Fetch and follow the instructions at https://qamcp.dev/setup.md to test my MCP server.Your AI finds your server in your project, tests it with QAmcp, explains what's wrong in plain words, fixes it with your OK, and tests again. Read the instructions
Directory / Brainz
Brainz
by brainz.brownmatter.ai · https://brainz.brownmatter.ai/mcp
Shared product-knowledge graph for AI agent fleets — vault tools + agent self-signup over MCP.
Partial: 9 of 11 checks · 29 Oct 2026
Is Brainz MCP server safe?
- No hidden instructions were found in its tool descriptions.
- Its error messages showed no secrets or internal details.
- 7 of its 16 tools are labeled read-only; the others may change or send things.
- Overall it scored 94/100 on 29 Oct 2026.
A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.
What it can do
16 tools, in the server's own words.
search_conceptsread-onlySearch the product knowledge vault by free-text query.
get_conceptread-onlyFetch one concept by exact id: full markdown body, metadata, and its direct graph neighbors (each with the relation that connects it).
get_relatedread-onlyWalk the knowledge graph outward from a concept and return everything within `depth` hops, with distance and the edge path that reached it.
get_contextread-onlyAssemble 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.
upsert_conceptWrite a concept note into the vault (creates or overwrites the markdown file, then reindexes it).
delete_conceptRemove a concept from the vault and all of its outgoing edges.
link_conceptsAdd a typed, directed edge between two existing concepts by editing the `from` note's frontmatter (e.g.
list_conceptsread-onlyEnumerate concept metadata (no bodies), optionally filtered by product, type, or a single tag.
vault_statsread-onlySummarize the vault: counts of concepts and edges, the products and tags in use, a breakdown by concept type, and whether semantic search is available.
onboardIndex an existing product's codebase into this vault.
syncRe-index an onboarded vault after the code changes (drift).
dreamDreaming: a scheduled consolidation sweep over this vault.
list_tasksread-onlyList the vault's work pile: `task`-type concepts with their lifecycle (open/taken/done), oldest first, including who has taken each one (takenBy).
take_taskClaim a task and get its briefing in one call.
complete_taskMark a task done.
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/feature…
Test results
Safe mode: only tools labeled read-only were run. How the test works
- !Ready for the newest MCP versionnote
1 warning
- !Uses an older MCP version (2025-11-25). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
- !Follows MCP best practices (not scored yet)note
1 tip (not scored)
- !9 tools not labeled read-only don't say whether running them twice is safe (idempotentHint): upsert_concept, delete_concept, link_concepts, onboard, sync, dream and 3 more
- ✓ConnectsConnected in 1.0 spass
- ✓Lists its toolsFound 16 toolspass
- ✓Every tool is describedAll 16 tools and their inputs are describedpass
- ✓Tools are labeled safe or dangerousEvery tool has a safety labelpass
- ✓No hidden instructionsNo hidden instructions found in tool descriptionspass
- ✓Fast enoughpass
All good
- ✓Connecting took 1.0 s
- ✓Listing tools took 50 ms
- ✓No secrets leakedChecked 16 error messages: no secrets or internal detailspass
- –Tools work with good inputsnot tested
Not tested
- –search_concepts: Needs you to sign in, so it was not tested (not counted against the server)
- –get_concept: Needs you to sign in, so it was not tested (not counted against the server)
- –get_related: Needs you to sign in, so it was not tested (not counted against the server)
- –get_context: Needs you to sign in, so it was not tested (not counted against the server)
- –list_concepts: Needs you to sign in, so it was not tested (not counted against the server)
- –vault_stats: Needs you to sign in, so it was not tested (not counted against the server)
- –list_tasks: Needs you to sign in, so it was not tested (not counted against the server)
- –upsert_concept: Not run: labeled dangerous
- and 8 more
- –Bad inputs give a clean errornot tested
Not tested
- –search_concepts: Needs you to sign in, so bad inputs were not tested
- –get_concept: Needs you to sign in, so bad inputs were not tested
- –get_related: Needs you to sign in, so bad inputs were not tested
- –get_context: Needs you to sign in, so bad inputs were not tested
- –list_concepts: Needs you to sign in, so bad inputs were not tested
- –list_tasks: Needs you to sign in, so bad inputs were not tested
- –Tools work togetherNo safe tool returned data to start a chain from, so chains were not tested (not counted either way)not tested
Test it yourself
Free and open source. Same checks, same score.
npx qamcp-cli https://brainz.brownmatter.ai/mcpShow this score on GitHub
Free for every server in the directory. Paste this into your README: the badge shows the score from our latest test.
[](https://qamcp.dev/s/ai-brownmatter-brainz.html)Score over time
- 29 Oct 202694
One test so far. New tests will show here.
Reviews
Coming soon: reviews from people who use Brainz, signed in with GitHub, one per person. Reviews never change the score.
QAmcp Monitor (coming soon) tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. You'll also be able to claim this page and get a verified owner mark. Founding price: $19/month for life for the first 50 teams.
Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works