Summary
Connects Claude to OmegaAI workspaces, letting you query data, browse resources, and trigger automations without leaving your MCP client. Runs over streamable HTTP with OAuth 2.0, so you can point it at the hosted endpoint or self-host if needed. Reach for this when you're working with OmegaAI projects and want to pull workspace data, run queries, or kick off workflows directly from Claude instead of switching between tools. The remote transport means no local installation, just authenticate and start sending requests to your OmegaAI instance.
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.
26 tools
omega_storeStore a memory with optional type and metadata. Use when the user says 'remember this' or for programmatic capture (decisions, lessons, errors). Defaults to type 'memory' if event_type is omitted.9 params
Store a memory with optional type and metadata. Use when the user says 'remember this' or for programmatic capture (decisions, lessons, errors). Defaults to type 'memory' if event_type is omitted.
Parameters* required
textstringAlias for content — use either content or text
contentstringMemory content (also accepts 'text' as alias)
projectstringmetadataobjectAdditional metadata
priorityintegerMemory priority 1-5 (5=highest). Auto-set from event type if omitted.
entity_idstringScope this memory to an entity (e.g., 'acme'). Omit for unscoped.
agent_typestringAgent type for sub-agent memory scoping (e.g., 'code-reviewer', 'test-runner').
event_typestringType: memory (default), session_summary, task_completion, error_pattern, lesson_learned, decision, user_preference
session_idstringomega_querySearch memories — semantic (default) or exact phrase match. Use mode='phrase' for literal substring search (error messages, specific strings).13 params
Search memories — semantic (default) or exact phrase match. Use mode='phrase' for literal substring search (error messages, specific strings).
Parameters* required
modestringSearch mode: 'semantic' (default) for meaning-based search, 'phrase' for exact substring matchone of
semantic · phraselimitintegerdefault: 10
querystringSearch query (or exact phrase when mode='phrase')
projectstringentity_idstringFilter results to a specific entity (e.g., 'acme'). Omit for all.
agent_typestringFilter results to a specific agent type (e.g., 'code-reviewer'). Omit for all.
event_typestringFilter by event type
session_idstringfilter_tagsarrayHard filter — only return memories containing ALL specified tags (AND logic)
context_filestringCurrent file being edited (boosts results relevant to this file's context)
context_tagsarrayCurrent context tags like language, tools (boosts matching results)
case_sensitivebooleanCase-sensitive search (only used with mode='phrase', default false)default: false
temporal_rangearrayOptional [start_iso, end_iso] date range filter. Auto-inferred from query text if omitted.
omega_welcomeGet a session welcome briefing with recent relevant memories and user profile.2 params
Get a session welcome briefing with recent relevant memories and user profile.
Parameters* required
projectstringsession_idstringomega_profileRead or update the user profile. Returns the profile by default. If 'update' dict is provided, merges those fields into the profile and saves.1 params
Read or update the user profile. Returns the profile by default. If 'update' dict is provided, merges those fields into the profile and saves.
Parameters* required
updateobjectProfile fields to save (merged with existing). Omit to read profile.
omega_delete_memoryDelete a specific memory by its ID.1 params
Delete a specific memory by its ID.
Parameters* required
memory_idstringThe memory ID to delete
omega_edit_memoryEdit the content of a specific memory.2 params
Edit the content of a specific memory.
Parameters* required
memory_idstringThe memory ID to edit
new_contentstringNew content for the memory
omega_list_preferencesList all stored user preferences.
List all stored user preferences.
No parameter schema in public metadata yet.
omega_healthDetailed health check with memory usage, node counts, cache stats, warnings, and recommendations.3 params
Detailed health check with memory usage, node counts, cache stats, warnings, and recommendations.
Parameters* required
warn_mbnumberMemory warning threshold in MB (default 350)default: 350
max_nodesintegerMaximum expected nodes (default 10000)default: 10000
critical_mbnumberMemory critical threshold in MB (default 800)default: 800
omega_backupExport or import memories for backup/restore. Default mode is export.3 params
Export or import memories for backup/restore. Default mode is export.
Parameters* required
modestringOperation mode: 'export' (default) or 'import'default: export
filepathstringFile path for export or import
clear_existingbooleanClear current data before import (default true, only used in import mode)default: true
omega_lessonsRetrieve cross-session or cross-project lessons learned, ranked by verification count and access frequency.7 params
Retrieve cross-session or cross-project lessons learned, ranked by verification count and access frequency.
Parameters* required
taskstringOptional task description for relevance filtering
limitintegerMax lessons to return (default 5)default: 5
agent_typestringFilter lessons to a specific agent type (e.g., 'code-reviewer'). Omit for all.
project_pathstringOptional project scope
cross_projectbooleanIf true, search across all projects (default false)default: false
exclude_projectstringProject path to exclude (only used with cross_project=true)
exclude_sessionstringSession ID to exclude
omega_feedbackRecord feedback on a surfaced memory (helpful, unhelpful, outdated). Improves future surfacing quality.3 params
Record feedback on a surfaced memory (helpful, unhelpful, outdated). Improves future surfacing quality.
Parameters* required
ratingstringOne of: helpful, unhelpful, outdated
reasonstringOptional explanation
memory_idstringThe memory node ID to rate
omega_clear_sessionClear all memories for a specific session. Use for cleanup after test sessions.1 params
Clear all memories for a specific session. Use for cleanup after test sessions.
Parameters* required
session_idstringThe session ID to purge
omega_similarFind memories similar to a given memory. Use for discovering related context.2 params
Find memories similar to a given memory. Use for discovering related context.
Parameters* required
limitintegerMax results (default 5)default: 5
memory_idstringThe memory node ID to find similar memories for
omega_timelineShow memory timeline grouped by day. Use to see what was captured recently.2 params
Show memory timeline grouped by day. Use to see what was captured recently.
Parameters* required
daysintegerNumber of days to look back (default 7)default: 7
limit_per_dayintegerMax memories per day (default 10)default: 10
omega_consolidateRun memory consolidation: prune stale low-value memories, cap session summaries, clean orphaned edges. Returns a report.2 params
Run memory consolidation: prune stale low-value memories, cap session summaries, clean orphaned edges. Returns a report.
Parameters* required
prune_daysintegerPrune zero-access memories older than N days (default 30)default: 30
max_summariesintegerMax session summaries to keep (default 50)default: 50
omega_traverseTraverse the memory relationship graph from a starting memory. Shows all connected memories within N hops, useful for understanding context chains and discovering related knowledge clusters.3 params
Traverse the memory relationship graph from a starting memory. Shows all connected memories within N hops, useful for understanding context chains and discovering related knowledge clusters.
Parameters* required
max_hopsintegerMaximum traversal depth (1-5, default 2)default: 2
memory_idstringThe starting memory node ID
min_weightnumberMinimum edge weight to follow (0.0-1.0, default 0.0)default: 0
omega_compactCompact related memories into consolidated knowledge nodes. Finds clusters of similar memories (same event type, high overlap) and creates summary nodes, marking originals as superseded. Reduces noise while preserving knowledge.4 params
Compact related memories into consolidated knowledge nodes. Finds clusters of similar memories (same event type, high overlap) and creates summary nodes, marking originals as superseded. Reduces noise while preserving knowledge.
Parameters* required
dry_runbooleanPreview clusters without compacting (default false)default: false
event_typestringEvent type to compact (default: lesson_learned)default: lesson_learned
min_cluster_sizeintegerMinimum memories in a cluster to compact (default 3)default: 3
similarity_thresholdnumberMinimum Jaccard similarity for clustering (0.0-1.0, default 0.6)default: 0.6
omega_checkpointSave a task checkpoint — captures current plan, progress, files touched, decisions, and key context. Use when: (1) context window is getting full, (2) completing a major milestone, (3) before starting a new session for an ongoing task. Checkpoints enable seamless session conti...9 params
Save a task checkpoint — captures current plan, progress, files touched, decisions, and key context. Use when: (1) context window is getting full, (2) completing a major milestone, (3) before starting a new session for an ongoing task. Checkpoints enable seamless session conti...
Parameters* required
planstringCurrent plan or goals — what you're trying to accomplish
projectstringProject path
progressstringWhat's been completed, what's in progress, what remains
decisionsarrayKey technical decisions made during this task
next_stepsstringWhat should be done next to continue this task
session_idstringCurrent session ID
task_titlestringBrief title of the current task (e.g., 'Frontend redesign Phase 2')
key_contextstringCritical context needed to continue — patterns, variable names, API shapes, conventions
files_touchedobjectMap of file paths to change summaries (e.g., {'src/App.tsx': 'Added routing'})
omega_resume_taskResume a previously checkpointed task. Retrieves the latest checkpoint with full plan, progress, files, decisions, and next steps. Use at the start of a new session to continue where you left off.4 params
Resume a previously checkpointed task. Retrieves the latest checkpoint with full plan, progress, files, decisions, and next steps. Use at the start of a new session to continue where you left off.
Parameters* required
limitintegerNumber of checkpoints to retrieve (default 1 = latest only)
projectstringProject path to filter checkpoints
verbositystringHow much context to return. 'full' = everything, 'summary' = plan + progress + next steps, 'minimal' = just next stepsone of
full · summary · minimaltask_titlestringTitle of the task to resume (semantic search — doesn't need to be exact)
omega_remindSet a time-based reminder. OMEGA will surface it when the time arrives (at session start or during active sessions). Use for 'remind me in 1 hour to...' requests.5 params
Set a time-based reminder. OMEGA will surface it when the time arrives (at session start or during active sessions). Use for 'remind me in 1 hour to...' requests.
Parameters* required
textstringWhat to be reminded about
contextstringOptional context to include with the reminder (e.g. relevant file paths, decisions)
projectstringdurationstringWhen to remind, e.g. '1h', '30m', '2d', '1w', '1d12h', '2 hours'
session_idstringomega_remind_listList active reminders with their status and due times.1 params
List active reminders with their status and due times.
Parameters* required
statusstringFilter by status (default: shows pending + fired)one of
pending · fired · dismissed · allomega_remind_dismissDismiss a reminder by its ID. Use after acknowledging a reminder.1 params
Dismiss a reminder by its ID. Use after acknowledging a reminder.
Parameters* required
reminder_idstringThe reminder memory ID to dismiss
omega_type_statsGet memory counts grouped by event type. Shows the composition of the memory store (how many decisions, lessons, errors, etc.).
Get memory counts grouped by event type. Shows the composition of the memory store (how many decisions, lessons, errors, etc.).
No parameter schema in public metadata yet.
omega_session_statsGet memory counts grouped by session. Shows which sessions have contributed the most memories (top 20).
Get memory counts grouped by session. Shows which sessions have contributed the most memories (top 20).
No parameter schema in public metadata yet.
omega_weekly_digestGet a weekly knowledge digest with stats, trends, and highlights. Shows new memories, session count, growth trends, type breakdown, and top topics.1 params
Get a weekly knowledge digest with stats, trends, and highlights. Shows new memories, session count, growth trends, type breakdown, and top topics.
Parameters* required
daysintegerNumber of days to include in the digest (default 7)default: 7
omega_protocolGet your coordination playbook — dynamically assembled operating instructions. Call at session start (step 2 after omega_welcome) or when you need protocol guidance. Returns context-sensitive rules based on project, peer activity, and learned lessons.2 params
Get your coordination playbook — dynamically assembled operating instructions. Call at session start (step 2 after omega_welcome) or when you need protocol guidance. Returns context-sensitive rules based on project, peer activity, and learned lessons.
Parameters* required
projectstringCurrent project path for context-sensitive protocol rules.
sectionstringSpecific section or group: 'memory', 'coordination', 'coordination_gate', 'teamwork', 'context', 'reminders', 'diagnostics', 'entity', 'heuristics', 'git', 'what_next'. Groups: 'solo', 'multi_agent', 'full', 'minimal'. Omit for auto-detect based on peer activity.
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
UpdatedMay 10, 2026
