projects_index
Trigger indexing for a project
Access: Free
search_semantic
Semantic vector search
Access: Free
search_hybrid
Hybrid search (semantic + keyword)
Access: Free
search_keyword
Keyword search
Access: Free
memory_create_event
Create a memory event for a workspace/project
Access: Free
memory_list_events
List memory events (optionally scoped)
Access: Free
memory_create_node
Create a knowledge node with optional relations
Access: Free
memory_list_nodes
List knowledge graph nodes
Access: Free
memory_search
Search memory events/notes
Access: Free
memory_decisions
List decision summaries from workspace memory
Access: Free
graph_related
Find related nodes in the knowledge graph
Access: Elite/Team (Full Graph) (upgrade: https://contextstream.io/pricing)
graph_path
Find path between two nodes
Access: Elite/Team (Full Graph) (upgrade: https://contextstream.io/pricing)
graph_decisions
Decision history in the knowledge graph
Access: Elite/Team (Full Graph) (upgrade: https://contextstream.io/pricing)
graph_dependencies
Dependency graph query
Access: Pro (Graph-Lite) (upgrade: https://contextstream.io/pricing)
graph_call_path
Find call path between two targets
Access: Elite/Team (Full Graph) (upgrade: https://contextstream.io/pricing)
graph_impact
Analyze impact of a target node
Access: Pro (Graph-Lite) (upgrade: https://contextstream.io/pricing)
graph_ingest
Build and persist the dependency graph for a project. Runs async by default (wait=false) and can take a few minutes for larger repos.
Access: Elite/Team (Full Graph) (upgrade: https://contextstream.io/pricing)
projects_get
Get project details by ID
Access: Free
projects_overview
Get project overview with summary information
Access: Free
projects_statistics
Get project statistics (files, lines, complexity)
Access: Free
projects_files
List all indexed files in a project
Access: Free
projects_index_status
Get project indexing status
Access: Free
projects_ingest_local
Read ALL files from a local directory and ingest them for indexing.
This indexes your entire project by reading files in batches.
Automatically detects code files and skips ignored directories like node_modules, target, dist, etc.
Access: Free
workspaces_get
Get workspace details by ID
Access: Free
memory_get_event
Get a specific memory event by ID with FULL content (not truncated). Use this when you need the complete content of a memory event, not just the preview returned by search/recall.
Access: Free
memory_update_event
Update a memory event
Access: Free
memory_delete_event
Delete a memory event
Access: Free
memory_timeline
Get chronological timeline of memory events for a workspace
Access: Free
memory_summary
Get condensed summary of workspace memory
Access: Free
graph_circular_dependencies
Detect circular dependencies in project code
Access: Elite/Team (Full Graph) (upgrade: https://contextstream.io/pricing)
graph_unused_code
Detect unused code in project
Access: Elite/Team (Full Graph) (upgrade: https://contextstream.io/pricing)
session_init
Initialize a new conversation session and automatically retrieve relevant context.
This is the FIRST tool AI assistants should call when starting a conversation.
Returns: workspace info, project info, recent memory, recent decisions, relevant context, and high-priority lessons.
Automatically detects the IDE workspace/project path and can auto-index code.
IMPORTANT: Pass the user's FIRST MESSAGE as context_hint to get semantically relevant context!
Example: session_init(folder_path="/path/to/project", context_hint="how do I implement auth?")
This does semantic search on the first message. You only need context_smart on subsequent messages.
Access: Free
session_tools
Get an ultra-compact list of all available ContextStream MCP tools.
Use this when you need to know what tools are available without reading full descriptions.
Returns a token-efficient tool catalog (~120 tokens) organized by category.
Format options:
- 'grouped' (default): Category: tool(hint) tool(hint) - best for quick reference
- 'minimal': Category:tool|tool|tool - most compact
- 'full': Detailed list with descriptions
Example output (grouped):
Session: init(start-conv) smart(each-msg) capture(save) recall(find) remember(quick)
Search: semantic(meaning) hybrid(combo) keyword(exact)
Memory: events(crud) nodes(knowledge) search(find) decisions(choices)
Access: Free
session_get_user_context
Retrieve user preferences, coding style, and persona from memory.
Use this to understand how the user likes to work and adapt your responses accordingly.
Access: Free
workspace_associate
Associate a folder/repo with a workspace after user selection.
Call this after session_init returns status='requires_workspace_selection' and the user has chosen a workspace.
This persists the selection to .contextstream/config.json so future sessions auto-connect.
Optionally creates a parent folder mapping (e.g., all repos under /dev/company/* map to the same workspace).
Optionally generates AI editor rules for automatic ContextStream usage.
Access: Free
workspace_bootstrap
Create a new workspace (user-provided name) and onboard the current folder as a project.
This is useful when session_init returns status='requires_workspace_name' (no workspaces exist yet) or when you want to create a new workspace for a repo.
Behavior:
- Creates a workspace with the given name
- Associates the folder to that workspace (writes .contextstream/config.json)
- Initializes a session for the folder, which creates the project (folder name) and starts indexing (if enabled)
Access: Free
session_capture
Automatically capture and store important context from the conversation.
Use this to persist decisions, insights, preferences, or important information.
Access: Free
session_capture_lesson
Capture a lesson learned from a mistake or correction.
Use this when the user corrects you, expresses frustration, or points out an error.
These lessons are surfaced in future sessions to prevent repeating the same mistakes.
Example triggers:
- User says "No, you should..." or "That's wrong"
- User expresses frustration (caps, "COME ON", "WTF")
- Code breaks due to a preventable mistake
The lesson will be tagged with 'lesson' and stored with structured metadata for easy retrieval.
Access: Free
session_get_lessons
Retrieve lessons learned from past mistakes and corrections.
Use this to check for relevant warnings before taking actions that have caused problems before.
Returns lessons filtered by:
- Query: semantic search for relevant lessons
- Category: workflow, code_quality, verification, communication, project_specific
- Severity: low, medium, high, critical
Access: Free
session_smart_search
Search memory with automatic context enrichment.
Returns memory matches, relevant code, and related decisions in one call.
Access: Free
session_remember
Quick way to store something in memory. Use natural language.
Example: "Remember that I prefer TypeScript strict mode" or "Remember we decided to use PostgreSQL"
Access: Free
session_recall
Quick way to recall relevant context. Use natural language.
Example: "What were the auth decisions?" or "What are my TypeScript preferences?"
Access: Free
generate_editor_rules
Generate AI rule files for editors (Windsurf, Cursor, Cline, Kilo Code, Roo Code, Claude Code, Aider).
These rules instruct the AI to automatically use ContextStream for memory and context.
Supported editors: codex, windsurf, cursor, cline, kilo, roo, claude, aider
Access: Free
session_summary
Get a compact, token-efficient summary of workspace context (~500 tokens).
This is designed to replace loading full chat history in AI prompts.
Returns: workspace/project info, top decisions (titles only), preferences, memory count.
Use this at conversation start instead of loading everything.
For specific details, use session_recall or session_smart_search.
Access: Free
session_compress
Extract and store key information from chat history as memory events.
This allows clearing chat history while preserving important context.
Use at conversation end or when context window is getting full.
Extracts:
- Decisions made
- User preferences learned
- Insights discovered
- Tasks/action items
- Code patterns established
After compression, the AI can use session_recall to retrieve this context in future conversations.
Access: Free
session_delta
Get new context added since a specific timestamp.
Useful for efficient context synchronization without reloading everything.
Returns:
- Count of new decisions and memory events
- List of new items with titles and timestamps
Use case: AI can track what's new since last session_init.
Access: Free
context_smart
**CALL THIS BEFORE EVERY AI RESPONSE** to get relevant context.
This is the KEY tool for token-efficient AI interactions. It:
1. Analyzes the user's message to understand what context is needed
2. Retrieves only relevant context in a minified, token-efficient format
3. Replaces the need to include full chat history in prompts
Format options:
- 'minified': Ultra-compact D:decision|P:preference|M:memory (default, ~200 tokens)
- 'readable': Line-separated with labels
- 'structured': JSON-like grouped format
Type codes: W=Workspace, P=Project, D=Decision, M=Memory, I=Insight, T=Task, L=Lesson
Example usage:
1. User asks "how should I implement auth?"
2. AI calls context_smart(user_message="how should I implement auth?")
3. Gets: "W:Maker|P:contextstream|D:Use JWT for auth|D:No session cookies|M:Auth API at /auth/..."
4. AI responds with relevant context already loaded
This saves ~80% tokens compared to including full chat history.
Access: Free
reminders_list
List all reminders for the current user.
Returns: reminders with title, content, remind_at, priority, status, and keywords.
Can filter by status (pending, completed, dismissed, snoozed) and priority (low, normal, high, urgent).
Use this to see what reminders you have set.
Access: Free
reminders_active
Get active reminders that are pending, overdue, or due soon.
Returns: reminders with urgency levels (overdue, due_soon, today, upcoming).
Optionally provide context (e.g., current task description) to get contextually relevant reminders.
Use this to see what reminders need attention now.
Access: Free
reminders_create
Create a new reminder for a specific date/time.
Set reminders to be notified about tasks, follow-ups, or important dates.
Priority levels: low, normal, high, urgent
Recurrence: daily, weekly, monthly (optional)
Example: Create a reminder to "Review PR #123" for tomorrow at 10am with high priority.
Access: Free
reminders_snooze
Snooze a reminder until a later time.
Use this to postpone a reminder without dismissing it.
Common snooze durations:
- 1 hour: add 1 hour to current time
- 4 hours: add 4 hours
- Tomorrow: next day at 9am
- Next week: 7 days from now
Access: Free
reminders_complete
Mark a reminder as completed.
Use this when the task or action associated with the reminder is done.
Access: Free
reminders_dismiss
Dismiss a reminder without completing it.
Use this to remove a reminder that is no longer relevant.
Access: Free