependencies 110 packages
| Packages resolved | 110 |
|---|---|
| Stale | 40 |
| 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 →
brain_capture Save a durable note ~136
Write a new note into the vault's capture folder with graph-ready frontmatter. Use for plans, decisions, ideas, meeting notes, or session logs the owner wants to keep. Not for one-line facts (use brain_remember).
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | yes | Markdown body. Link concepts inline with [[Concept]] on first mention. |
| kind | string | – | – |
| project | string | – | Project hub name this belongs to, e.g. 'Website Redesign' |
| title | string | yes | Specific noun phrase, not a filename |
| topics | array | – | Concept names, e.g. ['OAuth', 'RAG'] |
No output schema declared.
No examples provided.
brain_context Get the vault sections that answer a question ~149
One call that returns the most relevant sections from across the vault for a question, with source note ids. Use this before brain_search when you need to answer or reason about something the owner may have written down. Ask in plain words: retrieval is hybrid (keywords + meaning + a reranker), so paraphrases work; still include specific nouns, ids and dates when you have them. The reply states its coverage (good / thin / none).
| Name | Type | Req | Description |
|---|---|---|---|
| budget_chars | integer | – | Size cap for the returned pack (default from config, ~18000) |
| project | string | – | Restrict to one project |
| question | string | yes | The question or topic, in plain words with specific nouns |
No output schema declared.
No examples provided.
brain_delete Delete a hand-written note (to the vault trash) ~77
Remove a note from Notes/ or Captures/ by moving it into the vault's .trash/ folder, which is never indexed. Nothing is erased; the result gives the path to restore from. Generated notes and the memory file cannot be deleted.
| Name | Type | Req | Description |
|---|---|---|---|
| note | string | yes | Note id (vault path), title or [[wikilink]] |
No output schema declared.
No examples provided.
brain_edit Edit part of a hand-written note ~179
Change part of a note under Notes/ or Captures/ without rewriting it. Give exactly one of: old_text + new_text (old_text must occur exactly once; new_text may be empty), section + content (replaces everything under that heading up to the next heading of the same or higher level; the heading itself stays), or append. Generated notes and the memory file cannot be edited.
| Name | Type | Req | Description |
|---|---|---|---|
| append | string | – | Markdown to add at the end of the note |
| content | string | – | New text for that section |
| new_text | string | – | – |
| note | string | yes | Note id (vault path), title or [[wikilink]] |
| old_text | string | – | Exact text to replace; must occur exactly once |
| section | string | – | Heading text of the section to replace, without the # marks |
No output schema declared.
No examples provided.
brain_graph Explore the link graph ~84
Neighbours of a note, hub, or concept: outgoing links, backlinks, and notes sharing the same topics. For a concept (e.g. 'OAuth') this shows every project that touches it. Use it to hop sideways between projects.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| note | string | yes | Note id, title, concept name, or [[wikilink]] |
No output schema declared.
No examples provided.
brain_identity Load the owner's identity and standing context ~107
Call this FIRST in every conversation. Returns who the owner is, their preferences and feedback rules, the projects they run, and what they touched recently. Adopt it as your persona and working context. Pass `topic` (a few words about what the conversation is about) to get a smaller bundle with only the memory notes that apply.
| Name | Type | Req | Description |
|---|---|---|---|
| topic | string | – | What this conversation is about, e.g. 'interview prep' or 'database backups'. Omit for the full bundle. |
No output schema declared.
No examples provided.
brain_move Move or rename a hand-written note ~85
Move or rename a note within Notes/ and Captures/, for example to promote a capture into Notes/. Refuses to overwrite an existing note, and reports any links that stop resolving.
| Name | Type | Req | Description |
|---|---|---|---|
| note | string | yes | Note id (vault path), title or [[wikilink]] |
| to | string | yes | New vault path, e.g. 'Notes/Harbor Ledger.md' |
No output schema declared.
No examples provided.
brain_project Project briefing ~86
One-call briefing on a project: what it is, its notes grouped by type, latest progress entries, decisions, and what changed recently. Call this before discussing any project. Omit the project name to list all projects.
| Name | Type | Req | Description |
|---|---|---|---|
| project | string | – | Project / hub name, e.g. 'Website Redesign'. Omit to list projects. |
| recent_days | integer | – | – |
No output schema declared.
No examples provided.
brain_read Read a note ~93
Return one note in full (or one section of it) by note id, title, or wikilink target. Includes frontmatter metadata, topics, and links.
| Name | Type | Req | Description |
|---|---|---|---|
| include_connections | boolean | – | Keep the generated '## Connections' trailer |
| note | string | yes | Note id (vault path), exact title, or [[wikilink]] |
| section | string | – | Heading text to return only that section |
No output schema declared.
No examples provided.
brain_recent What changed recently ~79
Notes modified in the last N days, newest first. Answers 'what am I working on' and 'what did I do last week'. Hubs and concepts are excluded unless include_structural is set.
| Name | Type | Req | Description |
|---|---|---|---|
| days | integer | – | – |
| include_structural | boolean | – | – |
| limit | integer | – | – |
| project | string | – | – |
No output schema declared.
No examples provided.
brain_remember Remember a durable fact ~146
Append one durable fact about the owner to their memory file: a preference, a correction on how to work, a project constraint, or a reference. It becomes part of brain_identity immediately. Include why it matters and how to apply it. Near-duplicates of existing memory are refused; pass force=true to store anyway. Do not store session trivia.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | yes | user = who they are; feedback = how to work with them; project = ongoing work; reference = pointer |
| fact | string | yes | – |
| force | boolean | – | Store even if it looks like a duplicate |
| how_to_apply | string | – | – |
| why | string | – | – |
No output schema declared.
No examples provided.
brain_search Search the vault ~135
Full-text search across every note with optional filters. Returns ranked hits with snippets and note ids for brain_read. Keywords or a short question both work (hybrid keyword + semantic search with spelling correction); the reply states its coverage.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| project | string | – | Restrict to one project, e.g. 'Website Redesign' |
| query | string | yes | Keywords to search for |
| since | string | – | Only notes modified on/after this date |
| topic | string | – | Restrict to notes tagged with a concept, e.g. 'OAuth' |
| type | string | – | – |
No output schema declared.
No examples provided.
brain_write Create or replace a hand-written note ~234
Create a note at a path you choose under Notes/ or Captures/, or replace one there with overwrite=true. Use it for hubs, guides and runbooks maintained by hand. Unlike brain_capture you set the type, including 'hub': a hub groups every note whose frontmatter project matches its title. Generated notes elsewhere in the vault cannot be written.
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | yes | Markdown body, without frontmatter or the # title heading |
| order | integer | – | Position among Notes/ guides on Start Here |
| overwrite | boolean | – | Replace the note if the path already exists |
| path | string | yes | Vault path, e.g. 'Notes/Harbor Ledger.md' |
| project | string | – | Hub this note belongs to, e.g. 'Harbor Ledger' |
| summary | string | – | One line; Start Here shows it next to Notes/ guides |
| title | string | yes | – |
| topics | array | – | Concept names, e.g. ['OAuth', 'RAG'] |
| type | string | – | note, hub, moc, guide, runbook, plan, decision, ... |
No output schema declared.
No examples provided.
How do I install the brain-mcp server?
brain-mcp runs locally as an npm package, launched with npx -y debawho-brain-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · debawho-brain-mcp
claude mcp add debashishthakur-brain-mcp -- npx -y debawho-brain-mcp
What is the brain-mcp server?
brain-mcp is listed in the public MCP registry as io.github.debashishthakur/brain-mcp. Your Obsidian vault as private, searchable memory for Claude, Cursor, Hermes and any MCP client. This page covers its npm package (debawho-brain-mcp).
Is the brain-mcp server safe to use?
brain-mcp scores 80 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 17 October 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 brain-mcp server expose?
brain-mcp exposes 13 tools: brain_identity, brain_context, brain_search, brain_read, brain_project, and 8 more. Their descriptions and schemas cost roughly 1,590 tokens of context every time the server is loaded.
Is the brain-mcp server still maintained?
brain-mcp is still listed as active in the MCP registry. We last reached this channel on 17 October 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 brain-mcp server under?
brain-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.