Skip to main content
Glama
contextium-mcp-server

contextium-mcp-server

Official

Contextium MCP Server

contextium-io/contextium-mcp-server MCP server

Give Claude your team's brain. Pipe SOPs, coding standards, agents, and workflows directly into Claude Desktop, Claude Code, Cursor, and any MCP-compatible assistant.

Stop copy-pasting context into every chat. Contextium is a shared knowledge platform that connects your team's documentation, AI agents, skills, and workflows to Claude via MCP — so the right context is always there, automatically.

npm version npm downloads MCP Registry License: MIT


See it in action

Ask Claude to create a Contextium project — it architects the full structure and populates it with content via MCP:

Claude Desktop creating a Contextium project

The result appears instantly in the Contextium Desktop app, ready for your whole team:

Contextium Desktop showing created skills


Related MCP server: repo-memory-mcp

Get connected in 2 minutes

Step 1 — Add to Claude Desktop

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "contextium": {
      "command": "npx",
      "args": ["@contextium/mcp-server"]
    }
  }
}

Step 2 — Authenticate

npx @contextium/mcp-server setup

A browser window opens. Log in, select your workspace, and authorise. Done.

Step 3 — You're live

Contextium appears as running in Claude Desktop's Developer settings:

Claude Desktop showing Contextium MCP server connected


What you can do

Say to Claude

What happens

"Create a new Contextium project for our API docs"

Claude architects and populates a full library

"Load my onboarding workflow"

Full team context loads into the session

"Find anything about our authentication approach"

Searches across all your Contextium libraries

"What agents do we have set up?"

Lists your team's AI agents with descriptions

"Add this decision to our architecture library"

Creates a versioned file in Contextium

"Browse the marketplace for a skill"

Searches and installs from the Contextium Marketplace


Built-in tool instructions

Every tool ships with structured descriptions so Claude Desktop and other platforms understand exactly how and when to use each tool — no prompt engineering required on your end.


Full tool reference

Core CRUD

Tool

What it does

list

List any resource — workspaces, libraries, files, agents, skills, workflows, tags, members

get

Retrieve full details of any resource by ID — including member profiles

create

Create any resource — files, libraries, agents, skills, workflows, tags

update

Update any existing resource — files, agents, workflows, skills, tags

delete

Delete files and resources (moves to trash, restorable)

search

Semantic search across all documentation

search_by_tags

Filter resources by tag

manage_relationship

Link agents to skills, apply tags, manage associations

Workflows & Projects

Tool

What it does

load_workflow

Load a full workflow — bundles agents, skills, and libraries into context

new_project

Guided flow to create a new Contextium project

resume_project

Resume work from a previous session handoff

harness

Structured feature development — get next phase, mark complete, close session

Skills

Tool

What it does

list_skills

List all skills in the workspace Skills Library

get_skill

Retrieve a skill's full markdown content by ID or name

update_skill

Update a skill's title or content

Tasks

Tool

What it does

add_task

Add a task to a workflow (accepts workflow name or ID)

update_task_status

Update a task's status — not_started, in_progress, done

list_tasks

List tasks for a workflow or across the workspace

Identities

Tool

What it does

list_identities

List all identities in the workspace

get_identity

Retrieve full identity details

create_identity

Create a new identity — voice, tone, role, and audience

update_identity

Update an existing identity

delete_identity

Delete an identity

Team

Tool

What it does

notify_team_members

Notify workspace members about a file, workflow, agent, or library

Integrations & Utilities

Tool

What it does

figma_sync

Sync Figma designs into a Contextium library

marketplace

Browse, search, and install from the Contextium Marketplace

contextium_status

Check auth status, current workspace, and available resources

contextium_help

Show available tools and usage guidance


Works with

  • Claude Desktop

  • Claude Code

  • Cursor

  • Any MCP-compatible client

Requirements: Node.js ≥ 18


Available Tools

67 tools
access_requestA

Request access to a private library or workflow you cannot see, or — as the resource owner — list, approve, or deny pending requests. Use action="request" when a loaded workflow reports a locked library (see its requestAccess affordance). This works from the terminal — the user does not need to open the web app.

Inputs: action (required), mine, reason, requestId, +4 more.

add_commentA

Add a comment to a file, or reply to an existing comment (pass parentCommentId). Authored as the connected user. Optionally anchor to a line with lineNumber. Replying to an external (guest) commenter also emails them.

Inputs: fileId (required), content (required), lineNumber, parentCommentId.

add_phaseA

Add a phase (work item) to a workflow's project plan. Phases are appended at the end of the existing list. If the workflow has no project plan yet, one is created automatically.

Inputs: title (required), workflowId (required), description, workspaceId, +1 more.

add_taskA

Add a task — autonomous by default. Just pass a title and the server will (a) auto-ROUTE the task to the workflow it best fits (matched from the task text against workflow names/descriptions), falling back to the workspace's "General" workflow when no workflow clearly relates, and (b) auto-ASSIGN it to the right team member(s) by role/default. Every task belongs to a workflow — there is no workspace-level task. The caller does NOT need to choose a workflow or assignee. Provide an explicit workflowId/workflowName and/or assigneeIds ONLY to override that decision (the user has already decided) — explicit values are used verbatim and skip auto-routing/auto-assignment for whatever was specified. Set autoRoute:false to skip AI routing and place the task directly in the "General" workflow. Tasks are stored as DB tasks under the chosen workflow by default; only legacy workflows that still have a file-backed project library store the task as a phase file tagged "task".

Inputs: title (required), dueDate, priority, autoRoute, +8 more.

auto_project_setupA

Autonomous one-shot project setup — creates a full Contextium workspace (library, agents, workflow, project-state.md) without asking any questions. Use when the user says "just set it up", "create a project for X", or is on mobile/voice.

Inputs: name (required), description, workspaceId.

auto_research_setupA

Autonomous one-shot research workspace setup — creates a research library, agents, and workflow without asking any questions. Use when the user says "deep dive into X", "research X for me", or is on mobile/voice.

Inputs: name (required), depth, description, workspaceId.

break_down_taskA

Use AI to break a broad task into 3-6 concrete, actionable subtasks. Claude analyses the task title and workflow context, then creates the subtasks automatically. Use when a task is too broad to complete in one step.

Inputs: taskId (required), workflowId (required), workspaceId.

capture_ideaA

Capture a quick note or seed to remember later — saves into an existing project's seeds or a general Quick Notes library. Use ONLY for lightweight "remember this" notes: when the user says "remember this", "note that", "jot this down", or "add this to [project]". Do NOT use this for a brand-new business, product, app, SaaS, or venture idea ("I have an idea for…", "I want to start a business that…", "I want to build…") — those are not quick notes; route them to idea_kickoff, which runs a full business analysis. When unsure between capturing and kicking off a venture idea, prefer idea_kickoff.

Inputs: text (required), projectName, workspaceId.

connector_requestA

Make an HTTP request to a third-party platform that is allocated to a workflow, on the user's behalf. The request is brokered securely — you never see or handle any access token. Give the path RELATIVE to the connector base URL (e.g. "/repos/acme/api/issues"), not a full URL. Use list_workflow_connectors first to find a connector_id.

Inputs: path (required), method (required), workflowId (required), connector_id (required), +3 more.

contextium_helpA

Show all available Contextium capabilities and how to use them. Call this when the user asks: "what can Contextium do", "help with Contextium", "how do I use Contextium", "what Contextium tools are available", "show me what I can do with Contextium".

Inputs: no named parameters.

contextium_statusA

Show a Contextium workspace health dashboard — available workspaces, libraries, agents, skills, and workflows. Call this when the user asks: "check Contextium status", "what workspace am I in", "what resources do I have in Contextium", "show my Contextium setup", "what libraries do I have".

Inputs: workspaceId.

createB

Create a new resource in a workspace. Set type to what you're creating: "file" (needs libraryId + title + complete content), "library" (a context library — needs name), or "agent" / "skill" / "workflow" (need name; a workflow can bundle projectIds, agentIds, skillIds, and tagIds). Always provide full, real content for files — never empty or placeholder.

File linking: to link to another file in the SAME workspace, put // inline in the content — use the target file's UUID (from search/list/get results), not its title. The link renders as the target's title and is indexed automatically on save; the target gains a backlink with no extra step. Add a link only where the text genuinely references an existing file; never invent // for a file that does not exist (it becomes a dangling link). Use get({ type: "file_links", id }) to inspect a file's links and backlinks.

Inputs: type (required), name, path, title, +10 more.

create_agentA

Create a new agent in the workspace.

WHAT IS AN AGENT: An agent is a specialised AI assistant with a defined role, persona, and behavioural instructions. Agents are where you put "You are a..." system prompts, persona definitions, tone of voice rules, and task-specific instructions. Agents can have skills attached to them to give them access to reference knowledge.

EXAMPLES of correct agent content:

  • "You are a senior customer support agent for Acme Corp. You handle billing and account queries..."

  • "You are a code reviewer specialising in Python. You check for security vulnerabilities..."

DO NOT use create_agent to store reference material, policies, or documentation — use create_skill for that.

IMPORTANT: You MUST always provide both a clear name AND a meaningful description — never leave description blank. The description should explain the agent's role, specialisation, and how it behaves.

WORKFLOW ATTACHMENT: Always provide workflowId when creating an agent for a specific project or feature — this ensures the agent is immediately attached to the right workflow and won't be orphaned.

Inputs: name (required), description (required), personaId, workflowId, +2 more.

create_identityB

Creates a new identity in the workspace. Identities capture voice, tone, role, and audience context so AI produces work from the right perspective.

Inputs: name (required), type, scope, neverDo, +12 more.

create_planA

Create a phase plan for a workflow. A workflow can have at most one plan. Returns the new plan ID to use with add_phase. This is an alias of create_project.

Inputs: workflowId (required), name, spec, description, +1 more.

create_projectA

Create a phase plan for a workflow (despite the name, this does NOT create a context library — it creates the project plan that holds phases). A workflow can have at most one plan. Returns the new plan ID to use with add_phase. Alias: create_plan.

Inputs: workflowId (required), name, spec, description, +1 more.

create_resourceA

Interactively create an agent, skill, or workflow in the current Contextium workspace. Call this when the user says things like: "create an agent", "make a new agent", "create a skill", "build a workflow", "I need a skill for X", "set up an agent that does X", "make an agent that can do X".

Inputs: no named parameters.

deleteA

Delete a resource (moves to trash, restorable). type: file | skill | workflow

Inputs: id (required), type (required), workspaceId.

delete_agentA

Permanently delete an agent from the workspace. This cannot be undone. System agents (harness agents) cannot be deleted.

Inputs: agentId (required), workspaceId.

delete_done_phasesA

Bulk delete all phases marked as done from a workflow's project plan. Use this to clean up completed work. Returns the number of phases deleted.

Inputs: workflowId (required), workspaceId.

delete_identityA

Permanently deletes an identity by ID. Use dryRun=true first to preview which workflows will have their identity_id set to null.

Inputs: identityId (required), dryRun, workspaceId.

delete_libraryA

Delete a context library (moves to trash, recoverable within 30 days). Requires owner or admin role.

Inputs: libraryId (required), workspaceId.

delete_phaseA

Delete a single phase from a project plan by its phase ID. Use this to remove a specific work item. To bulk-remove completed work, use delete_done_phases instead.

Inputs: phaseId (required), workspaceId.

dismiss_broadcastA

Dismiss a broadcast notification so it no longer appears in the inbox.

Inputs: broadcastId (required), workspaceId.

dispatch_agent_jobA

Dispatch an AI agent runner job with a natural-language intent. The runner autonomously selects the right agent, plans actions, and executes them. Returns a job ID you can poll with get_agent_job.

Inputs: intent (required), workspaceId.

figma_syncA

Manage Figma connector integrations — list connected files or trigger a sync to pull design tokens, components, and page structure into your Contextium libraries.

Inputs: action (required), workspaceId, integrationId.

getA

Get full details of a resource by ID. Use workspace_activity for recent activity logs. Use activity_archive to read a specific month's archived logs by YYYY-MM (e.g. 2025-02). Use list_activity_archives to see which months have archives. Use workflow_activity for the activity digest since a workflow's last session. Use entity_activity for recent activity on a specific file or entity.

Inputs: type (required), id, page, year, +13 more.

get_agent_jobA

Get the status and result of a specific agent runner job. Poll this after dispatch_agent_job to check completion.

Inputs: jobId (required), workspaceId.

get_identityA

Gets the full profile of a single identity by ID, including voice descriptors, writing samples, and all contextual fields.

Inputs: identityId (required), workspaceId.

get_notificationsB

Get the notification inbox for the current user — both activity notifications and broadcasts.

Inputs: limit, offset, unreadOnly, workspaceId.

get_projectA

Get the project plan attached to a workflow, including all its phases (open and completed). Returns phase titles, statuses, assigned agents, and sort order. Use this to understand what work is planned or in progress for a workflow.

Inputs: workflowId (required), workspaceId.

get_unread_countA

Get the total number of unread notifications (activity + broadcasts) for the current user.

Inputs: workspaceId.

idea_kickoffA

Autonomous business-idea kickoff. Call this FIRST and IMMEDIATELY whenever a user voices a brand-new business, product, app, SaaS, startup, or venture idea — e.g. "I have an idea for…", "I have a business idea", "I want to start a business that…", "I want to build a product that…", "what if there was an app that…", "here's a business idea", "idea: …". Returns instructions to run a FULL business analysis autonomously — SWOT, market size (live TAM/SAM/SOM), competitor analysis with funding/revenue/valuation, build plan, RICE scorecard, timeline, roles, two-tier startup financials, and a synthesised go/no-go verdict — written as files into a dedicated project library. Do NOT present a "what do you want to do with this idea" menu and do NOT run the step-by-step new_project wizard: the idea IS the go-ahead, so just do the research. Use new_project instead for a feature inside an EXISTING product; use capture_idea only for a lightweight "remember this" note.

Inputs: idea, workspaceId.

listA

List all resources of a given type in a workspace — the fast way to see what already exists before you act. Returns lightweight summaries (IDs, names, key fields), not full content: use get for one resource's full detail, or search to find resources by text or tag. Set type to choose what to list — workspaces, libraries (context libraries), agents, skills, files (pass libraryId), workflows, tags, file_tags (pass fileId), workspace_status, or members (with roles + activity). Uses your active workspace when workspaceId is omitted.

Inputs: type (required), fileId, status, folderId, +2 more.

list_agent_jobsA

List recent agent runner jobs for the workspace — shows status (pending, running, done, failed), intent, and result summary.

Inputs: workspaceId.

list_agentsB

Lists all agents (AI assistant configurations) in a workspace. Agents define assistant roles and capabilities.

Inputs: workspaceId.

list_commentsA

List the comments on a file — open (unresolved) threads by default. Comments are feedback to act on: each shows the author (members and external share-link guests), the anchored line number if any, and the comment id needed by resolve_comment / add_comment replies.

Inputs: fileId (required), includeResolved.

list_identitiesA

Lists identities visible to the current user in a workspace. Identities capture voice, tone, role, and audience context so AI produces work from the right perspective.

Inputs: scope, workspaceId.

list_phasesA

List all phases for a workflow's project plan, ordered by sort_order. Returns each phase with its ID, title, status (pending/in_progress/done/blocked), assigned agent name, and creation date. Use the phase IDs with update_phase_status to progress work.

Inputs: workflowId (required), workspaceId.

list_tasksA

List tasks. Omit workflowId to list ALL tasks across every workflow in the workspace. Provide workflowId to list a single workflow's tasks instead; these are DB tasks by default, or phase files tagged "task" for legacy file-backed workflows. Returns status, creator, priority, and due dates. Use sparingly — load_workflow already includes active workflow tasks.

Inputs: mine, status, priority, workflowId, +2 more.

list_trashA

List all context libraries currently in the workspace trash (deleted within the last 30 days, not yet permanently removed).

Inputs: workspaceId.

list_workflow_connectorsA

List the third-party connectors allocated to a workflow (GitHub, Grafana, etc.). Use this to discover what connector_id values you can call with connector_request. You never see any access token — only connector ids and base URLs.

Inputs: workflowId (required), workspaceId.

load_workflowC

Load complete workflow context — agents, skills, files, and libraries. Use this to initialise a full workflow session.

Inputs: workflowId (required), workspaceId, includeFileContent.

manage_relationshipA

Manage relationships: add/remove skills on agents, add/remove inline tags on files, and share/unshare a private workflow with an individual workspace member. For type=tag this EDITS THE FILE CONTENT — it writes (or deletes) a # token in the file body, which is the source of truth for a file's tags; the tag is auto-created if new. (Equivalent to updating the file content yourself.) For type=workflow_member, add is an upsert (re-adding an existing member updates their role).

Inputs: type (required), action (required), role, value, +7 more.

manual_project_setupA

Guided, interactive project setup — walks the user through creating a Contextium workspace step by step, asking for confirmation at each stage. Use when the user is present and wants to work through the setup together.

Inputs: workspaceId.

manual_research_setupA

Guided, interactive research workspace setup — walks the user through creating a research workspace step by step. Use when the user is present and wants to steer the research direction.

Inputs: workspaceId.

marketplaceA

Browse, inspect, and install shared skills, agents, and MCP servers from the Contextium Marketplace. Set action: "search" to browse listings (optionally filter by itemType skill/agent/mcp_server, category, or query); "get" for a listing's full details by slug; "install" to add a listing to a workspace by slug. Typically search first to find a slug, then get or install with it.

Inputs: action (required), slug, query, category, +2 more.

mark_notification_readA

Mark one notification as read, or mark all notifications as read when no ID is provided.

Inputs: workspaceId, notificationId.

new_projectA

Start a guided new Contextium project setup. Call this tool FIRST whenever a user wants to set up a new project in Contextium, create libraries/agents/skills for a project, get started with Contextium, or organise their AI context. Returns complete step-by-step setup instructions that you must follow exactly.

Inputs: no named parameters.

notify_team_membersA

Notify all eligible workspace team members about a resource you just created or updated — file, workflow, agent, or library. Use this when the user says things like "notify the team of this new file", "let everyone know about this workflow", or "notify @sarah about this". Respects each member's notification preferences and Do Not Disturb settings. Returns how many members were notified.

Inputs: resourceId (required), resourceName (required), resourceType (required), message, +5 more.

projectA

DEPRECATED — phases are now DB-backed. Use list_phases (replaces get_next_phase), update_phase_status(phaseId, "done") (replaces mark_phase_complete), and load_workflow (replaces load_session/close_session).

Inputs: action (required), workflowId (required), phaseFileId, workspaceId, +1 more.

reorder_phasesA

Reorder the phases in a workflow's project plan. Provide the full list of phase IDs in the desired order; the plan's sort order is updated to match.

Inputs: orderedIds (required), workflowId (required), workspaceId.

resolve_commentA

Resolve (acknowledge) a comment thread once it has been addressed — it disappears from default views everywhere (web, desktop, public share page, list_comments). Pass the ROOT comment id; the whole thread resolves. Set resolved=false to reopen.

Inputs: commentId (required), resolved.

restore_libraryA

Restore a context library from trash. Must be within the 30-day restore window.

Inputs: libraryId (required), workspaceId.

resume_projectA

Resume a Contextium project from a session handoff — loads the project plan, finds the last handoff note, and briefs you so you can continue without losing context. Call this when the user says things like: "resume my project", "continue where I left off", "pick up from last session", "what was I working on", "I'm back let's continue", "carry on from yesterday", "what's next in my project".

Inputs: workflowId, workspaceId.

share_createA

Create a public share link for a file so someone outside the workspace can view it. Returns the full link ONCE. accessMode "link" = anyone with the link; "restricted" = only allowlisted emails/domains (verified by emailed code). permission "view" or "download".

Inputs: fileId (required), accessMode, permission, allowComments, +3 more.

share_listA

List the active public share links for a file, with access mode, permission, and view count.

Inputs: fileId (required).

share_revokeA

Revoke a public share link. The link stops working immediately.

Inputs: fileId (required), shareId (required).

suggest_librariesA

Suggest existing context libraries that look relevant to a workflow you are about to create, ranked by keyword overlap between the workflow name/description and each library's name/description. Call this BEFORE create_workflow (or create type=workflow) so you can present the matches to the user and let them choose which to attach via projectIds. Nothing is auto-attached — these are suggestions only. Returns [] when no libraries score above zero.

Inputs: name (required), description, workspaceId.

summarize_done_phasesA

Generate an AI summary of all done phases in a workflow's project plan, save it as a context file in the specified library, then delete the source phases. Updates the plan's last_summarized_at timestamp.

Inputs: libraryId (required), workflowId (required), summaryTitle (required), workspaceId.

updateA

Update an existing resource in place by ID — edit a file's title, path, content, or status, or rename/reconfigure an agent, skill, workflow, or project. Only the fields you pass are changed; for files, a new version is created automatically so history is preserved. Set type to the resource kind and id to its UUID (from list/search/get).

File linking (type=file): to link to another file in the SAME workspace, put // inline in the content — use the target's UUID (from search/list/get results), not its title. The link renders as the target's title and is re-indexed on save; backlinks are automatic. To add a backlink to file B, add // to this file's content. Remove a link by deleting its // token. Only link to files that exist. Use get({ type: "file_links", id }) to inspect links and backlinks.

Inputs: id (required), type (required), name, path, +17 more.

update_identityB

Updates an existing identity by ID. Only the fields you provide are changed.

Inputs: identityId (required), name, type, scope, +13 more.

update_notification_preferencesA

Update notification preferences for the current user — per-type toggles, email frequency, or Do Not Disturb.

Inputs: preferences, workspaceId, doNotDisturb, emailEnabled, +3 more.

update_phase_statusA

Update the status of a project phase. Valid statuses: pending, in_progress, done, blocked. Use this to progress phases as work is completed. Setting a phase to "done" automatically records the completion time.

Inputs: status (required), phaseId (required), workspaceId.

update_taskA

Update a task title, description, or status. Works for all task types (DB tasks, phase tasks, file-backed tasks). Omit workflowId to update a task by id regardless of its workflow (the server resolves it). Use this instead of update_task_status when you also need to set a title or description.

Inputs: taskId (required), title, status, workflowId, +2 more.

update_task_statusA

Update the status of a task. Omit workflowId to update a task by id regardless of its workflow (the server resolves it). Updates the DB task record; for legacy file-backed workflows it instead swaps the status tag on the underlying phase file. Use in_progress when starting work, done when complete, dismissed when no longer relevant.

Inputs: status (required), taskId (required), priority, workflowId, +2 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 67 tools

    Disambiguation1/5

    Several tools are effectively indistinguishable or redundant: create_project and create_plan are exact aliases, generic create/update/list overlap with create_agent, create_resource, list_agents, and other typed tools, and new_project vs manual_project_setup both describe guided setup. The deprecated project tool adds yet another source of confusion.

    Naming Consistency2/5

    Lowercase snake_case is used throughout, but naming styles vary widely: generic single-verb CRUD (list, get, create, update, delete), noun-only tools (marketplace, project), reversed share_create/share_list, and product-prefixed names like contextium_status. Aliases such as create_project/create_plan and overlapping generic/specific tools make the pattern unpredictable.

    Tool Count1/5

    67 tools is far more than a focused MCP server should expose and will overwhelm agent selection and context. The surface bundles many unrelated domains—files, tasks, phases, identities, notifications, sharing, connectors, marketplace, and setup wizards—that should be split into separate servers.

    Completeness4/5

    The surface covers substantial lifecycle coverage: CRUD for files, libraries, agents, skills, workflows, identities, tasks, phases, comments, notifications, shares, and connectors. Minor gaps remain, such as no delete_task, no delete_project plan, and no get_comment, but agents can usually work around these.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      MCP server that gives AI coding agents on-demand access to private project docs via BM25 ranked search. One setup for Claude Code, Cursor, Codex, Gemini CLI, and more. Docs stay private, never in public repos.
      15
      16
      Apache 2.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      A local MCP server that provides a shared context and learning foundation across multiple AI tools (Claude, Copilot, Codex) for multiple projects, enabling persistent knowledge, decisions, and gap reflection through note storage.
      MIT