이 MCP로 할 수 있는 일
Manages and queries neuroscience knowledge graphs, including RDF ingestion, named graphs, jobs, spaces, memberships, roles, and access controls.
기능
도구
55
도구
brainkb_activate_user
(Admin) Activate a user's account (sets the JWT user active) by email.
입력 스키마
{'type': 'object', 'title': 'brainkb_activate_userArguments', 'required': ['email'], 'properties': {'email': {'type': 'string', 'title': 'Email'}}}
brainkb_add_access_rule
(Space manager) Restrict a space action to a subject.
action: 'read' | 'write' | 'manage'.
subject_type: 'global_role' (e.g. 'Admin','Lab Member') | 'member' (an email) |
'space_role' ('viewer'|'editor'|'owner', matched as >=).
When rules exist for an action, only matching callers may perform it; the space
owner and Admin/SuperAdmin always bypass (no lockout). Example: restrict writing
to Admins -> action='write', subject_type='global_role', subject_value='Admin'.
입력 스키마
{'type': 'object', 'title': 'brainkb_add_access_ruleArguments', 'required': ['slug', 'action', 'subject_type', 'subject_value'], 'properties': {'slug': {'type': 'string', 'title': 'Slug'}, 'action': {'type': 'string', 'title': 'Action'}, 'subject_type': {'type': 'string', 'title': 'Subject Type'}, 'subject_value': {'type': 'string', 'title': 'Subject Value'}}}
brainkb_add_space_graph
Register a named graph and bind it to a space, so ingest/read on that graph
are governed by the space's membership and visibility. Owner/editor only.
The named_graph_iri is **globally unique** â one graph belongs to exactly one
space. If it's already registered (to any space) the call returns 409; graph
bindings are permanent (no unregister/delete).
입력 스키마
{'type': 'object', 'title': 'brainkb_add_space_graphArguments', 'required': ['slug', 'named_graph_iri'], 'properties': {'slug': {'type': 'string', 'title': 'Slug'}, 'description': {'type': 'string', 'title': 'Description', 'default': ''}, 'named_graph_iri': {'type': 'string', 'title': 'Named Graph Iri'}}}
brainkb_add_space_member
Add/update a space member. role: 'owner' | 'editor' | 'viewer'. Owner only.
입력 스키마
{'type': 'object', 'title': 'brainkb_add_space_memberArguments', 'required': ['slug', 'member_email'], 'properties': {'role': {'type': 'string', 'title': 'Role', 'default': 'viewer'}, 'slug': {'type': 'string', 'title': 'Slug'}, 'member_email': {'type': 'string', 'title': 'Member Email'}}}
brainkb_assign_role
(Admin) Assign a role/group to a user by email (e.g. 'Lab Member', 'External',
or a custom group). The user must already have a profile (created on first
login/registration). NOTE: assigning the 'Admin'/'SuperAdmin' role is
SuperAdmin-only (hierarchy: SuperAdmin > Admin).
입력 스키마
{'type': 'object', 'title': 'brainkb_assign_roleArguments', 'required': ['email', 'role'], 'properties': {'role': {'type': 'string', 'title': 'Role'}, 'email': {'type': 'string', 'title': 'Email'}}}
brainkb_available_roles
(Admin) List the available roles/groups (Admin, Lab Member, Curator, â¦).
입력 스키마
{'type': 'object', 'title': 'brainkb_available_rolesArguments', 'properties': {}}
brainkb_ban_user
(Admin) Ban a user by email (reversible; preserves history). This is how
accounts are removed â there is NO hard delete. Banning an Admin is
SuperAdmin-only; SuperAdmin accounts cannot be banned.
입력 스키마
{'type': 'object', 'title': 'brainkb_ban_userArguments', 'required': ['email', 'reason'], 'properties': {'email': {'type': 'string', 'title': 'Email'}, 'reason': {'type': 'string', 'title': 'Reason'}}}
brainkb_capabilities
(Admin only) Show a user's roles, effective capabilities, and delegated
grants. Useful to check why someone can/can't create team spaces, ingest, etc.
입력 스키마
{'type': 'object', 'title': 'brainkb_capabilitiesArguments', 'required': ['member'], 'properties': {'member': {'type': 'string', 'title': 'Member'}}}
brainkb_create_permission
(Admin) Create a new usermanagement permission, e.g.
name='dataset.export', resource='dataset', action='export'. Attach it to roles
via the usermanagement role-permissions API.
입력 스키마
{'type': 'object', 'title': 'brainkb_create_permissionArguments', 'required': ['name', 'resource', 'action'], 'properties': {'name': {'type': 'string', 'title': 'Name'}, 'action': {'type': 'string', 'title': 'Action'}, 'resource': {'type': 'string', 'title': 'Resource'}, 'description': {'type': 'string', 'title': 'Description', 'default': ''}}}
brainkb_create_role
(Admin) Create a new role/group â e.g. an 'External' collaborator group â
which can then be assigned with brainkb_assign_role.
입력 스키마
{'type': 'object', 'title': 'brainkb_create_roleArguments', 'required': ['name'], 'properties': {'name': {'type': 'string', 'title': 'Name'}, 'category': {'type': 'string', 'title': 'Category', 'default': 'Content'}, 'description': {'type': 'string', 'title': 'Description', 'default': ''}}}
brainkb_create_space
Create a workspace/space. The caller becomes owner.
slug: lowercase/hyphen id, **globally unique** â if it's already taken the call
returns 409 (pick another slug; slugs are never reused/deleted).
visibility: 'private' or 'public';
description: short human description (recommended â surfaces in the registry);
space_type: 'individual' (a personal space â any write-capable role) or 'team'
(a shared space â only Admin/SuperAdmin, or a user granted create_team_space).
입력 스키마
{'type': 'object', 'title': 'brainkb_create_spaceArguments', 'required': ['slug', 'name'], 'properties': {'name': {'type': 'string', 'title': 'Name'}, 'slug': {'type': 'string', 'title': 'Slug'}, 'space_type': {'type': 'string', 'title': 'Space Type', 'default': 'individual'}, 'visibility': {'type': 'string', 'title': 'Visibility', 'default': 'private'}, 'description': {'type': 'string', 'title': 'Description', 'default': ''}}}
brainkb_create_token
Generate a Personal Access Token (PAT) for browser-free auth. Requires you
to be logged in already (brainkb_login or brainkb_globus_login). The token is
shown ONCE and never again â copy it and set it as BRAINKB_TOKEN in your
MCP/skill config; then no login or browser is needed until it expires.
`name`: a label so you can tell tokens apart (e.g. 'laptop'). `days`: lifetime
(default 90, server-capped). Treat the returned token like a password.
입력 스키마
{'type': 'object', 'title': 'brainkb_create_tokenArguments', 'properties': {'days': {'type': 'integer', 'title': 'Days', 'default': 90}, 'name': {'type': 'string', 'title': 'Name', 'default': ''}}}
brainkb_deactivate_user
(Admin) Deactivate a user's account by email.
입력 스키마
{'type': 'object', 'title': 'brainkb_deactivate_userArguments', 'required': ['email'], 'properties': {'email': {'type': 'string', 'title': 'Email'}}}
brainkb_delta
The exact triples a job added (its delta), as JSON-LD.
입력 스키마
{'type': 'object', 'title': 'brainkb_deltaArguments', 'required': ['job_id'], 'properties': {'job_id': {'type': 'string', 'title': 'Job Id'}}}
brainkb_delta_compare
Compare two jobs' deltas: A-only / B-only / shared triple counts + triples.
입력 스키마
{'type': 'object', 'title': 'brainkb_delta_compareArguments', 'required': ['job_id_a', 'job_id_b'], 'properties': {'job_id_a': {'type': 'string', 'title': 'Job Id A'}, 'job_id_b': {'type': 'string', 'title': 'Job Id B'}}}
brainkb_delta_history
A named graph's change history: one entry per ingest delta (job, triple
count, timestamp), newest first.
입력 스키마
{'type': 'object', 'title': 'brainkb_delta_historyArguments', 'required': ['named_graph_iri'], 'properties': {'named_graph_iri': {'type': 'string', 'title': 'Named Graph Iri'}}}
brainkb_discard_upload
Delete one of your staged uploads without ingesting it.
입력 스키마
{'type': 'object', 'title': 'brainkb_discard_uploadArguments', 'required': ['upload_id'], 'properties': {'upload_id': {'type': 'string', 'title': 'Upload Id'}}}
brainkb_finish_login
Complete an OAuth login started with brainkb_globus_login by exchanging the
one-time code shown in the browser for a session token. The code is single-use
and never echoed back.
입력 스키마
{'type': 'object', 'title': 'brainkb_finish_loginArguments', 'required': ['code'], 'properties': {'code': {'type': 'string', 'title': 'Code'}, 'base_url': {'type': 'string', 'title': 'Base Url', 'default': ''}}}
출력 스키마
{'type': 'object', 'title': 'brainkb_finish_loginOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
brainkb_globus_login
Start an OAuth login (Globus / ORCID / GitHub) for THIS session â use this
instead of brainkb_login when the user signs in with Globus rather than a
password. Returns a URL to open in a browser; after signing in, the page shows
a short one-time code â pass it to brainkb_finish_login(code) to complete.
(The browser step is unavoidable: only the user can consent at the provider.)
입력 스키마
{'type': 'object', 'title': 'brainkb_globus_loginArguments', 'properties': {'base_url': {'type': 'string', 'title': 'Base Url', 'default': ''}, 'provider': {'type': 'string', 'title': 'Provider', 'default': 'globus'}}}
출력 스키마
{'type': 'object', 'title': 'brainkb_globus_loginOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
brainkb_grant_capability
(Admin only) Delegate a capability to a user â e.g. 'create_team_space' or
'manage_team_space' so a Curator/Lab Member can create/manage team spaces.
Grantable: create_private_space, create_team_space, manage_team_space, ingest,
recover, read_private (NOT the admin-only 'grant'/'sparql_admin').
입력 스키마
{'type': 'object', 'title': 'brainkb_grant_capabilityArguments', 'required': ['member', 'capability'], 'properties': {'member': {'type': 'string', 'title': 'Member'}, 'capability': {'type': 'string', 'title': 'Capability'}}}
brainkb_grant_role_capability
(Admin only) Grant a capability to a whole role/group so EVERY member gets
it â e.g. give a custom group 'uk_collaborator' the 'ingest' or
'create_private_space' capability. Grantable: create_private_space,
create_team_space, manage_team_space, ingest, recover, read_private (NOT the
admin-only 'grant'/'sparql_admin'). Create the group first with
brainkb_create_role, then assign it to users with brainkb_assign_role.
입력 스키마
{'type': 'object', 'title': 'brainkb_grant_role_capabilityArguments', 'required': ['role', 'capability'], 'properties': {'role': {'type': 'string', 'title': 'Role'}, 'capability': {'type': 'string', 'title': 'Capability'}}}
brainkb_ingest_files
Ingest local RDF files (ttl/nt/nq/rdf/owl/jsonld/json) into a named graph.
Returns a job_id; runs in the background â poll with brainkb_job_status.
입력 스키마
{'type': 'object', 'title': 'brainkb_ingest_filesArguments', 'required': ['named_graph_iri', 'file_paths'], 'properties': {'file_paths': {'type': 'array', 'items': {'type': 'string'}, 'title': 'File Paths'}, 'max_concurrency': {'type': 'integer', 'title': 'Max Concurrency', 'default': 8}, 'named_graph_iri': {'type': 'string', 'title': 'Named Graph Iri'}}}
brainkb_ingest_text
Ingest raw RDF text (Turtle / N-Triples / JSON-LD, auto-detected) into a
named graph. Returns a job_id; ingestion runs in the background â poll with
brainkb_job_status. The graph must be registered (see brainkb_add_space_graph)
and the caller must have write access to its space.
`sha256` / `expected_bytes` are an integrity contract, and you should use them
whenever the RDF came from a file. Ingest is append-only â no delete for
triples, no unregister for a graph â so RDF that arrives here mangled is
permanent. Because `data` is a string, it passes through the caller's context,
where dense Turtle is exactly what gets silently altered: ligatures, Greek
letters, embedded newlines, escaped quotes. Declare the digest of the bytes you
MEANT to send (`shasum -a 256 file.ttl`) and this refuses the write on any
mismatch, turning an unrecoverable corruption into a clean rejection.
입력 스키마
{'type': 'object', 'title': 'brainkb_ingest_textArguments', 'required': ['named_graph_iri', 'data'], 'properties': {'data': {'type': 'string', 'title': 'Data'}, 'sha256': {'type': 'string', 'title': 'Sha256', 'default': ''}, 'expected_bytes': {'type': 'integer', 'title': 'Expected Bytes', 'default': 0}, 'named_graph_iri': {'type': 'string', 'title': 'Named Graph Iri'}}}
brainkb_ingest_upload
Ingest a file you staged with `POST /upload` into a named graph.
This is the route for a large local file: your HTTP client streams the bytes
straight to this server over HTTPS, then you name the resulting upload_id here. The
server reads its own staged copy and posts it to the ingest API internally, so
the RDF never passes through a model's context â nothing to transcribe, no
context-window ceiling, and no reason to split the document (splitting breaks
blank-node identity and silently detaches triples, permanently).
Stage a file with any HTTP client â the point is that the LIBRARY reads the file,
so the bytes never pass through a model:
import requests, hashlib, pathlib
f = pathlib.Path("review.ttl")
r = requests.post(
"https://mcp.brainkb.org/upload",
params={"filename": f.name,
"sha256": hashlib.sha256(f.read_bytes()).hexdigest()},
headers={"Authorization": f"Bearer {TOKEN}"},
data=f.open("rb"), # streamed â never loaded into memory
)
print(r.json()) # -> {"upload_id": "up_...", "state": "staged"}
It returns an upload_id and the sha256 the server computed â compare it with your
own before ingesting.
Returns a job_id; poll brainkb_job_status, then reconcile brainkb_delta(job_id)
against the triple count you expected. The staged copy is deleted once the
ingest API has accepted the bytes.
입력 스키마
{'type': 'object', 'title': 'brainkb_ingest_uploadArguments', 'required': ['named_graph_iri', 'upload_id'], 'properties': {'upload_id': {'type': 'string', 'title': 'Upload Id'}, 'named_graph_iri': {'type': 'string', 'title': 'Named Graph Iri'}}}
brainkb_job_status
Detailed status of one ingest job: status, progress %, current file/stage,
per-file failures, and (when complete) a summary.
입력 스키마
{'type': 'object', 'title': 'brainkb_job_statusArguments', 'required': ['job_id'], 'properties': {'job_id': {'type': 'string', 'title': 'Job Id'}}}
brainkb_list_access_rules
List a space's fine-grained access rules (member/manager of the space).
입력 스키마
{'type': 'object', 'title': 'brainkb_list_access_rulesArguments', 'required': ['slug'], 'properties': {'slug': {'type': 'string', 'title': 'Slug'}}}
brainkb_list_capabilities
(Admin only) Catalog of all KG capabilities, which are delegatable
('grantable'), which are admin-only, and a description of each. Use this to see
the available permission options before granting to a user or group/role.
입력 스키마
{'type': 'object', 'title': 'brainkb_list_capabilitiesArguments', 'properties': {}}
brainkb_list_jobs
List the user's ingest jobs (newest first) with status and progress.
입력 스키마
{'type': 'object', 'title': 'brainkb_list_jobsArguments', 'properties': {'limit': {'type': 'integer', 'title': 'Limit', 'default': 50}}}
brainkb_list_permissions
(Admin) List all usermanagement permissions (resource/action pairs used for
page-access and role-permission mapping). These are the addable 'permission'
options; KG action-capabilities are listed by brainkb_list_capabilities.
입력 스키마
{'type': 'object', 'title': 'brainkb_list_permissionsArguments', 'properties': {}}
brainkb_list_registered_graphs
List registered named graphs visible to the caller (private-space graphs the
caller can't access are hidden).
입력 스키마
{'type': 'object', 'title': 'brainkb_list_registered_graphsArguments', 'properties': {}}
brainkb_list_spaces
List spaces the user can see (their own/member spaces + public ones), each
annotated with THIS caller's permission so you know what they may do:
- your_role: 'owner' | 'editor' | 'viewer' | null (their space membership)
- is_owner: they own the space
- access: 'owner' | 'member' | 'public' (how it's available to them)
- can_write: their space role permits ingest (owner/editor) â a real ingest
also needs the 'ingest' capability + any per-space access rules.
Use this to tell the user which spaces they can read vs. write vs. only see as
public.
입력 스키마
{'type': 'object', 'title': 'brainkb_list_spacesArguments', 'properties': {}}
brainkb_list_tokens
List your Personal Access Tokens (metadata only â the secret is never
shown): id, name, prefix, created/last-used/expiry, and whether each is
active/revoked/expired. Use the id with brainkb_revoke_token.
입력 스키마
{'type': 'object', 'title': 'brainkb_list_tokensArguments', 'properties': {}}
brainkb_list_uploads
List RDF files YOU have staged with POST /upload but not yet ingested.
Shows each upload_id, its size, sha256 and when it expires. Only your own
uploads are visible.
입력 스키마
{'type': 'object', 'title': 'brainkb_list_uploadsArguments', 'properties': {}}
brainkb_list_users
(Admin) List users (profiles) â filter by `q` (name/email/orcid) or `role`.
Shows profile_id, email, roles, providers, ban status.
입력 스키마
{'type': 'object', 'title': 'brainkb_list_usersArguments', 'properties': {'q': {'type': 'string', 'title': 'Q', 'default': ''}, 'role': {'type': 'string', 'title': 'Role', 'default': ''}, 'limit': {'type': 'integer', 'title': 'Limit', 'default': 50}}}
brainkb_login
Authenticate to BrainKB with the user's credentials and cache the JWT for
THIS session only (isolated per caller). The password/token are never echoed.
Uses single sign-on: one login mints a refresh token, cached for THIS session,
which is exchanged on demand for per-service access tokens (query_service,
usermanagement, â¦). Falls back to a legacy per-service token if the backend
has no SSO. On the hosted multi-user remote you can skip this and instead have
your client send an 'Authorization: Bearer <token>' header (a refresh token
unlocks all services).
입력 스키마
{'type': 'object', 'title': 'brainkb_loginArguments', 'required': ['email', 'password'], 'properties': {'email': {'type': 'string', 'title': 'Email'}, 'base_url': {'type': 'string', 'title': 'Base Url', 'default': ''}, 'password': {'type': 'string', 'title': 'Password'}}}
출력 스키마
{'type': 'object', 'title': 'brainkb_loginOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
brainkb_logout
Forget the cached token for this session.
입력 스키마
{'type': 'object', 'title': 'brainkb_logoutArguments', 'properties': {}}
출력 스키마
{'type': 'object', 'title': 'brainkb_logoutOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
brainkb_provenance_graph
PROV-O ingestion/activity history (JSON-LD) for a named graph.
입력 스키마
{'type': 'object', 'title': 'brainkb_provenance_graphArguments', 'required': ['named_graph_iri'], 'properties': {'named_graph_iri': {'type': 'string', 'title': 'Named Graph Iri'}}}
brainkb_provenance_job
PROV-O provenance bundle (JSON-LD) for one ingest job.
입력 스키마
{'type': 'object', 'title': 'brainkb_provenance_jobArguments', 'required': ['job_id'], 'properties': {'job_id': {'type': 'string', 'title': 'Job Id'}}}
brainkb_qa_list
Find a canned question BrainKB can answer, then run it with brainkb_qa_run.
Prefer these over writing SPARQL: they are vetted against BrainKB's actual
vocabulary. Discovery is two steps, so you never read every query at once:
1. brainkb_qa_list() -> the menu: each category's name, a description of
the questions it covers, and how many queries it has. Pick the category
whose description matches the user's question.
2. brainkb_qa_list(category="<name>") -> that category's queries. Each has
`question` (what it answers), `notes` (when to use it, where parameter
values come from, what the results mean), `params` (required ones have
no default â ask the user rather than guess) and a working `example`.
`search="words"` filters queries by words in their id/question/notes; use it
alone to search every category when none of the descriptions fits.
입력 스키마
{'type': 'object', 'title': 'brainkb_qa_listArguments', 'properties': {'search': {'type': 'string', 'title': 'Search', 'default': ''}, 'category': {'type': 'string', 'title': 'Category', 'default': ''}}}
brainkb_qa_run
Run a canned question from brainkb_qa_list by id. `params` maps parameter
names to values; they are validated and escaped, never spliced in raw. Runs
through the same SPARQL endpoint as brainkb_sparql, so it needs the same
role.
입력 스키마
{'type': 'object', 'title': 'brainkb_qa_runArguments', 'required': ['query_id'], 'properties': {'params': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'title': 'Params', 'default': None}, 'query_id': {'type': 'string', 'title': 'Query Id'}}}
brainkb_read_space
Read all RDF (JSON-LD) in a space's graphs. Public spaces are readable by
anyone; private spaces require membership.
입력 스키마
{'type': 'object', 'title': 'brainkb_read_spaceArguments', 'required': ['slug'], 'properties': {'slug': {'type': 'string', 'title': 'Slug'}}}
brainkb_recover_job
Attempt to recover a stuck/errored ingest job (marks it recoverable/errored).
입력 스키마
{'type': 'object', 'title': 'brainkb_recover_jobArguments', 'required': ['job_id'], 'properties': {'job_id': {'type': 'string', 'title': 'Job Id'}}}
brainkb_remove_access_rule
(Space manager) Delete a fine-grained access rule by its id
(see brainkb_list_access_rules).
입력 스키마
{'type': 'object', 'title': 'brainkb_remove_access_ruleArguments', 'required': ['slug', 'rule_id'], 'properties': {'slug': {'type': 'string', 'title': 'Slug'}, 'rule_id': {'type': 'integer', 'title': 'Rule Id'}}}
brainkb_remove_role
(Admin) Remove a role/group from a user by email.
입력 스키마
{'type': 'object', 'title': 'brainkb_remove_roleArguments', 'required': ['email', 'role'], 'properties': {'role': {'type': 'string', 'title': 'Role'}, 'email': {'type': 'string', 'title': 'Email'}}}
brainkb_revoke_capability
(Admin only) Revoke a previously granted capability from a user.
입력 스키마
{'type': 'object', 'title': 'brainkb_revoke_capabilityArguments', 'required': ['member', 'capability'], 'properties': {'member': {'type': 'string', 'title': 'Member'}, 'capability': {'type': 'string', 'title': 'Capability'}}}
brainkb_revoke_role_capability
(Admin only) Revoke a capability from a role/group.
입력 스키마
{'type': 'object', 'title': 'brainkb_revoke_role_capabilityArguments', 'required': ['role', 'capability'], 'properties': {'role': {'type': 'string', 'title': 'Role'}, 'capability': {'type': 'string', 'title': 'Capability'}}}
brainkb_revoke_token
Revoke one of your Personal Access Tokens by id (see brainkb_list_tokens).
Takes effect immediately â the next call using that token fails.
입력 스키마
{'type': 'object', 'title': 'brainkb_revoke_tokenArguments', 'required': ['token_id'], 'properties': {'token_id': {'type': 'integer', 'title': 'Token Id'}}}
brainkb_role_capabilities
(Admin only) List the capabilities granted to a role/group (e.g.
'uk_collaborator', 'Lab Member').
입력 스키마
{'type': 'object', 'title': 'brainkb_role_capabilitiesArguments', 'required': ['role'], 'properties': {'role': {'type': 'string', 'title': 'Role'}}}
brainkb_search
Full-text search over the knowledge graphs, access-filtered by space
visibility. Pass `space` to scope to one workspace, omit for a full search.
Anonymous/other users never see private-space data.
입력 스키마
{'type': 'object', 'title': 'brainkb_searchArguments', 'required': ['q'], 'properties': {'q': {'type': 'string', 'title': 'Q'}, 'limit': {'type': 'integer', 'title': 'Limit', 'default': 25}, 'space': {'type': 'string', 'title': 'Space', 'default': ''}, 'offset': {'type': 'integer', 'title': 'Offset', 'default': 0}}}
brainkb_set_space_visibility
Set a space 'public' (anyone, even anonymous, can read) or 'private'
(members only). Owner only.
입력 스키마
{'type': 'object', 'title': 'brainkb_set_space_visibilityArguments', 'required': ['slug', 'visibility'], 'properties': {'slug': {'type': 'string', 'title': 'Slug'}, 'visibility': {'type': 'string', 'title': 'Visibility'}}}
brainkb_sparql
Run an arbitrary SPARQL query. Requires an Admin/SuperAdmin role (the
sparql_admin capability) â for ordinary questions prefer brainkb_search,
brainkb_read_space, or the provenance/delta tools, which need no admin role.
입력 스키마
{'type': 'object', 'title': 'brainkb_sparqlArguments', 'required': ['sparql_query'], 'properties': {'sparql_query': {'type': 'string', 'title': 'Sparql Query'}}}
brainkb_unban_user
(Admin) Lift a ban on a user by email.
입력 스키마
{'type': 'object', 'title': 'brainkb_unban_userArguments', 'required': ['email'], 'properties': {'email': {'type': 'string', 'title': 'Email'}}}
brainkb_upload_status
State of one of your staged/submitted uploads.
`state` is `staged` (waiting for brainkb_ingest_upload), `submitting` (the server
is streaming it to the ingest API), `submitted` (accepted â `job_id` is set, poll
brainkb_job_status) or `failed` (the staged bytes were KEPT, so retry with
brainkb_ingest_upload rather than re-uploading).
입력 스키마
{'type': 'object', 'title': 'brainkb_upload_statusArguments', 'required': ['upload_id'], 'properties': {'upload_id': {'type': 'string', 'title': 'Upload Id'}}}
brainkb_use_token
Use a Personal Access Token (brainkb_pat_...) for THIS session â an
alternative to setting BRAINKB_TOKEN in the config. Validates the token, then
caches it so subsequent calls authenticate with it. The token is never echoed.
입력 스키마
{'type': 'object', 'title': 'brainkb_use_tokenArguments', 'required': ['token'], 'properties': {'token': {'type': 'string', 'title': 'Token'}, 'base_url': {'type': 'string', 'title': 'Base Url', 'default': ''}}}
출력 스키마
{'type': 'object', 'title': 'brainkb_use_tokenOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
brainkb_whoami
Report the current caller's auth state (email, authenticated, and when the
cached session expires). When signed in it also returns base_url â the backend
THIS SERVER talks to, which on a hosted deployment is an internal address and
says nothing about the caller's own machine.
입력 스키마
{'type': 'object', 'title': 'brainkb_whoamiArguments', 'properties': {}}
출력 스키마
{'type': 'object', 'title': 'brainkb_whoamiOutput', 'required': ['result'], 'properties': {'result': {'type': 'object', 'title': 'Result', 'additionalProperties': True}}}
기록
최근 도구 변경
추가됨
brainkb_qa_run
2026년 10월 1일 2:51 AM
추가됨
brainkb_qa_list
2026년 10월 1일 2:51 AM
추가됨
brainkb_create_permission
2026년 9월 17일 12:54 PM
추가됨
brainkb_list_permissions
2026년 9월 17일 12:54 PM
추가됨
brainkb_unban_user
2026년 9월 17일 12:54 PM
추가됨
brainkb_ban_user
2026년 9월 17일 12:54 PM
추가됨
brainkb_deactivate_user
2026년 9월 17일 12:54 PM
추가됨
brainkb_activate_user
2026년 9월 17일 12:54 PM
추가됨
brainkb_remove_role
2026년 9월 17일 12:54 PM
추가됨
brainkb_assign_role
2026년 9월 17일 12:54 PM
추가됨
brainkb_create_role
2026년 9월 17일 12:54 PM
추가됨
brainkb_available_roles
2026년 9월 17일 12:54 PM
추가됨
brainkb_list_users
2026년 9월 17일 12:54 PM
추가됨
brainkb_remove_access_rule
2026년 9월 17일 12:54 PM
추가됨
brainkb_add_access_rule
2026년 9월 17일 12:54 PM
추가됨
brainkb_list_access_rules
2026년 9월 17일 12:54 PM
추가됨
brainkb_revoke_role_capability
2026년 9월 17일 12:54 PM
추가됨
brainkb_grant_role_capability
2026년 9월 17일 12:54 PM
추가됨
brainkb_role_capabilities
2026년 9월 17일 12:54 PM
추가됨
brainkb_list_capabilities
2026년 9월 17일 12:54 PM
추가됨
brainkb_revoke_capability
2026년 9월 17일 12:54 PM
추가됨
brainkb_grant_capability
2026년 9월 17일 12:54 PM
추가됨
brainkb_capabilities
2026년 9월 17일 12:54 PM
추가됨
brainkb_delta_compare
2026년 9월 17일 12:54 PM
추가됨
brainkb_delta_history
2026년 9월 17일 12:54 PM
추가됨
brainkb_delta
2026년 9월 17일 12:54 PM
추가됨
brainkb_provenance_graph
2026년 9월 17일 12:54 PM
추가됨
brainkb_provenance_job
2026년 9월 17일 12:54 PM
추가됨
brainkb_sparql
2026년 9월 17일 12:54 PM
추가됨
brainkb_list_registered_graphs
2026년 9월 17일 12:54 PM
탐색
유사한 MCP 서버
Opentargets
io.github.pipeworx-io/opentargets
Provides Open Targets disease, drug, target, therapeutic-area, and disease-association knowledge graph lookups.
Inspire Hep
io.github.pipeworx-io/inspire-hep
Searches and retrieves high-energy physics literature, authors, institutions, and conference records from INSPIRE-HEP.
Bioportal
io.github.pipeworx-io/bioportal
Searches biomedical ontologies and retrieves concept definitions, synonyms, hierarchy relationships, and mappings across clinical…
Eol
io.github.pipeworx-io/eol
Provides access to Encyclopedia of Life taxonomy pages, scientific names, synonyms, common names, and biological hierarchies.
Nci Evs
io.github.pipeworx-io/nci-evs
Searches NCI Enterprise Vocabulary Services and retrieves cancer-research terminology concepts, definitions, relationships, hiera…
Hal Fr
io.github.pipeworx-io/hal-fr
Searches and retrieves scholarly documents and author records from the HAL French national open research archive.
Civic
io.github.pipeworx-io/civic
Provides curated clinical interpretations and evidence for cancer gene variants, including associated diseases, therapies, action…
Bioregistry
io.github.pipeworx-io/bioregistry
Looks up biomedical identifier prefixes and metadata, including URI patterns, aliases, homepages, and cross-registry mappings.