Summary
If you're running data pipelines and need to know when things break before your users do, this wraps AnomalyArmor's observability platform into 52 MCP tools. You get alerts, freshness checks, schema drift detection, and data quality metrics directly in Claude. The tools are grouped by domain: manage alert rules and destinations, set up freshness schedules, create validity rules and referential checks, explore lineage, and ask natural language questions about your data. It surfaces a daily briefing with unresolved alerts and coverage gaps. Requires an AnomalyArmor account and API key. Useful when you want AI assistance debugging stale tables, analyzing schema changes, or configuring monitoring without leaving your editor.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Tools
Public tool metadata for what this MCP can expose to an agent.
53 tools
get_alerts_summaryGet alert overview with counts by status and severity. Quick snapshot of triggered, acknowledged, and resolved alerts. For individual alerts use list_alerts.
Get alert overview with counts by status and severity. Quick snapshot of triggered, acknowledged, and resolved alerts. For individual alerts use list_alerts.
No parameter schema in public metadata yet.
list_alertsList recent alerts with severity, status, and asset info. Use update_alert to acknowledge, resolve, dismiss, or snooze alerts.6 params
List recent alerts with severity, status, and asset info. Use update_alert to acknowledge, resolve, dismiss, or snooze alerts.
Parameters* required
asset_idvalueFilter by asset UUID (from list_assets)
from_datevalueStart of date range (ISO 8601, e.g., "2026-01-29T00:00:00Z")
limitintegerMaximum results (default 25, max 100)default: 25
severityvalueFilter by severity ("info", "warning", "critical")
statusvalueFilter by status ("triggered", "acknowledged", "resolved", "dismissed", "snoozed")
to_datevalueEnd of date range (ISO 8601)
list_inbox_alertsList unresolved alerts in inbox view (triggered + acknowledged only). Focused view for triaging active alerts. Use update_alert to take action.3 params
List unresolved alerts in inbox view (triggered + acknowledged only). Focused view for triaging active alerts. Use update_alert to take action.
Parameters* required
asset_idvalueFilter by asset UUID (from list_assets)
limitintegerMaximum results (default 25)default: 25
severityvalueFilter by severity ("info", "warning", "critical")
update_alertUpdate an alert's lifecycle status. Use list_alerts to find alert IDs.6 params
Update an alert's lifecycle status. Use list_alerts to find alert IDs.
Parameters* required
action_categoryvalueFor resolve/dismiss: reran_job, updated_sql, rolled_back,
false_positive, expected_behavior, code_change, other
alert_idstringAlert UUID (from list_alerts)
duration_hoursintegerSnooze duration in hours, 1-720 (default 24). Only for status="snoozed".default: 24
notesvalueOptional notes explaining the status change
root_cause_categoryvalueFor resolve/dismiss: pipeline_failure, schema_change,
data_source_issue, configuration_error, expected_behavior,
code_change, infrastructure, unknown
statusstringNew status: "acknowledged", "resolved", "dismissed", or "snoozed"
list_alert_rulesList configured alert rules showing which events and severities each rule monitors. Use create_alert_rule to add new rules, list_destinations to find destination IDs for routing.2 params
List configured alert rules showing which events and severities each rule monitors. Use create_alert_rule to add new rules, list_destinations to find destination IDs for routing.
Parameters* required
active_onlybooleanOnly return active rules (default True)default: true
asset_idvalueFilter by asset UUID (from list_assets)
create_alert_ruleCreate an alert rule to notify when data issues are detected. Routes to specified destinations (or default email). Use list_destinations to find destination IDs, list_assets for asset IDs.6 params
Create an alert rule to notify when data issues are detected. Routes to specified destinations (or default email). Use list_destinations to find destination IDs, list_assets for asset IDs.
Parameters* required
asset_idsvalueUUIDs of assets to scope the rule to (from list_assets). Omit for all.
descriptionvalueOptional description of the rule's purpose
destination_idsvalueUUIDs of destinations to route alerts to (from list_destinations).
Falls back to default email if omitted.
event_typesvalueEvent types to monitor: "freshness_stale", "schema_drift",
"metric_anomaly", "validity_failure", "custom_sql". Omit for all.
namestringHuman-readable name for the alert rule
severitiesvalueSeverity levels to trigger on: "info", "warning", "critical". Omit for all.
manage_alert_ruleManage an existing alert rule: get details, update, or delete. Use list_alert_rules to find rule IDs.7 params
Manage an existing alert rule: get details, update, or delete. Use list_alert_rules to find rule IDs.
Parameters* required
actionstringOperation: "get", "update", or "delete"
descriptionvalueNew description (for update)
event_typesvalueNew event types (for update)
is_activevalueEnable/disable rule (for update)
namevalueNew name (for update)
rule_idstringAlert rule UUID (from list_alert_rules)
severitiesvalueNew severity levels (for update)
get_alert_trendsGet aggregate alert trend data across all assets. Shows alert volume and patterns over time for trend analysis.1 params
Get aggregate alert trend data across all assets. Shows alert volume and patterns over time for trend analysis.
Parameters* required
periodstringTime period: "24h", "7d", "30d", "90d" (default "7d")default: 7d
get_alert_historyGet status change history for a specific alert. Shows the full lifecycle: when it was triggered, acknowledged, resolved, etc., with notes and who made each change.1 params
Get status change history for a specific alert. Shows the full lifecycle: when it was triggered, acknowledged, resolved, etc., with notes and who made each change.
Parameters* required
alert_idstringAlert UUID (from list_alerts)
get_api_key_infoView API key information (read-only). Cannot create or revoke keys.2 params
View API key information (read-only). Cannot create or revoke keys.
Parameters* required
key_idvalueAPI key UUID (required for view="detail")
viewstringWhat to show:
"list" - list all API keys with names and last-used dates
"detail" - get details of a specific key (requires key_id)
"usage" - show API usage statisticsdefault: list
list_assetsList all connected data assets (databases, warehouses). Returns asset IDs needed by most other tools. Start here to find asset UUIDs for use with check_freshness, list_metrics, explore, etc.2 params
List all connected data assets (databases, warehouses). Returns asset IDs needed by most other tools. Start here to find asset UUIDs for use with check_freshness, list_metrics, explore, etc.
Parameters* required
asset_typevalueFilter by type ("postgresql", "snowflake", "bigquery", etc.)
limitintegerMaximum results (default 25)default: 25
trigger_asset_discoveryStart schema discovery for an asset. Discovers all schemas, tables, columns, and metadata. Runs as background job. Use job_status() to track progress, then explore() to browse results.1 params
Start schema discovery for an asset. Discovers all schemas, tables, columns, and metadata. Runs as background job. Use job_status() to track progress, then explore() to browse results.
Parameters* required
asset_idstringAsset UUID (from list_assets)
create_assetConnect a new data source to AnomalyArmor. After creating, use trigger_asset_discovery to discover tables and columns.4 params
Connect a new data source to AnomalyArmor. After creating, use trigger_asset_discovery to discover tables and columns.
Parameters* required
connection_configobjectConnection details (varies by source_type). Examples:
PostgreSQL: {"host": "...", "port": 5432, "database": "...",
"username": "...", "password": "..."}
Snowfla...
descriptionvalueOptional description of the data source
namestringDisplay name for the asset (e.g., "Production PostgreSQL")
source_typestringDatabase type: "postgresql", "snowflake", "bigquery",
"redshift", "mysql", "databricks"
manage_assetGet asset details or test its connection.2 params
Get asset details or test its connection.
Parameters* required
actionstringOperation to perform:
"get" - get full asset details including schema, table count, etc.
"test" - test the database connection is working
asset_idstringAsset UUID (from list_assets)
get_lineageGet data lineage for an asset showing upstream sources and downstream consumers. Requires a dbt manifest to be uploaded via the UI or API.4 params
Get data lineage for an asset showing upstream sources and downstream consumers. Requires a dbt manifest to be uploaded via the UI or API.
Parameters* required
asset_idstringAsset UUID (from list_assets)
depthintegerHow many hops to traverse (default 2)default: 2
directionstringLineage direction: "upstream", "downstream", or "both" (default "both")default: both
list_allbooleanList all lineage entries for the asset instead of graph view (default False)default: false
job_statusCheck status of an async job (discovery, intelligence generation, etc.). Returns a user_status field with simplified status: "in_progress", "completed", "failed", or "cancelled". Internal states like "pending" and "claimed" are mapped to "in_progress" so consumers don't need t...1 params
Check status of an async job (discovery, intelligence generation, etc.). Returns a user_status field with simplified status: "in_progress", "completed", "failed", or "cancelled". Internal states like "pending" and "claimed" are mapped to "in_progress" so consumers don't need t...
Parameters* required
job_idstringJob UUID (from trigger_asset_discovery, generate_intelligence, etc.)
cancel_jobCancel a running or pending background job. Use this when a long-running operation (intelligence generation, asset discovery) needs to be stopped.1 params
Cancel a running or pending background job. Use this when a long-running operation (intelligence generation, asset discovery) needs to be stopped.
Parameters* required
job_idstringJob UUID (from trigger_asset_discovery, generate_intelligence, etc.)
create_tagCreate a new tag for labeling database objects. After creating, use apply_tags to attach it to tables or columns.3 params
Create a new tag for labeling database objects. After creating, use apply_tags to attach it to tables or columns.
Parameters* required
colorvalueOptional hex color code (e.g., "#FF5733")
descriptionvalueOptional description of the tag's purpose
namestringTag name (e.g., "pii", "revenue-critical", "deprecated")
list_tagsList tags applied to database objects within an asset. Use explore to find valid object paths.2 params
List tags applied to database objects within an asset. Use explore to find valid object paths.
Parameters* required
asset_idstringAsset UUID (from list_assets)
object_pathvalueFilter to tags on a specific object (e.g., "public.users.email")
apply_tagsApply tags to database objects. Supports single or cross-asset bulk tagging. Use explore to find valid object paths before tagging.5 params
Apply tags to database objects. Supports single or cross-asset bulk tagging. Use explore to find valid object paths before tagging.
Parameters* required
asset_idstringAsset UUID (from list_assets)
asset_idsvalueApply tags across multiple assets (for bulk apply, overrides asset_id)
object_pathvalueFull path to the object (e.g., "public.users.email")
object_typestringType of database object: "column", "table", or "schema"default: column
tagsvalueList of tag names to apply (e.g., ["pii", "revenue-critical"])
get_coverageGet monitoring coverage score and tier information. Shows how well your data assets are monitored with scores, tiers, and per-feature breakdowns.2 params
Get monitoring coverage score and tier information. Shows how well your data assets are monitored with scores, tiers, and per-feature breakdowns.
Parameters* required
asset_idvalueAsset UUID (required when scope="asset")
scopestringCoverage scope:
"company" - company-wide rollup across all assets
"asset" - per-asset score with feature breakdown (requires asset_id)default: company
manage_coverageAnalyze coverage gaps or apply monitoring recommendations in batch. Use get_coverage to see current scores first.5 params
Analyze coverage gaps or apply monitoring recommendations in batch. Use get_coverage to see current scores first.
Parameters* required
actionstringOperation to perform:
"gaps" - list unmonitored tables ranked by importance
"apply" - apply recommended monitoring in batch
asset_idstringAsset UUID (from list_assets)
limitintegerMaximum gap recommendations (for gaps action, default 20)default: 20
table_pathsvalueLimit to specific tables (for apply action, omit for all)
typesvalueMonitoring types to apply: "freshness", "metrics", "schema_drift"
(for apply action, omit for all)
list_destinationsList configured alert destinations (Slack, email, webhook). Returns ALL destinations by default, including disabled ones. Check the is_active field to see if a destination is enabled or disabled. Prefer re-enabling existing destinations over creating new ones. Returns destinat...2 params
List configured alert destinations (Slack, email, webhook). Returns ALL destinations by default, including disabled ones. Check the is_active field to see if a destination is enabled or disabled. Prefer re-enabling existing destinations over creating new ones. Returns destinat...
Parameters* required
active_onlybooleanOnly return active destinations (default False, shows all)default: false
destination_typevalueFilter by type: "slack", "webhook", "email"
setup_destinationCreate an alert destination with auto-discovery. For Slack: provide channel_name (auto-discovers OAuth connection). For webhook: provide webhook_url. For email: provide email address. After creating, use create_alert_rule to route alerts to the destination.5 params
Create an alert destination with auto-discovery. For Slack: provide channel_name (auto-discovers OAuth connection). For webhook: provide webhook_url. For email: provide email address. After creating, use create_alert_rule to route alerts to the destination.
Parameters* required
channel_namevalueSlack channel name without # (required for Slack)
destination_typestringType of destination: "slack", "webhook", or "email"
emailvalueEmail address (required for email)
namevalueDisplay name for the destination (auto-generated if omitted)
webhook_urlvalueFull webhook URL (required for webhook)
manage_destinationManage an existing alert destination: get details, update, delete, or test. Use list_destinations to find destination IDs.5 params
Manage an existing alert destination: get details, update, delete, or test. Use list_destinations to find destination IDs.
Parameters* required
actionstringOperation: "get", "update", "delete", or "test"
configvalueNew config dict (for update, e.g., {"webhook_url": "..."})
destination_idstringDestination UUID (from list_destinations)
is_activevalueEnable/disable (for update)
namevalueNew display name (for update)
manage_rule_destinationsManage which destinations an alert rule routes to.4 params
Manage which destinations an alert rule routes to.
Parameters* required
actionstringOperation:
"list" - list destinations linked to this rule
"link" - link destinations to the rule (requires destination_ids)
"unlink" - unlink a destination from the rule (requires desti...
destination_idvalueSingle destination UUID to unlink (for unlink action)
destination_idsvalueDestination UUIDs to link (for link action)
rule_idstringAlert rule UUID (from list_alert_rules)
get_freshness_summaryGet freshness monitoring summary with counts of fresh, stale, and unknown tables. For a quick overview use health_summary. For per-table details use check_freshness.
Get freshness monitoring summary with counts of fresh, stale, and unknown tables. For a quick overview use health_summary. For per-table details use check_freshness.
No parameter schema in public metadata yet.
check_freshnessCheck freshness status for all monitored tables in an asset. Shows which tables are fresh, stale, or unknown. Use setup_freshness to add monitoring for new tables.2 params
Check freshness status for all monitored tables in an asset. Shows which tables are fresh, stale, or unknown. Use setup_freshness to add monitoring for new tables.
Parameters* required
asset_idstringAsset UUID (from list_assets)
stale_onlybooleanOnly return stale tables (default False)default: false
setup_freshnessCreate freshness monitoring for one or more tables. Use explore to find table paths, recommend_freshness for suggested intervals.7 params
Create freshness monitoring for one or more tables. Use explore to find table paths, recommend_freshness for suggested intervals.
Parameters* required
asset_idstringAsset UUID (from list_assets)
check_intervalstringHow often to check: "5m", "15m", "30m", "1h", "3h", "6h", "12h", "1d", "1w"default: 1h
expected_interval_hoursvalueHours until stale (required for explicit mode)
freshness_columnvalueColumn to check (auto-detected if not provided)
monitoring_modestring"auto_learn" (recommended, learns thresholds) or "explicit"default: auto_learn
table_pathvalueSingle table path (e.g., "public.orders")
table_pathsvalueMultiple table paths for bulk setup (overrides table_path)
list_freshness_schedulesList freshness monitoring schedules showing check intervals and status. Use setup_freshness to add new schedules.2 params
List freshness monitoring schedules showing check intervals and status. Use setup_freshness to add new schedules.
Parameters* required
asset_idvalueFilter by asset UUID (from list_assets)
limitintegerMaximum results (default 25)default: 25
manage_freshness_scheduleUpdate or delete a freshness monitoring schedule. Use list_freshness_schedules to find schedule IDs.7 params
Update or delete a freshness monitoring schedule. Use list_freshness_schedules to find schedule IDs.
Parameters* required
actionstringOperation: "update" or "delete"
check_intervalvalueNew check interval (for update)
expected_interval_hoursvalueNew staleness threshold (for update)
freshness_columnvalueNew column to check (for update)
is_activevalueEnable/disable schedule (for update)
monitoring_modevalueNew mode: "auto_learn" or "explicit" (for update)
schedule_idstringSchedule UUID (from list_freshness_schedules)
health_summaryStart here for a quick overview of data health. Returns aggregated status across alerts, freshness, schema drift, metrics, and validity. For per-table details, use check_freshness or list_schema_changes.
Start here for a quick overview of data health. Returns aggregated status across alerts, freshness, schema drift, metrics, and validity. For per-table details, use check_freshness or list_schema_changes.
No parameter schema in public metadata yet.
get_todays_briefingGet today's data health briefing with key events and recommendations. Provides a daily summary of alerts fired, freshness issues, schema changes, and suggested actions. Good starting point for a morning check-in.
Get today's data health briefing with key events and recommendations. Provides a daily summary of alerts fired, freshness issues, schema changes, and suggested actions. Good starting point for a morning check-in.
No parameter schema in public metadata yet.
ask_questionAsk a natural language question about your data. Uses AI to analyze your schema, metadata, and monitoring data to answer.4 params
Ask a natural language question about your data. Uses AI to analyze your schema, metadata, and monitoring data to answer.
Parameters* required
asset_idvalueAsset UUID to scope the question (from list_assets). Omit for all assets.
include_lineagebooleanInclude lineage info in context (default False)default: false
include_schemabooleanInclude schema info in context (default True)default: true
questionstringNatural language question (e.g., "What tables contain customer PII?")
generate_intelligenceGenerate AI analysis for an asset. Analyzes schema, data patterns, and metadata to generate insights. Results are cached. Runs as a background job with progress reporting.2 params
Generate AI analysis for an asset. Analyzes schema, data patterns, and metadata to generate insights. Results are cached. Runs as a background job with progress reporting.
Parameters* required
asset_idstringAsset UUID (from list_assets)
force_refreshbooleanForce regeneration even if cached (default False)default: false
get_metrics_summaryGet metrics monitoring summary for an asset. Shows total metrics, active count, anomaly count, and per-type breakdown.1 params
Get metrics monitoring summary for an asset. Shows total metrics, active count, anomaly count, and per-type breakdown.
Parameters* required
asset_idstringAsset UUID (from list_assets)
list_metricsList data quality metrics configured for an asset. Shows metric type, table, column, and active status. Use create_metric to add new metrics.2 params
List data quality metrics configured for an asset. Shows metric type, table, column, and active status. Use create_metric to add new metrics.
Parameters* required
asset_idstringAsset UUID (from list_assets)
limitintegerMaximum results (default 25)default: 25
create_metricCreate a data quality metric for a table. Use explore to find table paths and column names.4 params
Create a data quality metric for a table. Use explore to find table paths and column names.
Parameters* required
asset_idstringAsset UUID (from list_assets)
column_namevalueColumn to monitor (required for column-level metrics like
null_rate, mean, etc.)
metric_typestringType of metric: "row_count", "null_rate", "unique_rate",
"min", "max", "mean", "stddev"
table_pathstringFull table path (e.g., "public.orders")
manage_metricManage an existing metric: get details, update, delete, trigger capture, or view snapshots. Use list_metrics to find metric IDs.7 params
Manage an existing metric: get details, update, delete, trigger capture, or view snapshots. Use list_metrics to find metric IDs.
Parameters* required
actionstringOperation:
"get" - get metric details and current value
"update" - update metric settings
"delete" - delete the metric
"capture" - trigger an immediate metric capture
"snapshots...
asset_idstringAsset UUID (from list_assets)
capture_intervalvalueNew capture interval (for update)
is_activevalueEnable/disable metric (for update)
limitintegerMax snapshots to return (for snapshots action, default 100)default: 100
metric_idstringMetric UUID (from list_metrics)
sensitivityvalueAnomaly detection sensitivity 0.0-1.0 (for update)
get_validity_summaryGet validity rules summary for an asset. Shows total rules, active count, failing count, and per-type breakdown.1 params
Get validity rules summary for an asset. Shows total rules, active count, failing count, and per-type breakdown.
Parameters* required
asset_idstringAsset UUID (from list_assets)
list_validity_rulesList data validity rules configured for an asset. Shows rule type, table, column, and active status. Use create_validity_rule to add new rules.2 params
List data validity rules configured for an asset. Shows rule type, table, column, and active status. Use create_validity_rule to add new rules.
Parameters* required
asset_idstringAsset UUID (from list_assets)
limitintegerMaximum results (default 25)default: 25
create_validity_ruleCreate a data validity rule for a specific column. Checks column values against defined constraints. Use explore to find table and column names.7 params
Create a data validity rule for a specific column. Checks column values against defined constraints. Use explore to find table and column names.
Parameters* required
asset_idstringAsset UUID (from list_assets)
column_namestringColumn to validate
namevalueHuman-readable rule name (auto-generated if omitted)
rule_configobjectConfig for the rule type. Examples:
{"pattern": "^[A-Z]"} for regex_match,
{"values": ["a","b"]} for allowed_values,
{"min": 0, "max": 100} for range_bounds
rule_typestringType of check: "regex_match", "allowed_values", "range_bounds",
"format", "length_bounds"
severitystringAlert severity when rule fails: "error" (default), "warning", "critical"default: error
table_pathstringFull table path (e.g., "public.users")
manage_validity_ruleManage an existing validity rule: get details, update, delete, check, or view results. Use list_validity_rules to find rule IDs.8 params
Manage an existing validity rule: get details, update, delete, check, or view results. Use list_validity_rules to find rule IDs.
Parameters* required
actionstringOperation:
"get" - get rule details
"update" - update rule settings
"delete" - delete the rule
"check" - run the validity check now
"results" - view recent check results
asset_idstringAsset UUID (from list_assets)
is_activevalueEnable/disable (for update)
limitintegerMax results to return (for results action, default 25)default: 25
namevalueNew name (for update)
rule_configvalueNew rule config (for update)
rule_idstringValidity rule UUID (from list_validity_rules)
severityvalueNew severity (for update)
recommendGet AI-driven monitoring recommendations for an asset. Analyzes historical patterns, schema, and alert data to suggest monitoring improvements.7 params
Get AI-driven monitoring recommendations for an asset. Analyzes historical patterns, schema, and alert data to suggest monitoring improvements.
Parameters* required
asset_idstringAsset UUID (from list_assets)
daysintegerHistorical window in days (for thresholds, default 30)default: 30
include_monitoredbooleanInclude already-monitored tables (for freshness, default False)default: false
limitintegerMaximum recommendations (default 20)default: 20
min_confidencenumberMinimum confidence threshold 0.0-1.0 (for freshness/metrics, default 0.5)default: 0.5
recommendation_typestringType of recommendation:
"freshness" - suggest tables and thresholds for freshness monitoring
"metrics" - suggest quality metrics based on column analysis
"coverage" - identify unmonitor...
table_pathvalueFilter to specific table (for metrics)
create_referential_checkCreate a referential integrity check between two columns. Detects orphaned foreign key references. Use explore to find table and column names.7 params
Create a referential integrity check between two columns. Detects orphaned foreign key references. Use explore to find table and column names.
Parameters* required
asset_idstringAsset UUID (from list_assets)
namevalueHuman-readable name (auto-generated if omitted)
severitystringAlert severity: "warning" (default), "error", "critical"default: warning
source_columnstringForeign key column (e.g., "customer_id")
source_tablestringTable containing the foreign key (e.g., "public.orders")
target_columnstringReferenced column (e.g., "id")
target_tablestringReferenced table (e.g., "public.customers")
manage_referentialManage referential integrity checks: view, update, delete, execute, or get results. Use create_referential_check to create new checks.7 params
Manage referential integrity checks: view, update, delete, execute, or get results. Use create_referential_check to create new checks.
Parameters* required
actionstringOperation to perform:
"summary" - get overview of all checks for the asset
"list" - list all checks for the asset
"get" - get details of a specific check (requires check_id)
"update...
asset_idstringAsset UUID (from list_assets)
check_idvalueCheck UUID (required for get/update/delete/execute/results)
is_activevalueEnable/disable (for update action)
limitintegerMax results (for list/results actions, default 25)default: 25
namevalueNew name (for update action)
severityvalueNew severity (for update action)
get_schema_summaryGet schema drift summary with total changes, unacknowledged count, and severity breakdown. For individual changes use list_schema_changes.
Get schema drift summary with total changes, unacknowledged count, and severity breakdown. For individual changes use list_schema_changes.
No parameter schema in public metadata yet.
list_schema_changesList recent schema changes showing change type, severity, and acknowledgment status. For summary counts use get_schema_summary. To enable monitoring use enable_schema_monitoring.4 params
List recent schema changes showing change type, severity, and acknowledgment status. For summary counts use get_schema_summary. To enable monitoring use enable_schema_monitoring.
Parameters* required
asset_idvalueFilter by asset UUID (from list_assets)
limitintegerMaximum results (default 25)default: 25
severityvalueFilter by severity: "critical", "warning", "info"
unacknowledged_onlybooleanOnly return unacknowledged changes (default false)default: false
create_schema_baselineCapture current schema as baseline for drift detection. Required before enable_schema_monitoring can detect changes.2 params
Capture current schema as baseline for drift detection. Required before enable_schema_monitoring can detect changes.
Parameters* required
asset_idstringAsset UUID (from list_assets)
descriptionvalueOptional description for the baseline
enable_schema_monitoringEnable schema drift monitoring for an asset. Detects column additions, removals, type changes, and other schema modifications. Use list_schema_changes to view detected changes.3 params
Enable schema drift monitoring for an asset. Detects column additions, removals, type changes, and other schema modifications. Use list_schema_changes to view detected changes.
Parameters* required
asset_idstringAsset UUID (from list_assets)
auto_create_baselinebooleanCreate baseline if none exists (default True)default: true
schedule_typestringHow often to check for drift: "5m", "1h", "6h", "1d", "1w"default: 1d
disable_schema_monitoringDisable schema drift monitoring for an asset. Keeps baseline for re-enabling.1 params
Disable schema drift monitoring for an asset. Keeps baseline for re-enabling.
Parameters* required
asset_idstringAsset UUID (from list_assets)
get_schema_monitoringGet schema monitoring configuration for an asset. Shows whether monitoring is enabled, schedule type, baseline info, and last check timestamp.1 params
Get schema monitoring configuration for an asset. Shows whether monitoring is enabled, schedule type, baseline info, and last check timestamp.
Parameters* required
asset_idstringAsset UUID (from list_assets)
dry_run_schemaPreview schema drift detection without persisting. Compares current schema against baseline to show what changes would be detected. Use this to test before enabling monitoring.2 params
Preview schema drift detection without persisting. Compares current schema against baseline to show what changes would be detected. Use this to test before enabling monitoring.
Parameters* required
asset_idstringAsset UUID (from list_assets)
schedule_typestringSchedule for alert estimation: "1h", "1d", "1w"default: 1d
AnomalyArmor Agents
AI skills and MCP server for AnomalyArmor data observability. Monitor data quality, detect schema drift, and manage alerts directly from Claude Code, Cursor, or any MCP-compatible AI tool.
Version: 0.6.0 | Tools: 52 consolidated MCP tools | Skills: 14 slash commands
Quick Start
Option 1: Claude Code Plugin (Recommended)
# Install the plugin
claude plugin marketplace add anomalyarmor/agents
claude plugin install armor@anomalyarmor
# Or via skills.sh
npx skills add anomalyarmor/agents
Then use skills like:
/armor:status- Check data health/armor:alerts- View and manage alerts/armor:recommend- Get AI monitoring recommendations/armor:ask- Ask questions about your data
Option 2: MCP Server
Add to your MCP configuration (Claude Code, Cursor, etc.):
{
"mcpServers": {
"armor": {
"command": "uvx",
"args": ["armor-mcp"]
}
}
}
Prerequisites
- AnomalyArmor Account: Sign up at anomalyarmor.ai
- API Key: Generate at Settings > API Keys
- Configure: Set
ARMOR_API_KEYenv var or create~/.armor/config.yaml:
api_key: aa_live_your_key_here
Available Skills
| Skill | Description | Example |
|---|---|---|
/armor:start | Guided onboarding for new users | "Help me get set up" |
/armor:status | Health summary across all assets | "Is my data healthy?" |
/armor:connect | Connect a new data source | "Connect my Snowflake warehouse" |
/armor:monitor | Set up freshness and schema monitoring | "Monitor freshness for orders table" |
/armor:alerts | Query and manage alerts | "What alerts fired yesterday?" |
/armor:ask | Natural language Q&A about your data | "What tables contain customer data?" |
/armor:analyze | Trigger AI analysis | "Analyze the finance schema" |
/armor:quality | Data quality metrics and validity rules | "Add null check for customer_id" |
/armor:coverage | Monitoring coverage analysis | "What tables have no monitoring?" |
/armor:recommend | AI-driven monitoring recommendations | "What should I monitor?" |
/armor:tags | Asset tagging and classification | "Tag this table as PII" |
/armor:investigate | Root cause analysis | "Why is this table stale?" |
/armor:lineage | Data lineage exploration | "What depends on this table?" |
/armor:profile | Table profiling and stats | "Profile the orders table" |
MCP Tools (29 consolidated)
Tools follow a consolidated pattern: one tool per domain handles multiple operations via an action parameter, reducing context window usage while maintaining full functionality.
Health and Briefing
health_summary()- Overall data health across all assetsget_todays_briefing()- Daily AI briefing with alerts, freshness, and coverage gaps
Alerts (5 tools)
get_alerts_summary()- Alert counts by severity and statuslist_alerts(status, severity, asset_id, from_date, to_date)- Query alerts with filterslist_inbox_alerts(status, limit)- Unresolved alerts inboxupdate_alert(alert_id, action, ...)- Acknowledge, resolve, snooze, or comment on alertsget_alert_trends(period)- Alert trends over timeget_alert_history(alert_id)- Full history for a specific alert
Alert Rules (3 tools)
list_alert_rules(asset_id, is_active)- List configured rulescreate_alert_rule(asset_id, rule_type, ...)- Create new alert rulemanage_alert_rule(rule_id, action, ...)- Update, delete, enable/disable, or duplicate rules
Assets (3 tools)
list_assets(source, asset_type, search)- List monitored assetscreate_asset(name, source_type, connection_config)- Create data sourcemanage_asset(asset_id, action, ...)- Update, delete, test connection, or trigger discoverytrigger_asset_discovery(asset_id)- Start schema discovery
Freshness (4 tools)
get_freshness_summary()- Freshness overview across all assetscheck_freshness(asset_id, table_path)- Check specific table freshnesssetup_freshness(asset_id, table_path, check_interval, ...)- Create freshness schedulelist_freshness_schedules(asset_id)- List configured schedulesmanage_freshness_schedule(schedule_id, action, ...)- Update, delete, pause/resume schedules
Schema Drift (5 tools)
get_schema_summary()- Schema drift overviewlist_schema_changes(asset_id, severity, from_date, to_date)- List detected changescreate_schema_baseline(asset_id, description)- Create baselineenable_schema_monitoring(asset_id, schedule_type, notify_on)- Enable monitoringdisable_schema_monitoring(asset_id)- Disable monitoringget_schema_monitoring(asset_id)- View current monitoring configdry_run_schema(asset_id, schedule_type)- Test schema monitoring before enabling
Data Quality (4 tools)
get_metrics_summary(asset_id)/list_metrics(asset_id)- View metricscreate_metric(asset_id, metric_type, table_path, ...)- Create row count, null rate, or custom metricmanage_metric(metric_id, action, ...)- Update, delete, capture, or view snapshotsget_validity_summary(asset_id)/list_validity_rules(asset_id)- View validity rulescreate_validity_rule(asset_id, rule_type, table_path, ...)- Create validity rulemanage_validity_rule(rule_id, action, ...)- Update, delete, check, or view results
Referential Integrity (2 tools)
create_referential_check(asset_id, ...)- Create cross-table referential checkmanage_referential(check_id, action, ...)- List, delete, run, or view results
Destinations (4 tools)
list_destinations(destination_type)- List alert destinations (Slack, email, webhook)setup_destination(destination_type, ...)- Create Slack channel, email, or webhook destinationmanage_destination(destination_id, action, ...)- Update, delete, test, enable/disablemanage_rule_destinations(rule_id, action, ...)- Link/unlink destinations to alert rules
Coverage and Recommendations (3 tools)
get_coverage(asset_id)- Coverage tier and score for an assetmanage_coverage(asset_id, action)- Get next steps or apply recommended monitoringrecommend(asset_id, recommendation_type)- AI recommendations for freshness, metrics, coverage, or thresholds
Intelligence (2 tools)
ask_question(asset, question)- Natural language Q&Agenerate_intelligence(asset)- Trigger AI knowledge base generation
Catalog (4 tools)
get_lineage(asset_id, depth, direction)- Data lineage graphjob_status(job_id)- Check async job statuscreate_tag(asset_id, name, object_path, ...)- Create and assign tagslist_tags(asset_id)/apply_tags(asset_id, ...)- List and apply tags
API Keys
get_api_key_info()- View current API key details and permissions
Examples
Check Data Health
User: Is my data healthy?
Your data health status:
- Overall: WARNING
- 3 unresolved alerts (1 critical, 2 warning)
- 2 stale tables (orders, customers)
- 1 unacknowledged schema change
- Coverage: 65% (Tier 2: Protected)
Get AI Recommendations
User: What should I monitor on my Snowflake warehouse?
Based on your table patterns and update frequency:
1. orders (high traffic) - Add freshness check (hourly), row count metric
2. customers (PII) - Enable schema drift monitoring, add null checks
3. payments (financial) - Add freshness + row count + validity rules
Want me to set these up? I can configure all three in one go.
Daily Briefing
User: What happened overnight?
Your daily briefing:
- 2 new alerts: orders table stale (6h), schema change in users
- Coverage improved: finance schema now at Tier 3 (Verified)
- Recommendation: 4 tables still have no monitoring. Run /armor:recommend.
Root Cause Analysis
User: Why is the orders table stale?
Investigation results:
- Last update: 6 hours ago (expected: hourly)
- Upstream dependency: raw_orders was last updated 8 hours ago
- Likely cause: upstream ETL job failed or delayed
- Impact: 3 downstream dashboards affected
Troubleshooting
Authentication Failed
Error: No API key configured
Solution: Set ARMOR_API_KEY environment variable or create ~/.armor/config.yaml
MCP Server Not Found
Error: MCP server 'armor' not found
Solution:
- Restart your AI tool after config changes
- Verify uvx is installed:
uvx --version - Check MCP config syntax
Skills Not Loading
Solution:
- Verify plugin installed:
claude plugin list - Check skills directory exists
- Restart Claude Code
Development
See AGENTS.md for development guidelines.
Support
- Issues: GitHub Issues
- Docs: docs.anomalyarmor.ai
- Email: support@anomalyarmor.ai
License
MIT License - see LICENSE
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Configuration
ARMOR_API_KEY*secretAnomalyArmor API key (aa_live_*). Generate at https://app.anomalyarmor.ai/settings/api-keys.
Registryactive
Packagearmor-mcp
TransportSTDIO, HTTP
AuthRequired
UpdatedApr 18, 2026
