ChatGPT Plugin

Knotr

Profile, skills, and notes

Brand: Unknown

Category: Pending
Primary Subcategory: Pending

Integration details

Description

Knotr brings an existing Knotr profile into ChatGPT and Codex. After you connect the account, it can read your profile context, search knowledgebases, open and save profile skills, store notes, save shareable artifacts, and check draft copy against your style guides. Use it when you want the context you already keep on knotr.ai while working in chat. Knotr only accesses data available to the connected account. It does not send email, browse unrelated sites, move money, or change data in accounts you have not authorized. Creating or updating a skill, note, artifact, or style guide uses that account's write access.

Integration type: Plugin
Verification status: Not applicable
Platform: ChatGPT
Category: Pending
Primary Subcategory: Pending
Secondary Subcategories: None listed
Brand: Unknown
Access: Account required
First tracked: 2026-10-31
Tool count: 32
Market: US

Agent DiscoverabilityChatGPT Plugin Discovery Score

ChatGPT organic discovery is live

Your score is coming

ChatGPT now suggests Plugins on its own when they match a user's request.Your Plugin Discovery Score measures how often yours appears, and it will show here as soon as it’s ready.

ChatGPT recommends Airtable when a user asks it to update a CRM. — ChatGPT surfaces Airtable because it matches the user's request.

Primary Subcategory

Competitive lineup

No Primary Subcategory assigned yetOnce Knotr has a Primary Subcategory, the Plugins and Connectors it competes with will appear here with their scores.

Tools

32 tools agents can invoke

Returns markdown with a Profile owner section (who the profile represents) and an Assistant behavior section (how LLMs should respond in chat), plus Knowledgebases, Style guides, and Artifacts when applicable
about-me
Copy a publicly listed catalog skill into the user's workspace and assign it to this MCP profile. Requires confirm: true after reviewing list_catalog_skills results. OAuth clients need mcp_write scope.
add_catalog_skill_to_workspace
Run Vale against submitted text using active profile style guides. Returns issues with line, match text, message, rule, and suggested fix. Use before shipping user-facing prose to match the profile voice; fix issues and re-check. Requires an active style guide (see list_style_guides).
check_style
Create or update an Artifact in this profile’s workspace (creator-only updates, matching UI share settings)—durable shareable outputs, not skills or KB notes. On create: title and artifact_type are required. Builtin document/page still require content_format and body. Custom types take attributes keyed by field key; content fields are { content_format, body }. status defaults to active when omitted. Updates stay on the artifact’s pinned type version unless use_current_type_version is true (remaps fields onto the type’s current schema; missing required fields set draft). Use list_artifact_types for keys and schemas. LLM ingest mapping for builtins: Cursor .canvas.tsx → page+tsx with source_kind cursor_canvas; long-form markdown → document+markdown; static HTML → page+html. Returns hosted_path, hosted_url, present_url, raw_url, and collection_ids. OAuth needs mcp_write.
create_or_update_artifact
Create or update an Artifact Collection owned by the authenticated user. On create, title is required. Pass artifact_ids (ordered UUIDs) to set membership; omit artifact_ids on update to leave membership unchanged. Artifacts must be readable by the user (any workspace they can access). Returns present_url for the collection presenter. OAuth needs mcp_write.
create_or_update_artifact_collection
Create or update a custom Artifact Type in this profile’s workspace. Pass artifact_type_id to update. Schema is an attributes array with key, name, kind (text, number, boolean, date, datetime, enum, url, content), group (primary or secondary), required, and kind-specific options. Enum uses options plus multiple. Content uses allowed_content_formats (markdown, html, tsx) and must be primary. Schema edits create a new type version. OAuth needs mcp_write.
create_or_update_artifact_type
Create a document in an active knowledgebase or update an existing document. If document_id is omitted, knowledgebase_id and name are required. For text_note, set mime_type and content: text/markdown and text/plain are stored verbatim; code mime types use raw source; text/html may be converted to rich HTML. For file, set content_type file plus file_base64, filename, file_content_type. OAuth clients need mcp_write scope.
create_or_update_document
Create a knowledgebase or update an existing one linked to this MCP profile. If knowledgebase_id is omitted, creates a knowledgebase (name required) linked only to this profile. Set status to draft, active, or inactive (no delete). Document tools require an active knowledgebase. OAuth clients need mcp_write scope.
create_or_update_knowledgebase
Create a new skill or update an existing one when the user wants a durable reusable workflow on this profile (not one-off chat instructions; not KB notes or Artifacts). If skill_id is omitted, creates a skill (name required) linked only to this MCP profile—prefer status draft unless they want it live. If skill_id is set, updates that skill (must belong to this profile). Call list_skills first to avoid duplicates. Link skills to additional profiles in the app UI. Content is stored verbatim as markdown (fences, underscores, and quotes preserved). Do not soft-off (inactive) or overwrite active skills without confirmation. OAuth clients need mcp_write scope.
create_or_update_skill
Create a style guide or update an existing one linked to this MCP profile. If style_guide_id is omitted, creates a guide (name and source_text required) linked only to this profile and enqueues rule generation from source_text. If style_guide_id is set, updates that guide (partial fields). Set status to draft, active, or inactive (no delete). On update, set source_text or regenerate: true to enqueue rule generation. OAuth clients need mcp_write scope.
create_or_update_style_guide
Delete an Artifact Collection owned by the authenticated user. Memberships are removed; the artifacts themselves are not deleted. OAuth needs mcp_write.
delete_artifact_collection
Fetch one non-archived Artifact by UUID in this profile’s workspace, including hosted_path, hosted_url, present_url (recommended handoff link), raw_url, sync/cross-link fields, content_editable, and collection_ids (user-owned collections that contain this artifact). Creators receive share settings (visibility, link_scope); non-creators receive access labels and can_manage_sharing=false. source_document_id is included only when the actor can open that document. Body included by default. Archived artifacts cannot be opened/read; use create_or_update_artifact to change status first, or list_artifacts with status archived to discover them.
get_artifact
Fetch one Artifact Collection owned by the authenticated user, including ordered artifacts. Each artifact row includes readable/presentable flags; presentable rows include hosted_url and present_url. The collection present_url is the recommended handoff link for scrolling through the collection.
get_artifact_collection
Fetch one artifact type visible in this workspace by uuid or key, including the current schema.
get_artifact_type
Retrieve a document by UUID. return_type metadata (default): same fields as one list_documents row (id, knowledgebase_id, name, content_type, tags, mime_type, filename, file_byte_size). return_type contents: text_note body only (markdown/code) or file extracted text with headers. return_type file: file documents only (signed download URL).
get_document
Fetch one skill by UUID (any status). Returns structured content: name, description, intended_use, content (markdown), referenced_documents, resource_uri. Preferred path for skill bodies in IDEs—prefer over get_ide_plugin_install / full IDE zip sync. Active-only discovery: knotr-ai://manifests/skills; all statuses: list_skills.
get_skill
Fetch one style guide by UUID (any status). Returns name, description, status, resource_visibility, source_text, editorial_guidelines, unified rules, generation_status, generation_error, and resource_uri. Active-only discovery: knotr-ai://manifests/style-guides; all statuses: list_style_guides.
get_style_guide
Import all skills, commands, and agents from a synced GitHub plugin group into the workspace. Requires confirm: true after reviewing list_plugin_marketplaces. OAuth clients need mcp_write scope. Returns safety scan summary per imported skill.
import_plugin_skills
Lists Artifact Collections owned by the authenticated user (not workspace-scoped). Collections group artifacts the user can browse and present in order. Each row includes present_path and present_url (recommended handoff link for the full-screen collection presenter). Optional query filters by title or description.
list_artifact_collections
Returns builtin Document and Page types plus custom types visible in this profile’s workspace, including schema (ordered primary/secondary attributes). Keep using key when creating artifacts. uuid is also returned. Workspace-scoped artifact tools only see Artifacts owned by this profile’s workspace, not the user’s full /artifacts library.
list_artifact_types
Lists Artifacts owned by this profile’s workspace that the authenticated user may read. Each row includes hosted_path, hosted_url, present_url (recommended handoff link), raw_url, and collection_ids (UUIDs of collections owned by the authenticated user that contain the artifact, collections are user-owned, not workspace-scoped). Archived artifacts are hidden by default; pass status to include them (draft, active, or archived). Does not include bookmarks or Shared items from other workspaces. Optional filters: query (title), tag, type (artifact type key), status, visibility (private|workspace|link|team), collection_id. Visibility and link_scope in results match the UI: creators see share settings; non-creators see access labels (team/link). source_document_id and source_sync_* are included only when the artifact is linked to a document the actor can open.
list_artifacts
Browse globally approved skills in the Knotr public catalog. Optional query and category filters. Use add_catalog_skill_to_workspace (with confirm: true) to copy into the user's workspace.
list_catalog_skills
List documents in active knowledgebases linked to this profile. Returns UUIDs, effective mime_type (blob type for file uploads), and file metadata when applicable. One document’s fields: get_document (return_type metadata, default). Body: return_type contents; original file: return_type file (signed URL). Optional knowledgebase_id and limit (default 50, max 200).
list_documents
Returns all knowledgebases linked to this profile (draft, active, inactive), including UUID, name, description, status, and document count. Optional query filters by name or description. Use create_or_update_knowledgebase to edit; search/document tools require active knowledgebases.
list_knowledgebases
Browse GitHub plugin marketplaces added to the active workspace and their plugin groups. Use import_plugin_skills (with confirm: true) to import skills, commands, and agents from a synced plugin.
list_plugin_marketplaces
Returns all skills linked to this profile (draft, active, inactive). Optional query filters by name or description. Preferred IDE discovery path (metadata only)—use get_skill for bodies instead of syncing a full IDE skill zip. Use to discover skill UUIDs for get_skill or create_or_update_skill.
list_skills
Returns all style guides linked to this profile (draft, active, inactive): uuid, name, description, status, rule_count, resource_uri. Optional query filters by name or description. Use to discover UUIDs for get_style_guide or create_or_update_style_guide. check_style requires an active style guide.
list_style_guides
Publish an eligible KB text note (markdown/HTML) as a linked Artifact in this workspace. Body stays content-locked to the document. created is true only on first publish; calling again syncs the existing artifact and returns created=false. Optional collection_ids assigns the published artifact across collections owned by the authenticated user (omit to leave membership unchanged; [] clears). Sharing options match the UI (personal: private|link with knotr; team: private|workspace|link; shared team documents cannot publish as private). OAuth needs mcp_write.
publish_document_as_artifact
Search the Knotr public skills catalog by keyword. Alias of list_catalog_skills with query emphasized.
search_catalog_skills
Semantically search across knowledgebases to find relevant information. Returns chunks of content with document and knowledgebase metadata.
search_knowledgebase
Append a new ArtifactVersion from the linked source document. Pass artifact_id or document_id (at least one required). OAuth needs mcp_write.
sync_artifact_from_document
Update this MCP profile’s identity and assistant-behavior fields. Only the current profile can be updated (no create, no delete). Status and resource_visibility cannot be changed via MCP, manage those in the Knotr app. OAuth clients need mcp_write scope.
update_profile

FAQs

Knotr ChatGPT Plugin FAQ

How the directory, categories and Discoverability Score work.

Read the methodology

How do I improve Knotr's ChatGPT Plugin discoverability?

The levers are the listing surface agents actually read: names, descriptions, keywords, tool metadata, and registry health. Which lever matters depends on where discovery breaks, which is what continuous measurement shows.

Where is this profile measured?

This profile uses the geography attached to the latest public registry snapshot: US. Locale tags are intentionally omitted.