MCP Awareness
UnclaimedCross-platform memory and ambient awareness for AI agents — knowledge store, alert collation, and intention tracking via MCP. Self-host or cloud.
Install
pip install -e ".[dev]" # install with dev dependenciesSet up this server
More in AI & ML
Browse the full directoryUnclaimed listing
Is this your MCP server?
This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.
Claim this serverSecurity profile
Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works
32 of 32 tools
Documented tools (32)
From project documentation. A server handshake does not verify each tool’s description or behavior.
acted_on
Log that you took action because of an entry. Tags inherited from the entry.
add_context
Store temporal knowledge that auto-expires (default 30 days). Use for current events, milestones, or temporary states that will become stale.
backfill_embeddings
Generate embeddings for entries that don't have one yet, and re-embed stale entries whose content changed. Requires embedding provider.
create_record
Write a validated data entry conforming to a registered schema. Records pin exact schema version and re-validate on content update. Validation errors include every failure with structured envelope.
delete_entry
Soft-delete entries (30-day trash). By ID, by source + type, or by source. Bulk deletes require confirm=True (dry-run by default).
get_actions
Action history — what was done because of an entry.
get_activity
Combined read + action feed, chronological.
get_alerts
Active alerts, optionally filtered by source. Drill-down from briefing.
get_briefing
Compact awareness summary (~200 tokens all-clear, ~500 with issues). Call at conversation start. Pre-filtered through patterns and suppressions.
get_deleted
List all entries in trash with IDs for restore.
get_intentions
Pending/active intentions, optionally filtered by state, source, or tags.
get_knowledge
Knowledge entries (patterns, context, preferences, notes). Filter by source, tags, entrytype, since/until, createdafter/createdbefore, learnedfrom. hint param re-ranks results by semantic similarity.
get_reads
Read history for entries — who read what, when, from which platform.
get_related
Bidirectional entry relationships — entries referenced via relatedids and entries that reference the given entry.
get_stats
Entry counts by type, list of sources, total count. Call before getknowledge to decide whether to filter.
get_status
Full status for a specific source including metrics and inventory.
get_suppressions
Active alert suppressions with expiry times and escalation settings.
get_tags
All tags in use with usage counts. Use to discover existing tags and prevent drift.
get_unread
Entries with zero reads. Cleanup candidates or missed knowledge.
learn_pattern
Record an if/then operational rule with conditions/effects for alert matching. Use only when there's a clear "when X happens, expect Y" relationship.
register_schema
Define a typed data contract using JSON Schema Draft 2020-12. Schemas are immutable after registration; family + version become logicalkey. Per-owner with system fallback for shared built-in shapes.
remember
Store permanent knowledge — facts still true in 30 days. Optional content payload with MIME contenttype. Default choice for personal facts, project notes, design decisions.
remind
Create a todo, reminder, or planned action. Optional deliverat timestamp for time-based surfacing. Intentions have a lifecycle: pending → fired → active → completed.
report_alert
Report or resolve an alert. Captures diagnostics at detection time. Levels: warning, critical. Types: threshold, structural, baseline.
report_status
Report system status. Called periodically by edge processes. Upserts one entry per source; stale if TTL expires without refresh.
restore_entry
Restore a soft-deleted entry from trash.
search
Hybrid search — finds entries by meaning (vector) and by exact terms (FTS), fused via Reciprocal Rank Fusion. Combines with tag/source/type/date/language filters. Requires embedding provider for vector branch; FTS works without it.
semantic_search
Deprecated alias for search. Will be removed in a future release.
set_preference
Set a portable presentation preference (e.g., alertverbosity, checkfrequency). Upserts by key + scope.
suppress_alert
Suppress alerts by source/tags/metric. Time-limited with escalation override — critical alerts can break through.
update_entry
Update a knowledge entry in place (note, pattern, context, preference). Tracks changes in changelog. Status/alert/suppression are immutable.
update_intention
Transition an intention state: pending → fired → active → completed/snoozed/cancelled.
Tool change history
FAQ
Questions about MCP Awareness MCP Server
- How do I connect MCP Awareness MCP Server to Claude?
- The listing records `pip install -e ".[dev]" # install with dev dependencies` as its setup step. Run it, then follow the repository's instructions for the client configuration; the listing names Claude Desktop, Claude Code, Cursor as compatible clients.
- Is MCP Awareness MCP Server free?
- The listed licence is AGPL-3.0. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
- What can MCP Awareness MCP Server do?
- MCP Awareness MCP Server documents 32 tools to the agent, including acted_on, add_context, backfill_embeddings. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.