Skip to content

Brainz MCP server

ai.brownmatter/brainzbrownmatter.aistreamable-httpv0.1.0Scanned

Shared product-knowledge graph for AI agent fleets — vault tools + agent self-signup over MCP.

17 tools: 3 can delete or cancel things, 1 do something that can't be undone, 6 change things and 7 only read.

Tools: 3 delete, 1 irreversible, 6 write, 7 read.
  • Reads private data · 3
  • Reads text others write · 1
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

3 tools here can delete or cancel things and 1 does something that can't be undone. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Brainz MCP server can do

The Brainz MCP server is published by brownmatter.ai, a domain the MCP Registry verified. It has 17 tools. It can delete or cancel things (3 tools: upsert_concept, delete_concept and dream), do things that cannot be undone, such as sending, paying or publishing (link_concepts) and create or change data (6 tools: onboard, sync, take_task, complete_task and 2 more). 7 tools only read.

3 tools read private data (search_concepts, vault_stats and list_tasks); 1 tool brings in text other people can write (dream); 1 tool can send data out of your system (link_concepts). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 10, 2026, version 0.1.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

17 tools

Deletes or cancels 3Claude Code: deny
  • delete_conceptRemove a concept from the vault and all of its outgoing edges.No findings

    Why it is in this group

    • The name "delete_concept" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Remove a concept from the vault and all of its outgoing edges. Use to clear a note that is wrong, obsolete, or junk (e.g. a probe or test node that shouldn't be in the graph). Idempotent: deleting an id that doesn't exist is a no-op success (deleted:false), not an error. Deletion is permanent — prefer upsert_concept to correct a note you want to keep. Returns { deleted, id }.

    Annotations the server declares

    • title: Delete concept
    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: false
  • dreamDreaming: a scheduled consolidation sweep over this vault.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Dreaming: a scheduled consolidation sweep over this vault. Light stages what changed since the last dream (near-duplicate concepts, finished task outcomes, hygiene counts); REM asks an LLM for proposals; deep applies the ones that pass threshold gates: merges duplicates (edges redirected, the other tombstoned), promotes outcome knowledge into concepts, adds missing links, and files a task for each contradiction. A sweep that would touch too much of the vault is rejected; every applied dream keeps preimages and can be reverted. {action: "status"} shows schedule + last dream; {action: "run"} dreams now; {action: "diary"} reads the Dream Diary; {action: "revert", id} undoes one dream; {action: "configure", ...} sets the schedule, mode (apply, propose, light-only), phases, thresholds, caps, a stricter loss rail and the LLM choice; {action: "apply", id, proposals?} decides a proposed dream. Without an LLM only light runs.

    Annotations the server declares

    • title: Dream (nightly consolidation)
    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • upsert_conceptWrite a concept note into the vault (creates or overwrites the markdown file, then reindexes it).No findings

    Why it is in this group

    • The name "upsert_concept" says "upsert": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Write a concept note into the vault (creates or overwrites the markdown file, then reindexes it). Use to capture new product knowledge discovered during a task — a decision made, a constraint hit, a pattern adopted — so future agents can find it. Omit `id` to derive a slug from the title; pass an existing id to update that note. Body is markdown; [[wiki-links]] to other concept ids create graph edges. Returns the saved concept's metadata.

    Annotations the server declares

    • title: Create or update concept
    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: false
Can't be undone 1Claude Code: ask
Changes things 6Claude Code: ask
  • complete_taskMark a task done.No findings

    Why it is in this group

    • The description's first verb is "mark": a word for a change.
    Description, as the server wrote it
    Mark a task done. Sets taskStatus=done + doneAt and appends `outcome` to the task body as an Outcome section. The result carries a one-line `reminder` that the rest of the graph is not updated automatically.

    Annotations the server declares

    • title: Complete a task
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • create_taskTurn a finding into first-class work: creates a `task`-type concept with taskStatus=open and the given relations — part_of a domain, `realizes` stories/features, `governed_by` spec…No findings

    Why it is in this group

    • The name "create_task" says "create": a word for a change.
    Description, as the server wrote it
    Turn a finding into first-class work: creates a `task`-type concept with taskStatus=open and the given relations — part_of a domain, `realizes` stories/features, `governed_by` specs — plus codeAreas pointing at where the work lands. Use when you discover work that isn't reflected in the codebase yet (a gap, a needed fix, a follow-up). The task then shows up in list_tasks / take_task and on the Kanban board.

    Annotations the server declares

    • title: Create a task
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • create_vaultCreate a new, empty vault owned by you and add it to this connection.No findings

    Why it is in this group

    • The name "create_vault" says "create": a word for a change.
    Description, as the server wrote it
    Create a new, empty vault owned by you and add it to this connection. Returns the new vault and the vaults this connection can now use. Once a connection covers more than one vault, every vault tool takes a `vault` argument (a slug or id) and list_vaults lists the vaults. Each account has a vault limit and an hourly creation limit.

    Annotations the server declares

    • title: Create a vault
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • onboardIndex an existing product's codebase into this vault.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Index an existing product's codebase into this vault. {action: "start"} returns the onboarding playbook: a method for surveying the codebase and recording its product knowledge (domains, features, stories, specs, workflows, decisions, constraints) as concepts via upsert_concept, each anchored to the code with codeAreas. {action: "status", areaList} reports onboarded state, concept counts and, given your repo's source areas (Brainz can't read the repo), which areas are covered or uncovered. {action: "complete", summary, areaList} marks the vault onboarded and stores the summary; it is rejected while too many areas are uncovered. Until onboarding completes, search_concepts and get_context results include a one-line note saying so.

    Annotations the server declares

    • title: Onboard this vault
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • syncRe-index an onboarded vault after the code changes (drift).No findings

    Why it is in this group

    • The name "sync" says "sync": a word for a change.
    Description, as the server wrote it
    Re-index an onboarded vault after the code changes (drift). {action: "start"} returns the sync playbook: the vault's last_synced_at, a coverage map over the concepts' code_areas, and a method for re-indexing only what changed (you run git — Brainz can't read the repo — and pass back changedPaths + areaList): update stale concepts in place, add concepts or tasks for new work, and report coverage gaps. {action: "status", areaList} reports onboarded state, last sync time, staleness, concept counts and coverage. {action: "complete", summary, areaList} stamps last_synced_at and appends the summary to the product-onboarding-summary concept (a running sync log). After ~14 days without a sync, get_context and search results include a one-line note saying so.

    Annotations the server declares

    • title: Sync this vault to the current code
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • take_taskClaim a task and get its briefing in one call.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Claim a task and get its briefing in one call. Pass an `id` to claim a specific task, or omit it to claim the next open task (oldest open by createdAt then id). Atomically flips the task to "taken" and records takenBy/takenAt; errors if it's already taken or done. Returns the task and a get_context-style briefing for its part_of domain plus the concepts it realizes / is governed_by (with code_areas). complete_task marks it done.

    Annotations the server declares

    • title: Take a task off the pile
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
Only reads 7Show 7 read-only tools
  • get_conceptFetch one concept by exact id: full markdown body, metadata, and its direct graph neighbors (each with the relation that connects it).No findings

    Why it is in this group

    • The name "get_concept" says "get": a word for reading.
    Description, as the server wrote it
    Fetch one concept by exact id: full markdown body, metadata, and its direct graph neighbors (each with the relation that connects it). Use after search_concepts or when another note wiki-links an id you need in full. The neighbors list tells you what to fetch next. If you don't know the id, use search_concepts instead.

    Annotations the server declares

    • title: Get concept
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • get_contextAssemble a markdown briefing of the concepts most relevant to a query and/or explicit ids, expanded through the graph and trimmed to a token budget.No findings

    Why it is in this group

    • The name "get_context" says "get": a word for reading.
    Description, as the server wrote it
    Assemble a markdown briefing of the concepts most relevant to a query and/or explicit ids, expanded through the graph and trimmed to a token budget. The briefing is self-contained, so it can be handed to another agent or pasted into a prompt as-is. The final JSON line reports which concept ids were included, whether the bundle was truncated, and its approximate token count. Provide at least one of `query` or `ids`.

    Annotations the server declares

    • title: Assemble context bundle
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • list_conceptsEnumerate concept metadata (no bodies), optionally filtered by product, type, or a single tag.No findings

    Why it is in this group

    • The name "list_concepts" says "list": a word for reading.
    Description, as the server wrote it
    Enumerate concept metadata (no bodies), optionally filtered by product, type, or a single tag. Use to get the lay of the land in an unfamiliar vault, to audit what exists (e.g. all decisions for a product), or when search vocabulary isn't matching. For content, follow up with get_concept or get_context.

    Annotations the server declares

    • title: List concepts
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • list_tasksList the vault's work pile: `task`-type concepts with their lifecycle (open/taken/done), oldest first, including who has taken each one (takenBy).Reads private dataNo findings

    Why it is in this group

    • The name "list_tasks" says "list": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "list" and "vault": it reads secrets.
    Description, as the server wrote it
    List the vault's work pile: `task`-type concepts with their lifecycle (open/taken/done), oldest first, including who has taken each one (takenBy). Filter by taskStatus or by the domain the tasks are part_of. Read-only; take_task is what claims a task.

    Annotations the server declares

    • title: List tasks
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • search_conceptsSearch the product knowledge vault by free-text query.Reads private dataNo findings

    Why it is in this group

    • The name "search_concepts" says "search": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "search" and "vault": it reads secrets.
    Description, as the server wrote it
    Search the product knowledge vault by free-text query. Useful when you need product knowledge but don't yet know which concept ids exist. Returns ranked hits (id, title, type, score, snippet) only; get_concept returns one full note and get_context an assembled briefing. An empty hit list means nothing matched.

    Annotations the server declares

    • title: Search concepts
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • vault_statsSummarize the vault: counts of concepts and edges, the products and tags in use, a breakdown by concept type, and whether semantic search is available.Reads private dataNo findings

    Why it is in this group

    • The description's first verb is "summarize": a word for reading.

    What it can reach

    • private-dataThe name "vault_stats" says "vault": it reads secrets.
    • private-dataThe description's first sentence says "summarize" and "vault": it reads secrets.
    Description, as the server wrote it
    Summarize the vault: counts of concepts and edges, the products and tags in use, a breakdown by concept type, and whether semantic search is available. Useful for gauging how much knowledge is here and which product/tag filters exist.

    Annotations the server declares

    • title: Vault stats
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

3 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.

Reads private data3
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__brainz__link_concepts"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:23 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
11
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://brainz.brownmatter.ai/.well-known/oauth-protected-resource/mcp
Authorization servers
https://brainz.brownmatter.ai
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
yes
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 11 tools that change things (3 destructive, 2 irreversible, 6 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://brainz.brownmatter.ai/mcp: tools/list returned 18 tools to an anonymous client, including upsert_concept (destructive), delete_concept (destructive), dream (destructive), link_concepts (irreversible), burndown (irreversible) and 6 more

    What this check looks for

Posture changes

  1. Nov 20, 2026
    • Tools that change things, listed without credentials: 10 to 11
  2. Nov 6, 2026
    • Tools that change things, listed without credentials: 9 to 10

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. Tools that change things, listed without credentials: 10 -> 11.View diff
    • Tools that change things, listed without credentials: 10 to 11
  2. Tools1 added, 1 changed.+1 added~1 changedView diff
    • Added:create_vaultChanges things
    • Changed:dreamDeletes or cancelsdescriptioninputSchema
  3. PostureRemote posture changed. Tools that change things, listed without credentials: 9 -> 10.View diff
    • Tools that change things, listed without credentials: 9 to 10

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http brainz https://brainz.brownmatter.ai/mcp
claude mcp add --transport http brainz https://brainz.brownmatter.ai/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__brainz__search_concepts",
      "mcp__brainz__get_concept",
      "mcp__brainz__get_related",
      "mcp__brainz__get_context",
      "mcp__brainz__list_concepts",
      "mcp__brainz__vault_stats",
      "mcp__brainz__list_tasks"
    ],
    "ask": [
      "mcp__brainz__link_concepts",
      "mcp__brainz__onboard",
      "mcp__brainz__sync",
      "mcp__brainz__take_task",
      "mcp__brainz__complete_task",
      "mcp__brainz__create_task",
      "mcp__brainz__create_vault"
    ],
    "deny": [
      "mcp__brainz__upsert_concept",
      "mcp__brainz__delete_concept",
      "mcp__brainz__dream"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as brainz. Review it before you use it.

Capability tags behind 5 rules
  • mcp__brainz__search_concepts private-data
  • mcp__brainz__link_concepts outbound
  • mcp__brainz__vault_stats private-data
  • mcp__brainz__dream untrusted-input
  • mcp__brainz__list_tasks private-data

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/ai.brownmatter/brainz/verify?hash=a1bc871baa7935251c63d2e125aab8eb50dbdd513028b0ddc1ddaa6bb7665b7b" | jq -e '.changed == false'

Pinned hash a1bc871baa79, from Nov 10, 2026, 09:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/ai.brownmatter/brainz/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for ai.brownmatter/brainz
[![Anlyon Radar](https://radar.anlyon.com/badge/ai.brownmatter/brainz.svg)](https://radar.anlyon.com/servers/ai.brownmatter/brainz)

Source: MCP Registry. Synced Oct 29, 2026, 02:17 UTC.

Brainz MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Brainz MCP server safe?

No scan can promise that. What its definitions show: 17 tools, 10 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Brainz MCP server delete data?

Yes. 3 tools can delete, cancel or revoke something: upsert_concept, delete_concept and dream.

Can the Brainz MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: link_concepts.

What tools does the Brainz MCP server have?

17 tools: 3 destructive, 1 irreversible, 6 write, 7 read. upsert_concept, delete_concept, dream, link_concepts, onboard, sync, take_task, complete_task and 9 more.

Does the Brainz MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Brainz MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): link_concepts.

Has the Brainz MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.