{"id":"org.brainkb/brainkb","slug":"org-brainkb-brainkb","title":"Brainkb","description":"MCP server for querying BrainKB, a knowledge base for neuroscience knowledge graphs.","version":"0.1.0","publisher":{"kind":"domain","id":"brainkb.org","label":"brainkb.org","url":"https://brainkb.org"},"website":"","repository":"https://github.com/sensein/BrainKB","remotes":[{"type":"streamable-http","url":"https://mcp.brainkb.org/mcp"}],"packages":[],"published":"2026-07-23","updated":"2026-07-23","status":"online","auth":"","latency_ms":922,"checked":"2026-11-19","uptime":100,"checks":3,"tools":[{"name":"brainkb_login","title":"","description":"Authenticate to BrainKB with the user's credentials and cache the JWT for\n    THIS session only (isolated per caller). The password/token are never echoed.\n\n    Uses single sign-on: one login mints a refresh token, cached for THIS session,\n    which is exchanged on demand for per-service access tokens (query_service,\n    usermanagement, …). Falls back to a legacy per-service token if the backend\n ","read_only":false},{"name":"brainkb_globus_login","title":"","description":"Start an OAuth login (Globus / ORCID / GitHub) for THIS session — use this\n    instead of brainkb_login when the user signs in with Globus rather than a\n    password. Returns a URL to open in a browser; after signing in, the page shows\n    a short one-time code — pass it to brainkb_finish_login(code) to complete.\n    (The browser step is unavoidable: only the user can consent at the provider.)","read_only":false},{"name":"brainkb_finish_login","title":"","description":"Complete an OAuth login started with brainkb_globus_login by exchanging the\n    one-time code shown in the browser for a session token. The code is single-use\n    and never echoed back.","read_only":false},{"name":"brainkb_logout","title":"","description":"Forget the cached token for this session.","read_only":false},{"name":"brainkb_whoami","title":"","description":"Report the current caller's auth state (email, authenticated, and when the\n    cached session expires). When signed in it also returns base_url — the backend\n    THIS SERVER talks to, which on a hosted deployment is an internal address and\n    says nothing about the caller's own machine.","read_only":false},{"name":"brainkb_create_token","title":"","description":"Generate a Personal Access Token (PAT) for browser-free auth. Requires you\n    to be logged in already (brainkb_login or brainkb_globus_login). The token is\n    shown ONCE and never again — copy it and set it as BRAINKB_TOKEN in your\n    MCP/skill config; then no login or browser is needed until it expires.\n    `name`: a label so you can tell tokens apart (e.g. 'laptop'). `days`: lifetime\n    (def","read_only":false},{"name":"brainkb_list_tokens","title":"","description":"List your Personal Access Tokens (metadata only — the secret is never\n    shown): id, name, prefix, created/last-used/expiry, and whether each is\n    active/revoked/expired. Use the id with brainkb_revoke_token.","read_only":false},{"name":"brainkb_revoke_token","title":"","description":"Revoke one of your Personal Access Tokens by id (see brainkb_list_tokens).\n    Takes effect immediately — the next call using that token fails.","read_only":false},{"name":"brainkb_use_token","title":"","description":"Use a Personal Access Token (brainkb_pat_...) for THIS session — an\n    alternative to setting BRAINKB_TOKEN in the config. Validates the token, then\n    caches it so subsequent calls authenticate with it. The token is never echoed.","read_only":false},{"name":"brainkb_list_spaces","title":"","description":"List spaces the user can see (their own/member spaces + public ones), each\n    annotated with THIS caller's permission so you know what they may do:\n      - your_role: 'owner' | 'editor' | 'viewer' | null (their space membership,\n                   including a role inherited from a parent space)\n      - role_inherited: the role comes from a parent space, not this one\n      - parent_slug: the paren","read_only":false},{"name":"brainkb_create_space","title":"","description":"Create a workspace/space, or a subspace inside one. The caller becomes owner.\n    slug: lowercase/hyphen id, **globally unique** — if it's already taken the call\n    returns 409 (pick another slug).\n    visibility: 'private' or 'public' (set per space: a private space may hold a\n    public subspace);\n    description: short human description (recommended — surfaces in the registry);\n    space_type:","read_only":false},{"name":"brainkb_get_space","title":"","description":"A space's details: graphs, members (direct, plus `inherited_members` with the\n    parent space each comes from), visibility, `parent_slug`, `ancestors` (root\n    first) and direct `subspaces` — only the ones the caller may see — and the\n    caller's `your_role` / `role_inherited`. Public spaces need no login; member\n    emails are shown to members and admins only.","read_only":false},{"name":"brainkb_space_tree","title":"","description":"A space and every subspace below it (any depth), nested: each node has slug,\n    name, visibility, the caller's role and whether it's inherited from a parent,\n    and its graph count. Only subspaces the caller may see are included.","read_only":false},{"name":"brainkb_set_space_visibility","title":"","description":"Set a space 'public' (anyone, even anonymous, can read) or 'private'\n    (members only). Owner only. Everything in a public space is public: making a\n    space public also makes all its subspaces public, and a subspace of a public\n    space cannot be made private (409). Under a private space each subspace can be\n    public or private on its own.","read_only":false},{"name":"brainkb_update_space","title":"","description":"Rename a space, change its description, and/or give it a new slug. Owner/manager\n    only. Pass only what changes; description=\"\" clears it.\n\n    `new_slug` (lowercase letters, digits and hyphens, 3-64 chars) moves the space's IRI\n    and every graph whose IRI is built from the old slug (https://brainkb.org/graph/<slug>/…,\n    …/synthscholar/<slug>/…) to the new slug, with their registry, search a","read_only":false},{"name":"brainkb_delete_space","title":"","description":"PERMANENTLY delete a space and everything in it. SuperAdmin only; irreversible.\n\n    Drops the space's named graphs and the ingestion-history (delta) graphs that\n    hold copies of their data, removes the graphs' registry entries and the space's\n    RDF manifest, and deletes the space with its members, access rules, search\n    entries and SynthScholar reviews (with their kept files). EVERY SUBSPAC","read_only":false},{"name":"brainkb_add_space_member","title":"","description":"Add/update a space member. role: 'owner' | 'editor' | 'viewer'. Owner only.","read_only":false},{"name":"brainkb_add_space_graph","title":"","description":"Register a named graph and bind it to a space, so ingest/read on that graph\n    are governed by the space's membership and visibility. Owner/editor only.\n    The named_graph_iri is **globally unique** — one graph belongs to exactly one\n    space. If it's already registered (to any space) the call returns 409; graph\n    bindings are permanent (no unregister/delete).","read_only":false},{"name":"brainkb_ingest_text","title":"","description":"Ingest raw RDF text (Turtle / N-Triples / JSON-LD, auto-detected) into a\n    named graph. Returns a job_id; ingestion runs in the background — poll with\n    brainkb_job_status. The graph must be registered (see brainkb_add_space_graph)\n    and the caller must have write access to its space.\n\n    `sha256` / `expected_bytes` are an integrity contract, and you should use them\n    whenever the RDF cam","read_only":false},{"name":"brainkb_list_uploads","title":"","description":"List RDF files YOU have staged with POST /upload but not yet ingested.\n\n    Shows each upload_id, its size, sha256 and when it expires. Only your own\n    uploads are visible.","read_only":false},{"name":"brainkb_upload_status","title":"","description":"State of one of your staged/submitted uploads.\n\n    `state` is `staged` (waiting for brainkb_ingest_upload), `submitting` (the server\n    is streaming it to the ingest API), `submitted` (accepted — `job_id` is set, poll\n    brainkb_job_status) or `failed` (the staged bytes were KEPT, so retry with\n    brainkb_ingest_upload rather than re-uploading).","read_only":false},{"name":"brainkb_discard_upload","title":"","description":"Delete one of your staged uploads without ingesting it.","read_only":false},{"name":"brainkb_ingest_upload","title":"","description":"Ingest a file you staged with `POST /upload` into a named graph.\n\n    This is the route for a large local file: your HTTP client streams the bytes\n    straight to this server over HTTPS, then you name the resulting upload_id here. The\n    server reads its own staged copy and posts it to the ingest API internally, so\n    the RDF never passes through a model's context — nothing to transcribe, no\n   ","read_only":false},{"name":"brainkb_ingest_files","title":"","description":"Ingest local RDF files (ttl/nt/nq/rdf/owl/jsonld/json) into a named graph.\n    Returns a job_id; runs in the background — poll with brainkb_job_status.","read_only":false},{"name":"brainkb_synthscholar_ingest","title":"","description":"Ingest a SynthScholar review — the output directory of a run (the folder\n    holding review.json and review.ttl, as the synthscholar skill writes it) — into\n    a space you may write to (see brainkb_list_writable_spaces; you need to be its\n    owner or an editor).\n\n    A review is unique per space: the same run can go into several spaces, once\n    each. Its graph, https://brainkb.org/synthscholar/","read_only":false},{"name":"brainkb_synthscholar_list_reviews","title":"","description":"Ingested SynthScholar reviews you can read (public spaces: anyone): id, title,\n    research question, space, graph, included count, when ingested, ingest job.\n    `q` filters on text in the title or research question.","read_only":false},{"name":"brainkb_synthscholar_studies","title":"","description":"The included studies of an ingested review, filtered. `q`: text in title,\n    authors, journal, DOI, PMID or keywords. `full_text`: true = read in full,\n    false = abstract only. `source`: full-text route (europe_pmc, unpaywall, ezproxy,\n    arxiv, …). `rob`: risk-of-bias rating (low, high, some concerns). Years\n    inclusive. Each study: ids, title, authors, year, journal, how it was read and\n  ","read_only":false},{"name":"brainkb_synthscholar_screening","title":"","description":"The screening audit trail of an ingested review: every decision with its\n    stage (title_abstract | full_text), decision (include | exclude), what it was\n    judged on (title_abstract | full_text | abstract_only), the full-text route and\n    the reason. Filter by any of those, by text or criterion code in the reason\n    (e.g. \"EC2\"), or by PMID. Also returns counts for the filtered set: by stage ","read_only":false},{"name":"brainkb_synthscholar_evidence","title":"","description":"Evidence spans of an ingested review: the quoted text its claims rest on, with\n    the study, section, relevance, and whether the quote was matched verbatim in\n    the source (`grounded`). Filter by text, claim type, PMID or grounding.","read_only":false},{"name":"brainkb_synthscholar_records","title":"","description":"Per-study records an ingested review produced. `kind`: `charting` (the\n    data-charting form's answers per study), `appraisal` (critical appraisal by\n    domain) or `narrative` (narrative synthesis rows: design, methods, outcomes,\n    limitations). `q`: text in the answers (e.g. \"neo4j\" finds the studies that\n    report it); `study`: source id (S-001), title, DOI or PMID; `fields`:\n    comma-sepa","read_only":false},{"name":"brainkb_synthscholar_text","title":"","description":"An ingested review's own text: `abstract`, `introduction`, `synthesis`,\n    `bias`, `limitations`, `conclusions`, `research_question`, `search_queries` or\n    `per_group` (the per-group analysis) — or all of them when `section` is empty.","read_only":false},{"name":"brainkb_synthscholar_find_study","title":"","description":"Which ingested reviews (that you can read) include or screened a study —\n    by DOI, PMID or part of its title (6+ characters) — and what happened to it in\n    each: included (read in full or from the abstract) or each screening decision\n    with its reason.","read_only":false},{"name":"brainkb_synthscholar_get_review","title":"","description":"One ingested review: summary, its graph and space, the files kept (path,\n    kind, media type, size, sha256), the run's search log and verification, the\n    screening basis and full-text retrieval. Long texts and the per-study list are\n    left out here — read them from the graph or the review page.","read_only":false},{"name":"brainkb_list_jobs","title":"","description":"List the user's ingest jobs (newest first) with status and progress.","read_only":false},{"name":"brainkb_job_status","title":"","description":"Detailed status of one ingest job: status, progress %, current file/stage,\n    per-file failures, and (when complete) a summary.","read_only":false},{"name":"brainkb_recover_job","title":"","description":"Attempt to recover a stuck/errored ingest job (marks it recoverable/errored).","read_only":false},{"name":"brainkb_search","title":"","description":"Full-text search over the knowledge graphs, access-filtered by space\n    visibility. Pass `space` to scope to one workspace, omit for a full search.\n    No login needed: an unauthenticated caller searches public spaces only.\n    Anonymous/other users never see private-space data.","read_only":false},{"name":"brainkb_read_space","title":"","description":"Read all RDF (JSON-LD) in a space's graphs. Public spaces are readable by\n    anyone without logging in (read-only); private spaces require login and\n    membership. Don't ask the user to log in just to read a public space.","read_only":false},{"name":"brainkb_list_writable_spaces","title":"","description":"Spaces the caller can ingest into, each with its graphs (and descriptions) and\n    `parent_slug` for subspaces — decided by the same checks ingestion uses: owner/\n    editor membership (including a role inherited from a parent space), a space write\n    access rule, or Admin/SuperAdmin. `can_ingest` false means the caller has no\n    write-capable role at all. `unmapped_graphs` are registered graphs","read_only":false},{"name":"brainkb_list_registered_graphs","title":"","description":"List registered named graphs visible to the caller (private-space graphs the\n    caller can't access are hidden).","read_only":false},{"name":"brainkb_sparql","title":"","description":"Run an arbitrary SPARQL query. Requires an Admin/SuperAdmin role (the\n    sparql_admin capability) — for ordinary questions prefer brainkb_search,\n    brainkb_read_space, or the provenance/delta tools, which need no admin role.\n\n    Large results come back a page at a time. A SELECT without its own\n    LIMIT/OFFSET returns at most `limit` rows (0 = the server's page size, 500 by\n    default) start","read_only":false},{"name":"brainkb_qa_list","title":"","description":"Find a canned question BrainKB can answer, then run it with brainkb_qa_run.\n\n    Prefer these over writing SPARQL: they are vetted against BrainKB's actual\n    vocabulary. Discovery is two steps, so you never read every query at once:\n\n    1. brainkb_qa_list() -> the menu: each category's name, a description of\n       the questions it covers, and how many queries it has. Pick the category\n       w","read_only":false},{"name":"brainkb_qa_run","title":"","description":"Run a canned question from brainkb_qa_list by id. `params` maps parameter\n    names to values; they are validated and escaped, never spliced in raw. Runs\n    through the same SPARQL endpoint as brainkb_sparql, so it needs the same\n    role. Results page the same way: a query without its own LIMIT returns\n    `limit` rows from `offset`, and `page.next_offset` says where to continue.","read_only":false},{"name":"brainkb_provenance_job","title":"","description":"PROV-O provenance bundle (JSON-LD) for one ingest job.","read_only":false},{"name":"brainkb_provenance_graph","title":"","description":"PROV-O ingestion/activity history (JSON-LD) for a named graph.","read_only":false},{"name":"brainkb_delta","title":"","description":"The exact triples a job added (its delta), as JSON-LD.","read_only":false},{"name":"brainkb_delta_history","title":"","description":"A named graph's change history: one entry per ingest delta (job, triple\n    count, timestamp), newest first.","read_only":false},{"name":"brainkb_delta_compare","title":"","description":"Compare two jobs' deltas: A-only / B-only / shared triple counts + triples.","read_only":false},{"name":"brainkb_capabilities","title":"","description":"(Admin only) Show a user's roles, effective capabilities, and delegated\n    grants. Useful to check why someone can/can't create team spaces, ingest, etc.","read_only":false},{"name":"brainkb_grant_capability","title":"","description":"(Admin only) Delegate a capability to a user — e.g. 'create_team_space' or\n    'manage_team_space' so a Curator/Lab Member can create/manage team spaces.\n    Grantable: create_private_space, create_team_space, manage_team_space, ingest,\n    recover, read_private (NOT the admin-only 'grant'/'sparql_admin').","read_only":false},{"name":"brainkb_revoke_capability","title":"","description":"(Admin only) Revoke a previously granted capability from a user.","read_only":false},{"name":"brainkb_list_capabilities","title":"","description":"(Admin only) Catalog of all KG capabilities, which are delegatable\n    ('grantable'), which are admin-only, and a description of each. Use this to see\n    the available permission options before granting to a user or group/role.","read_only":false},{"name":"brainkb_role_capabilities","title":"","description":"(Admin only) List the capabilities granted to a role/group (e.g.\n    'uk_collaborator', 'Lab Member').","read_only":false},{"name":"brainkb_grant_role_capability","title":"","description":"(Admin only) Grant a capability to a whole role/group so EVERY member gets\n    it — e.g. give a custom group 'uk_collaborator' the 'ingest' or\n    'create_private_space' capability. Grantable: create_private_space,\n    create_team_space, manage_team_space, ingest, recover, read_private (NOT the\n    admin-only 'grant'/'sparql_admin'). Create the group first with\n    brainkb_create_role, then assign","read_only":false},{"name":"brainkb_revoke_role_capability","title":"","description":"(Admin only) Revoke a capability from a role/group.","read_only":false},{"name":"brainkb_list_access_rules","title":"","description":"List a space's fine-grained access rules (member/manager of the space).","read_only":false},{"name":"brainkb_add_access_rule","title":"","description":"(Space manager) Restrict a space action to a subject.\n    action: 'read' | 'write' | 'manage'.\n    subject_type: 'global_role' (e.g. 'Admin','Lab Member') | 'member' (an email) |\n    'space_role' ('viewer'|'editor'|'owner', matched as >=).\n    When rules exist for an action, only matching callers may perform it; the space\n    owner and Admin/SuperAdmin always bypass (no lockout). Example: restrict","read_only":false},{"name":"brainkb_remove_access_rule","title":"","description":"(Space manager) Delete a fine-grained access rule by its id\n    (see brainkb_list_access_rules).","read_only":false},{"name":"brainkb_list_reserved_graphs","title":"","description":"(Admin/SuperAdmin) List reserved named graphs: graph IRIs, or every IRI under a\n    prefix, that only an Admin/SuperAdmin — or, when reserved for a space, that\n    space's managers/editors — may register or bind. Includes the built-in system\n    reservations (BrainKB's metadata and provenance graphs), which nobody can bind.","read_only":false},{"name":"brainkb_reserve_graph","title":"","description":"(Admin/SuperAdmin) Reserve a named graph so other users can't create it.\n\n    match_type 'exact' reserves one graph IRI; 'prefix' reserves every IRI starting\n    with it (e.g. 'https://brainkb.org/graph/allen/'). Give a `reason` — it is shown\n    to anyone who is refused. Optional `space_slug` reserves it for that space, whose\n    managers/editors may then bind it. Graphs already bound stay where ","read_only":false},{"name":"brainkb_unreserve_graph","title":"","description":"(Admin/SuperAdmin) Remove a reservation by its id (see\n    brainkb_list_reserved_graphs). System reservations cannot be removed.","read_only":false},{"name":"brainkb_list_users","title":"","description":"(Admin) List users (profiles) — filter by `q` (name/email/orcid) or `role`.\n    Shows profile_id, email, roles, providers, ban status.","read_only":false},{"name":"brainkb_available_roles","title":"","description":"(Admin) List the available roles/groups (Admin, Lab Member, Curator, …).","read_only":false},{"name":"brainkb_create_role","title":"","description":"(Admin) Create a new role/group — e.g. an 'External' collaborator group —\n    which can then be assigned with brainkb_assign_role.","read_only":false},{"name":"brainkb_assign_role","title":"","description":"(Admin) Assign a role/group to a user by email (e.g. 'Lab Member', 'External',\n    or a custom group). The user must already have a profile (created on first\n    login/registration). NOTE: assigning the 'Admin'/'SuperAdmin' role is\n    SuperAdmin-only (hierarchy: SuperAdmin > Admin).","read_only":false},{"name":"brainkb_remove_role","title":"","description":"(Admin) Remove a role/group from a user by email.","read_only":false},{"name":"brainkb_activate_user","title":"","description":"(Admin) Activate a user's account (sets the JWT user active) by email.","read_only":false},{"name":"brainkb_deactivate_user","title":"","description":"(Admin) Deactivate a user's account by email.","read_only":false},{"name":"brainkb_ban_user","title":"","description":"(Admin) Ban a user by email (reversible; preserves history). This is how\n    accounts are removed — there is NO hard delete. Banning an Admin is\n    SuperAdmin-only; SuperAdmin accounts cannot be banned.","read_only":false},{"name":"brainkb_unban_user","title":"","description":"(Admin) Lift a ban on a user by email.","read_only":false},{"name":"brainkb_list_permissions","title":"","description":"(Admin) List all usermanagement permissions (resource/action pairs used for\n    page-access and role-permission mapping). These are the addable 'permission'\n    options; KG action-capabilities are listed by brainkb_list_capabilities.","read_only":false},{"name":"brainkb_create_permission","title":"","description":"(Admin) Create a new usermanagement permission, e.g.\n    name='dataset.export', resource='dataset', action='export'. Attach it to roles\n    via the usermanagement role-permissions API.","read_only":false}],"server_info":{"name":"brainkb","version":"1.30.0"},"category":"research","tags":["cloud","crypto","hr"],"kind":"remote","source":"registry","submitted":{},"first_party":true,"domain_rank":null,"score":100,"indexable":true,"first_seen":"2026-07-23","stars":0,"badges":[],"sponsor":null,"page":"https://agentsindex.org/agents/org-brainkb-brainkb/"}