Summary
Gives your AI assistant a persistent memory layer that combines keyword, vector, and graph search in a single query. You get typed entities out of the box (people, projects, decisions, meetings, tasks) that link automatically into a knowledge graph. Works with Claude Desktop, Cursor, and ChatGPT over HTTP, authenticates via OAuth per user, and exposes tools for search, page CRUD, graph traversal, and task management. Useful when you need context that survives across sessions or want your agent to recall who decided what without manual tagging. Multilingual support for English and Russian. Hosted service with a 30 second setup through Smithery or manual config.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Tools
Public tool metadata for what this MCP can expose to an agent.
49 tools
read_pageRead a DashDoc page and return its content as Markdown with metadata.2 params
Read a DashDoc page and return its content as Markdown with metadata.
Parameters* required
page_idstringPage UUID (ref:<UUID> from get_tree, or id from search)
workspace_idstringTenant workspace ID (from list_workspaces). Optional — scopes to workspace if provided.
create_pageCreate a new page in DashDoc workspace. Content is Markdown (auto-converted to TipTap). Returns page_id and node_id.4 params
Create a new page in DashDoc workspace. Content is Markdown (auto-converted to TipTap). Returns page_id and node_id.
Parameters* required
titlestringPage title
markdownstringPage content in Markdown format
workspace_idstringTenant workspace ID (from list_workspaces)
parent_node_idstringTree node ID (node:<UUID> from get_tree, or parent_node_id from search/read_page) of parent folder. Omit for root level.
update_pageUpdate an existing DashDoc page. Handles optimistic locking automatically. Content is Markdown. Embedded blocks (kanban, spreadsheet, child pages) are preserved automatically.4 params
Update an existing DashDoc page. Handles optimistic locking automatically. Content is Markdown. Embedded blocks (kanban, spreadsheet, child pages) are preserved automatically.
Parameters* required
titlestringNew title
page_idstringPage UUID (ref:<UUID> from get_tree, or id from search)
markdownstringNew content in Markdown (replaces entire content). Embedded block markers are preserved.
workspace_idstringTenant workspace ID (from list_workspaces)
delete_pageSoft-delete a DashDoc page.2 params
Soft-delete a DashDoc page.
Parameters* required
page_idstringPage UUID to delete
workspace_idstringTenant workspace ID (from list_workspaces)
restore_pageRestore a soft-deleted DashDoc page. Clears deleted_at and re-registers workspace node.2 params
Restore a soft-deleted DashDoc page. Clears deleted_at and re-registers workspace node.
Parameters* required
page_idstringPage UUID to restore
workspace_idstringTenant workspace ID (from list_workspaces)
list_workspacesList all workspaces available to the current user. Returns workspace IDs needed for other tool calls.
List all workspaces available to the current user. Returns workspace IDs needed for other tool calls.
No parameter schema in public metadata yet.
get_treeGet workspace tree structure. Without node_id returns root items; with node_id drills into a subtree. OUTPUT FORMAT: Each line shows: - title (type, node:<tree-node-id>, ref:<entity-id>) Use node:<UUID> values as: - node_id parameter in get_tree to drill deeper - parent_node_i...2 params
Get workspace tree structure. Without node_id returns root items; with node_id drills into a subtree. OUTPUT FORMAT: Each line shows: - title (type, node:<tree-node-id>, ref:<entity-id>) Use node:<UUID> values as: - node_id parameter in get_tree to drill deeper - parent_node_i...
Parameters* required
node_idstringTree node ID (node:<UUID> from get_tree output) or page UUID to expand. Omit for root level.
workspace_idstringTenant workspace ID (from list_workspaces). Scopes to that workspace; omit for default.
create_folderCreate a folder in the DashDoc workspace tree.3 params
Create a folder in the DashDoc workspace tree.
Parameters* required
titlestringFolder name
workspace_idstringTenant workspace ID (from list_workspaces)
parent_node_idstringTree node ID (node:<UUID> from get_tree) of parent folder/project. Omit for root level.
create_projectCreate a new project in the DashDoc workspace tree. A project includes a Neo4j node, a linked page, and a workspace entry.3 params
Create a new project in the DashDoc workspace tree. A project includes a Neo4j node, a linked page, and a workspace entry.
Parameters* required
namestringProject name
workspace_idstringTenant workspace ID (from list_workspaces)
parent_node_idstringTree node ID (node:<UUID> from get_tree) of parent. Omit for root level.
move_pageMove a workspace item (page or folder) to a new parent within the SAME workspace. Cross-workspace moves are not supported — use create_page + delete_page instead.3 params
Move a workspace item (page or folder) to a new parent within the SAME workspace. Cross-workspace moves are not supported — use create_page + delete_page instead.
Parameters* required
node_idstringTree node ID (node:<UUID>) of item to move
workspace_idstringTenant workspace ID (from list_workspaces)
new_parent_node_idstringTree node ID (node:<UUID>) of target parent
upload_fileUpload a file to DashDoc workspace (max 500 MB). - Use file_path for local MCP servers (stdio mode) — most reliable for large files. - Use file_base64 + file_name for remote MCP servers (http mode). For files >25 MB, use file_base64_chunks to send in parts. - Use file_base64_c...8 params
Upload a file to DashDoc workspace (max 500 MB). - Use file_path for local MCP servers (stdio mode) — most reliable for large files. - Use file_base64 + file_name for remote MCP servers (http mode). For files >25 MB, use file_base64_chunks to send in parts. - Use file_base64_c...
Parameters* required
file_namestringFile name with extension (required with file_base64)
file_pathstringAbsolute path to a local file (only works when MCP server runs locally via stdio)
upload_idstringUnique upload session ID for chunked upload (use any UUID). All chunks of the same file must share the same upload_id.
chunk_indexnumber0-based chunk index for chunked upload (use with file_base64)
file_base64stringFile content encoded as base64 (for remote MCP servers). For files >25 MB consider chunked mode.
total_chunksnumberTotal number of chunks for chunked upload
workspace_idstringTenant workspace ID (from list_workspaces)
parent_node_idstringTree node ID (node:<UUID> from get_tree) of parent folder to upload into
reorder_workspaceReorder workspace items within their parent.2 params
Reorder workspace items within their parent.
Parameters* required
itemsarrayArray of {id, order} pairs
workspace_idstringTenant workspace ID (from list_workspaces)
searchKeyword search across all DashDoc content: pages, documents, meeting notes, decisions, discussions, tasks, graph nodes, canvases, boards. USE THIS TOOL when the user: - Asks about past discussions or conversations ("мы обсуждали", "мы говорили", "обсуждение с...") - Mentions a...4 params
Keyword search across all DashDoc content: pages, documents, meeting notes, decisions, discussions, tasks, graph nodes, canvases, boards. USE THIS TOOL when the user: - Asks about past discussions or conversations ("мы обсуждали", "мы говорили", "обсуждение с...") - Mentions a...
Parameters* required
typestringFilter by type: page, node, canvas, board, task. Comma-separated.
limitnumberMax results (1-100, default 10)default: 10
querystringSearch query — keywords, person names, topics (min 2 chars)
workspace_idstringTenant workspace ID (from list_workspaces). Optional — scopes search if provided.
unified_searchSemantic search combining keyword matching, vector similarity, knowledge graph traversal, and conversation search. Best for natural-language queries where exact keywords are unknown. USE THIS TOOL (preferred over basic search) when: - The user asks about discussions, meetings,...10 params
Semantic search combining keyword matching, vector similarity, knowledge graph traversal, and conversation search. Best for natural-language queries where exact keywords are unknown. USE THIS TOOL (preferred over basic search) when: - The user asks about discussions, meetings,...
Parameters* required
limitnumberMax results (1-100, default 10)default: 10
querystringNatural language query — questions, topics, person names, discussion references (min 2 chars)
typesarrayFilter by types: page, node, canvas, board, task, message, file, chat
offsetnumberPagination offset (default 0)default: 0
weightsobjectWeights for each search strategy
graph_depthnumberGraph traversal depth: 1 (direct) or 2 (two hops). Default 1.
workspace_idstringTenant workspace ID (from list_workspaces). Optional — scopes search if provided.
messages_per_chatnumberMax messages per matched chat (default 10)
include_conversationsbooleanInclude conversation/chat message search (default true)
include_graph_contextbooleanInclude graph context connections in response (default true)
graph_searchSearch graph nodes (entities) by name. Returns matching nodes with their types and properties.3 params
Search graph nodes (entities) by name. Returns matching nodes with their types and properties.
Parameters* required
querystringSearch query
typesstringFilter by node types (comma-separated): Person, Organization, Project, Server, Service, etc.
workspace_idstringTenant workspace ID (from list_workspaces). If provided, scopes to that workspace; if omitted, searches globally.
list_tasksList tasks from DashDoc with optional filters.7 params
List tasks from DashDoc with optional filters.
Parameters* required
tagsstringFilter by tags, comma-separated. Uses ANY matching.
limitnumberMax results (default 20)default: 20
statusstringFilter by status: inbox, planning, todo, in_progress, review, done, skip. Comma-separated.
assigneestringFilter by assignee name
board_idstringBoard ID (get from list_boards)
project_idstringFilter by project ID
workspace_idstringTenant workspace ID (from list_workspaces). Optional — scopes if provided.
get_taskGet full task details by ID.2 params
Get full task details by ID.
Parameters* required
task_idstringTask ID
workspace_idstringTenant workspace ID (from list_workspaces). If provided, scopes to that workspace; if omitted, reads globally.
create_taskCreate a new task in DashDoc. Agent tasks should always include tags: ["agent"] and board_id for Dev Board.11 params
Create a new task in DashDoc. Agent tasks should always include tags: ["agent"] and board_id for Dev Board.
Parameters* required
tagsarrayTags array. Use ["agent"] for agent-created tasks
titlestringTask title
statusstringStatus: inbox, planning, todo, in_progress, review, done, skipdefault: todo
assigneestringAssignee name
board_idstringBoard ID (get from list_boards)
due_datestringDue date (ISO format, e.g. 2026-04-10)
prioritystringPriority: low, medium, high, urgent
parent_idstringParent task ID to create as subtask (creates PART_OF relationship)
project_idstringProject ID to link task to (get from graph_search or get_tree)
descriptionstringTask description
workspace_idstringTenant workspace ID (from list_workspaces)
update_taskUpdate an existing task in DashDoc.10 params
Update an existing task in DashDoc.
Parameters* required
tagsarrayTags array
titlestringNew title
statusstringNew status: inbox, planning, todo, in_progress, review, done, skip
task_idstringTask ID
assigneestringNew assignee
due_datestringDue date (ISO format, e.g. 2026-04-10)
prioritystringNew priority: low, medium, high, urgent
project_idstringProject ID to link task to (get from graph_search or get_tree)
descriptionstringNew description
workspace_idstringTenant workspace ID (from list_workspaces)
delete_taskDelete a task.2 params
Delete a task.
Parameters* required
task_idstringTask ID
workspace_idstringTenant workspace ID (from list_workspaces)
get_task_relationsGet all relations for a task (subtasks, blocked by, blocks, project, etc.).2 params
Get all relations for a task (subtasks, blocked by, blocks, project, etc.).
Parameters* required
task_idstringTask ID
workspace_idstringTenant workspace ID (from list_workspaces). Optional.
link_tasksCreate a relationship between two tasks. Types: PART_OF (subtask→parent), BLOCKS (blocker→blocked), PART_OF_PROJECT (task→project).4 params
Create a relationship between two tasks. Types: PART_OF (subtask→parent), BLOCKS (blocker→blocked), PART_OF_PROJECT (task→project).
Parameters* required
typestringRelationship type: PART_OF (subtask), BLOCKS, PART_OF_PROJECT, ASSIGNED_TO, HAS_DOCUMENT, MENTIONS
task_idstringSource task ID
target_idstringTarget task/entity ID
workspace_idstringTenant workspace ID (from list_workspaces)
unlink_tasksRemove a relationship from a task by relation ID (get IDs from get_task_relations).3 params
Remove a relationship from a task by relation ID (get IDs from get_task_relations).
Parameters* required
task_idstringTask ID that owns the relation
relation_idstringRelation ID to delete
workspace_idstringTenant workspace ID (from list_workspaces)
bulk_update_tasksBulk update status for multiple tasks at once. Max 200 tasks per call.2 params
Bulk update status for multiple tasks at once. Max 200 tasks per call.
Parameters* required
updatesstringJSON array of updates: [{"id":"task-id","status":"done"}, ...]. Each item needs id and optional status.
workspace_idstringTenant workspace ID (from list_workspaces)
create_canvas_nodeCreate a new entity and place it on a canvas. Entity types: Person, Organization, Project, Server, Service, Agent, Interface, DataStore, Document, Task, etc.7 params
Create a new entity and place it on a canvas. Entity types: Person, Organization, Project, Server, Service, Agent, Interface, DataStore, Document, Task, etc.
Parameters* required
xnumberX position on canvasdefault: 0
ynumberY position on canvasdefault: 0
namestringEntity name
canvas_idstringCanvas ID to place the node on
propertiesobjectAdditional properties (description, status, url, etc.)
entity_typestringEntity type: Person, Organization, Project, Server, Service, Agent, Interface, DataStore, External, Human, Gateway, Document, Task, Frame, Annotation, Milestone, etc.
workspace_idstringTenant workspace ID (from list_workspaces)
add_node_to_canvasAdd an existing graph node to a canvas at specified position.5 params
Add an existing graph node to a canvas at specified position.
Parameters* required
xnumberX position on canvasdefault: 0
ynumberY position on canvasdefault: 0
node_idstringExisting node ID to add
canvas_idstringCanvas ID
workspace_idstringTenant workspace ID (from list_workspaces)
read_presentationRead a DashDoc presentation (Reveal.js markdown format). Returns markdown content, theme, and transition settings. Slides are separated by --- (horizontal) and -- (vertical sub-slides). Supports fragments (animations), data-background attributes, and HTML within slides.2 params
Read a DashDoc presentation (Reveal.js markdown format). Returns markdown content, theme, and transition settings. Slides are separated by --- (horizontal) and -- (vertical sub-slides). Supports fragments (animations), data-background attributes, and HTML within slides.
Parameters* required
workspace_idstringTenant workspace ID (from list_workspaces). If provided, scopes to that workspace; if omitted, reads globally.
presentation_idstringPresentation UUID
create_spreadsheetCreate a spreadsheet with optional headers and data rows.5 params
Create a spreadsheet with optional headers and data rows.
Parameters* required
rowsarrayData rows as array of arrays
titlestringSpreadsheet title
headersarrayColumn headers (first row)
workspace_idstringTenant workspace ID (from list_workspaces)
parent_node_idstringTree node ID (node:<UUID> from get_tree) of parent. Omit for root level.
read_spreadsheetRead spreadsheet data as markdown table, CSV, or JSON. For large spreadsheets (>1000 rows), consider using range parameter or CSV format.5 params
Read spreadsheet data as markdown table, CSV, or JSON. For large spreadsheets (>1000 rows), consider using range parameter or CSV format.
Parameters* required
rangestringA1 range to read, e.g. "A1:C10". If omitted, reads all data.
formatstringOutput format (default: markdown)one of
markdown · csv · jsonpage_idstringSpreadsheet page UUID
sheet_idstringSheet ID (default: first sheet)
workspace_idstringTenant workspace ID (from list_workspaces). If provided, scopes to that workspace; if omitted, reads globally.
update_cellsUpdate specific cells by A1 address (e.g. B2, D15). Handles optimistic locking with retry.4 params
Update specific cells by A1 address (e.g. B2, D15). Handles optimistic locking with retry.
Parameters* required
cellsarrayArray of cell updates
page_idstringSpreadsheet page UUID
sheet_idstringSheet ID (default: first sheet)
workspace_idstringTenant workspace ID (from list_workspaces)
append_rowsAppend rows to the end of a spreadsheet. Handles optimistic locking with retry.4 params
Append rows to the end of a spreadsheet. Handles optimistic locking with retry.
Parameters* required
rowsarrayRows to append as array of arrays
page_idstringSpreadsheet page UUID
sheet_idstringSheet ID (default: first sheet)
workspace_idstringTenant workspace ID (from list_workspaces)
manage_sheetsList, add, delete, rename a sheet, or toggle gridlines visibility. action=list reads sheets (workspace-optional); all others mutate.5 params
List, add, delete, rename a sheet, or toggle gridlines visibility. action=list reads sheets (workspace-optional); all others mutate.
Parameters* required
namestringSheet name (required for add/rename)
actionstringAction to performone of
list · add · delete · rename · show_gridlines · hide_gridlinespage_idstringSpreadsheet page UUID
sheet_idstringTarget sheet ID (required for delete/rename/gridlines)
workspace_idstringTenant workspace ID (from list_workspaces). Required for write actions; optional for action=list.
find_cellsSearch for a value in spreadsheet cells. Returns matching cell addresses.5 params
Search for a value in spreadsheet cells. Returns matching cell addresses.
Parameters* required
matchstringMatch mode (default: exact)one of
exact · containsquerystringValue to search for
page_idstringSpreadsheet page UUID
sheet_idstringSheet ID (default: first sheet)
workspace_idstringTenant workspace ID (from list_workspaces). If provided, scopes to that workspace; if omitted, reads globally.
style_cellsApply style (bold, italic, colors, alignment, etc.) to a cell or range.5 params
Apply style (bold, italic, colors, alignment, etc.) to a cell or range.
Parameters* required
rangestringCell or range, e.g. "B2" or "A1:C3"
styleobjectStyle properties to apply
page_idstringSpreadsheet page UUID
sheet_idstringSheet ID (default: first sheet)
workspace_idstringTenant workspace ID (from list_workspaces)
merge_cellsMerge or unmerge cells in a range.5 params
Merge or unmerge cells in a range.
Parameters* required
rangestringRange to merge, e.g. "A1:C1"
actionstringAction (default: merge)one of
merge · unmergepage_idstringSpreadsheet page UUID
sheet_idstringSheet ID (default: first sheet)
workspace_idstringTenant workspace ID (from list_workspaces)
resize_columns_rowsSet column widths and/or row heights.5 params
Set column widths and/or row heights.
Parameters* required
rowsarrayRow heights to set
columnsarrayColumn widths to set
page_idstringSpreadsheet page UUID
sheet_idstringSheet ID (default: first sheet)
workspace_idstringTenant workspace ID (from list_workspaces)
save_knowledgeSave structured facts to the knowledge graph with automatic entity resolution and deduplication. Entity resolution algorithm (in priority order): 1. Exact match by identifiers (phone, email, telegramUsername, domain, inn) 2. Exact match by name 3. Fuzzy match by name and alias...5 params
Save structured facts to the knowledge graph with automatic entity resolution and deduplication. Entity resolution algorithm (in priority order): 1. Exact match by identifiers (phone, email, telegramUsername, domain, inn) 2. Exact match by name 3. Fuzzy match by name and alias...
Parameters* required
factsarrayFacts to save (subject-predicate-object triples)
dry_runbooleanPreview resolution without committing changes
page_idstringLink all entities to an existing page via MENTIONED_IN edges
create_pageobjectCreate a new page and link entities to it
workspace_idstringTenant workspace ID (from list_workspaces). Required when using create_page.
list_remindersList reminders with optional status filter.4 params
List reminders with optional status filter.
Parameters* required
limitnumberMax results (default 50)default: 50
offsetnumberSkip first N results (default 0)default: 0
statusstringFilter by status (default: active)one of
active · done · dismisseddefault: activeworkspace_idstringTenant workspace ID (from list_workspaces). If provided, scopes to that workspace; if omitted, lists globally.
graph_nodeUnified CRUD for knowledge-graph nodes (entities). Replaces create_node, get_node, update_node, delete_node, get_related. Actions: - create: requires type, name; optional properties - get: requires node_id - update: requires node_id; optional name, properties - delete: require...6 params
Unified CRUD for knowledge-graph nodes (entities). Replaces create_node, get_node, update_node, delete_node, get_related. Actions: - create: requires type, name; optional properties - get: requires node_id - update: requires node_id; optional name, properties - delete: require...
Parameters* required
namestringEntity name (required for create; optional for update)
typestringEntity type (required for create): Person, Organization, Project, Server, Service, etc.
actionstringOperation to performone of
create · get · update · delete · relatednode_idstringNode ID (required for get/update/delete/related)
propertiesobjectKey-value properties (optional for create/update)
workspace_idstringTenant workspace ID; scopes the operation.
graph_edgeUnified CRUD for knowledge-graph edges (relationships). Also used to create connections between nodes on a canvas. Replaces create_edge, get_edge, update_edge, delete_edge. Actions: - create: requires source_id, target_id, type; optional properties - get: requires edge_id - up...7 params
Unified CRUD for knowledge-graph edges (relationships). Also used to create connections between nodes on a canvas. Replaces create_edge, get_edge, update_edge, delete_edge. Actions: - create: requires source_id, target_id, type; optional properties - get: requires edge_id - up...
Parameters* required
typestringRelationship type in UPPER_SNAKE_CASE (required for create; optional for update)
actionstringOperation to performone of
create · get · update · deleteedge_idstringEdge ID (required for get/update/delete)
source_idstringSource node ID (required for create)
target_idstringTarget node ID (required for create)
propertiesobjectEdge properties (style, label, etc.)
workspace_idstringTenant workspace ID; scopes the operation.
graph_schemaList all entity types, relationship types, and property schemas available in the knowledge graph. Renamed from graph_types.
List all entity types, relationship types, and property schemas available in the knowledge graph. Renamed from graph_types.
No parameter schema in public metadata yet.
boardUnified CRUD for kanban boards. Replaces list_boards, get_board, create_board, update_board, delete_board. Boards are filter views — pass filters JSON with include/exclude for projects, tags, people, statuses; matching tasks appear on the board automatically. Actions: - list:...9 params
Unified CRUD for kanban boards. Replaces list_boards, get_board, create_board, update_board, delete_board. Boards are filter views — pass filters JSON with include/exclude for projects, tags, people, statuses; matching tasks appear on the board automatically. Actions: - list:...
Parameters* required
namestringBoard name (required for create; optional for update)
limitnumberList: max results (default 50)
actionstringOperation to performone of
list · get · create · update · deleteoffsetnumberList: skip first N (default 0)
columnsarrayColumn statuses. Default: [inbox, planning, todo, in_progress, review, done, skip].
filtersstringJSON string with board filters. Example: {"include":{"projects":["CyberBrain"]},"tagsMatch":"any"}
board_idstringBoard ID (required for get/update/delete)
project_idstringProject ID to link the board to (create only)
workspace_idstringTenant workspace ID (required for create/update/delete; optional for list/get scoping)
canvasUnified CRUD for canvases (visual boards). Replaces list_canvases, get_canvas, create_canvas, update_canvas, delete_canvas. For node placement use create_canvas_node (new entity+placement) or add_node_to_canvas (attach existing). Those remain separate tools — their side effect...7 params
Unified CRUD for canvases (visual boards). Replaces list_canvases, get_canvas, create_canvas, update_canvas, delete_canvas. For node placement use create_canvas_node (new entity+placement) or add_node_to_canvas (attach existing). Those remain separate tools — their side effect...
Parameters* required
iconstringIcon emoji (update only)
namestringCanvas name (required for create; optional for update)
limitnumberList: max results (default 50)
actionstringOperation to performone of
list · get · create · update · deleteoffsetnumberList: skip first N (default 0)
canvas_idstringCanvas ID (required for get/update/delete)
workspace_idstringTenant workspace ID (required for create/update/delete)
canvas_nodeUpdate or delete a node on a canvas. Creators (create_canvas_node, add_node_to_canvas) are separate tools. Actions: - update: requires canvas_id, node_id; optional x, y, shape, color, node_size, properties - delete: requires node_id; optional canvas_id, delete_entity (default...11 params
Update or delete a node on a canvas. Creators (create_canvas_node, add_node_to_canvas) are separate tools. Actions: - update: requires canvas_id, node_id; optional x, y, shape, color, node_size, properties - delete: requires node_id; optional canvas_id, delete_entity (default...
Parameters* required
xnumberUpdate: X position
ynumberUpdate: Y position
colorstringUpdate: hex color, e.g. #ff6600
shapestringUpdate: rectangle, diamond, cylinder, circle, hexagon
actionstringOperation to performone of
update · deletenode_idstringNode ID (required)
canvas_idstringCanvas ID (required for update; optional for delete when removing from canvas only)
node_sizestringUpdate: sm, md, lg
propertiesobjectUpdate: property key-values
workspace_idstringTenant workspace ID (required for write ops)
delete_entitybooleanDelete: if true, removes the entity from the graph entirely (default false)
canvas_edgeUpdate or delete an edge on a canvas (styling layer). To CREATE an edge between canvas nodes, use graph_edge(action=create). Actions: - update: requires edge_id; optional type, style, label, shape - delete: requires edge_id7 params
Update or delete an edge on a canvas (styling layer). To CREATE an edge between canvas nodes, use graph_edge(action=create). Actions: - update: requires edge_id; optional type, style, label, shape - delete: requires edge_id
Parameters* required
typestringUpdate: new relationship type (UPPER_SNAKE_CASE). Changing type recreates the edge.
labelstringUpdate: edge label text
shapestringUpdate: bezier, step, smoothstep, straight
stylestringUpdate: solid, dashed
actionstringOperation to performone of
update · deleteedge_idstringEdge ID (required)
workspace_idstringTenant workspace ID
presentationUnified create/update for Reveal.js presentations. Read via read_presentation. Actions: - create: requires title, markdown, workspace_id; optional theme, transition, parent_id - update: requires presentation_id, workspace_id; optional markdown, theme, transition, title Markdow...8 params
Unified create/update for Reveal.js presentations. Read via read_presentation. Actions: - create: requires title, markdown, workspace_id; optional theme, transition, parent_id - update: requires presentation_id, workspace_id; optional markdown, theme, transition, title Markdow...
Parameters* required
themestringVisual theme (default: white)one of
black · white · moon · league · beige · skytitlestringCreate: required. Update: optional new title.
actionstringOperation to performone of
create · updatemarkdownstringCreate: required slide content. Update: optional new content (replaces all slides).
parent_idstringCreate: tree node ID (node:<UUID>) of parent folder
transitionstringTransition effect (default: slide)one of
none · fade · slide · convex · concave · zoomworkspace_idstringTenant workspace ID (required)
presentation_idstringPresentation UUID (required for update)
reminderUnified create/update/delete for reminders. Listing remains via list_reminders. Actions: - create: requires text, workspace_id; optional due_at (ISO 8601) - update: requires reminder_id, workspace_id; optional text, due_at, status - delete: requires reminder_id, workspace_id6 params
Unified create/update/delete for reminders. Listing remains via list_reminders. Actions: - create: requires text, workspace_id; optional due_at (ISO 8601) - update: requires reminder_id, workspace_id; optional text, due_at, status - delete: requires reminder_id, workspace_id
Parameters* required
textstringReminder text (required for create; optional for update)
actionstringOperation to performone of
create · update · deletedue_atstringISO 8601 due date (e.g. 2026-04-05T14:00:00Z)
statusstringUpdate: new statusone of
active · done · dismissedreminder_idstringReminder ID (required for update/delete)
workspace_idstringTenant workspace ID (required)
tree_nodeUpdate or delete an item in the workspace tree (page, folder, project, etc.). The tree is the workspace hierarchy projection of DashDoc nodes. For CREATE use the dedicated hot-path tools: create_page, create_folder, create_project, create_spreadsheet, create_canvas, create_pre...5 params
Update or delete an item in the workspace tree (page, folder, project, etc.). The tree is the workspace hierarchy projection of DashDoc nodes. For CREATE use the dedicated hot-path tools: create_page, create_folder, create_project, create_spreadsheet, create_canvas, create_pre...
Parameters* required
iconstringUpdate: new icon emoji
titlestringUpdate: new title
actionstringOperation to performone of
update · deletenode_idstringTree node ID (node:<UUID> from get_tree)
workspace_idstringTenant workspace ID (from list_workspaces)
manage_rows_columnsInsert or delete rows/columns in a spreadsheet, shifting existing cells. Actions: - insert: add N rows/columns at position - delete: remove N rows/columns at position Position format depends on axis: - axis=row: `at` is a 1-based row number (string or number) - axis=column: `a...7 params
Insert or delete rows/columns in a spreadsheet, shifting existing cells. Actions: - insert: add N rows/columns at position - delete: remove N rows/columns at position Position format depends on axis: - axis=row: `at` is a 1-based row number (string or number) - axis=column: `a...
Parameters* required
atstringRow number (1-based, for axis=row) or column letter (A, B, AA, for axis=column)
axisstringWhich axis to operate onone of
row · columncountnumberNumber of rows/columns (default: 1)
actionstringInsert or deleteone of
insert · deletepage_idstringSpreadsheet page UUID
sheet_idstringSheet ID (default: first sheet)
workspace_idstringTenant workspace ID (from list_workspaces)
Contexta MCP
Persistent memory & knowledge graph for your AI assistant.
Keyword + vector + graph search in a single lookup.
What is Contexta
Contexta is a memory MCP server that remembers like a human does — by meaning, by words, and by relationships.
Most memory tools give you one flavor of recall: embedding search, a raw log, or a graph you pay extra for. Contexta fuses all three into a single query. Your agent can ask "what did we decide about pricing with Acme last quarter?" and get back the right meeting, the right decision, and the people connected to it — in one round-trip.
Under the hood, Contexta indexes your notes, messages, and documents as typed entities (people, projects, decisions, meetings, tasks) and links them into a knowledge graph automatically. Every retrieval combines:
- Keyword search — exact phrases, names, IDs
- Vector search — semantic meaning across languages
- Graph traversal — follow relationships between entities
Why Contexta
- Typed entities out of the box — people, projects, decisions, meetings, tasks are first-class, not blobs of text
- Knowledge graph included — no paid tier gate on the graph layer
- Triple retrieval in one call — no need to stitch together three different memory APIs
- 30-second setup — install via Smithery, sign in with OAuth, done
- Per-user OAuth — your memory is private; the server authenticates every request individually
- Multilingual — English and Russian equally supported
Use cases
- Persistent memory for Claude, ChatGPT, and Cursor across sessions
- Long-term context for AI agents working on ongoing projects
- Personal knowledge base that actually understands who and what you mean
- Research and meeting recall without manually tagging anything
Install
Via Smithery (recommended)
One-click install from the Smithery listing — Smithery handles the OAuth flow and proxies connections through its gateway.
Manual — Claude Desktop
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):
{
"mcpServers": {
"contexta": {
"url": "https://mcp.contexta.cc/mcp"
}
}
}
Claude will walk you through the OAuth sign-in on first use. See examples/claude-desktop.json.
Manual — Cursor
Add a new MCP server in Cursor → Settings → MCP:
- Name: Contexta
- Transport: HTTP
- URL:
https://mcp.contexta.cc/mcp
See examples/cursor.json.
Manual — ChatGPT
In ChatGPT → Settings → Connectors → Add custom connector → paste https://mcp.contexta.cc/mcp. See examples/chatgpt.md for full instructions.
Authentication
Contexta uses OAuth 2.0 with dynamic client registration (RFC 7591) and PKCE. On first connection, your MCP client opens a browser window, you sign in with your Contexta account, and the client receives a per-user access token. Tokens are refreshed automatically.
No API keys, no shared credentials — every request runs as a specific user with that user's private memory.
Tools exposed
Contexta MCP exposes the following tools to your AI client (non-exhaustive):
search— keyword + vector + graph search across your memoryread_page— fetch a note or document by IDcreate_page— save a new memoryupdate_page— edit an existing memorygraph_search— traverse the knowledge graphlist_tasks/create_task/update_task— task managementlist_workspaces— available workspaces- and more — the full tool list is discovered automatically by your MCP client.
Links
- Website: contexta.cc
- App: app.contexta.cc
- Smithery: smithery.ai/servers/ai-jcce/mcp-contexta
- MCP endpoint:
https://mcp.contexta.cc/mcp
License
MIT — see LICENSE.
This repository is a public showcase for the hosted Contexta MCP service. The service itself is operated by the Contexta team at mcp.contexta.cc.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →Registryactive
TransportHTTP
UpdatedApr 9, 2026
