Atlas / MCP servers / betterdb-inc / BetterDB Monitor

BetterDB MonitorBLOCK

Name: BetterDB Monitor
Author: betterdb-inc

mcp/betterdb-inc/betterdb-monitor

MCP server by betterdb-inc · dragonfly · mcp · mcp server · Audited 2026-09-24

⚑ Report / re-scan Source ↗

Real-time monitoring, slowlog analysis, and audit trails for Valkey and Redis

Verdict

BLOCK

Grade

Trust score

36 /100

Exposed tools

78 69r · 8w · 1d

Transport

stdio

License

NOASSERTION

Stars

1,301

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://hub.docker.com/r/betterdb/monitor) [](https://hub.docker.com/r/betterdb/monitor/tags) [](https://artifacthub.io/packages/search?repo=betterdb-monitor) [](https://www.npmjs.com/package/@betterdb/monitor) [](https://www.npmjs.com/package/@betterdb/monitor) [](https://github.com/betterdb-inc/monitor/actions/workflows/api-tests.yml) [](LICENSE) [](https://valkey.io) [](https://redis.io)

The monitoring layer that Valkey deserves.

BetterDB persists what Valkey throws away - slowlogs, command patterns, client activity, anomaly signals - so you can debug what happened at 3am, not just what's happening now. Built for Valkey 8.x with native support for COMMANDLOG, CLUSTER SLOT-STATS, and per-thread I/O metrics. Redis 6+ compatible for everything else.

Website | Docker Hub | npm | Documentation | Blog

BetterDB is built by BetterDB Inc., a public benefit company operating under the OCV Open Charter.

![BetterDB Monitor - Key Analytics with per-type key size distribution h

Read from source at commit cffef10ac693OBSERVED · 2026-09-24

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code (npm)

claude mcp add mcp --env BETTERDB_TOKEN=${BETTERDB_TOKEN} -- npx -y @betterdb/[email protected]

Exposed tools (78)

69 read · 8 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

Tool	Risk	Description
`add_connection`	write	Add a new Valkey/Redis connection to BetterDB. Optionally set it as the active default.
`ai_instance_history`	read	Get the stored metrics time-series for one AI component instance (hits, misses, hit rate, cost saved, evictions, item count, index size, threshold). Use ai_list_instances first to find the instance field identifier. Use this to see trends: hit-rate degradation, growth, threshold drift.
`ai_list_instances`	read
`cache_approve_proposal`	read	Approve a pending proposal. Synchronously applies the change to Valkey and returns the terminal status (applied\|failed). Idempotent: a second call on an already-applied proposal returns the cached result.
`cache_edit_and_approve_proposal`	write	Edit an existing pending proposal and approve it in one step. Provide exactly one edit field matching the proposal type: new_threshold for threshold_adjust, new_ttl_seconds for tool_ttl_adjust. Invalidate proposals are not editable.
`cache_get_proposal`	read	Fetch a single cache proposal by id, including its audit trail.
`cache_health`	read	Detailed health for a single cache. Response branches by type: semantic_cache reports category_breakdown + uncertain_hit_rate; agent_cache reports tool_breakdown.
`cache_list`	read	List all caches (semantic_cache and agent_cache) registered for the active instance, with hit rate and total ops.
`cache_list_pending_proposals`	read	List pending cache proposals for the active instance, newest first. Optionally filter by cache_name.
`cache_propose_invalidate`	read	Propose a cache invalidation for review. Filter shape depends on cache type: semantic_cache requires filter_kind=valkey_search + filter_expression; agent_cache requires filter_kind in (tool\|key_prefix\|session) + filter_value. Warns when estimated_affected exceeds 10000.
`cache_propose_threshold_adjust`	read	Propose a semantic-cache similarity-threshold change for review. Creates a pending proposal that requires human approval before any change is applied. Reasoning must be at least 20 characters.
`cache_propose_tool_ttl_adjust`	read	Propose an agent-cache per-tool TTL change for review. Creates a pending proposal that requires human approval. Reasoning must be at least 20 characters.
`cache_recent_changes`	read	Recent proposals for a single cache (any status), so agents can avoid re-proposing pending or recently-applied changes. Newest first.
`cache_reject_proposal`	read	Reject a pending proposal. Optionally records a reason in the audit trail.
`cache_similarity_distribution`	read	Histogram of recent similarity scores (20 buckets, width 0.1) for a semantic_cache. Errors on agent_cache.
`cache_threshold_recommendation`	read	Threshold-tuning recommendation for a semantic_cache, based on the rolling similarity-score window. Errors with INVALID_CACHE_TYPE on agent_cache.
`cache_tool_effectiveness`	read	Per-tool hit rate, cost saved, and TTL recommendation for an agent_cache. Errors with INVALID_CACHE_TYPE on semantic_cache.
`calculate`	read	Math helper
`capability`	read	Runtime capability key (e.g. canSlowLog, canCommandLog, canLatency)
`correlate_ai_trace`	read
`deliveryId`	read	Delivery ID
`eventName`	read	Name of the latency event
`get_acl_audit`	read	Get persisted ACL audit log entries from storage. Filter by username, reason (auth, command, key, channel), or time range. Use this to investigate why a connection is failing or audit access patterns.
`get_acl_failures`	read	Get ACL/authentication failures from audit log
`get_ai_trace`	read	Get the full span waterfall for one AI trace: every span with timing, parent relationships, and attributes (model, cache hit/miss, similarity scores). Use list_ai_traces to find trace IDs.
`get_anomalies`	read	Get anomaly detection events from persisted storage. BetterDB continuously runs Z-score analysis on memory, hit rate, CPU, and other metrics — this returns the detected anomalies. Use to investigate what triggered an alert or correlate with an incident.
`get_client_activity`	read	Get time-bucketed client activity from persisted snapshots. Shows connection counts, command distribution, and buffer usage over time. Use startTime/endTime to focus on a specific incident window.
`get_client_analytics`	read	Get client connection analytics and trends
`get_client_list`	read	Get list of connected clients grouped by name
`get_clients`	read	Get the active client list with connection details.
`get_cluster_node_stats`	read	Get per-node performance stats: memory usage, ops/sec, connected clients, replication offset, and CPU. Use this to identify hot nodes, lagging replicas, or uneven load distribution.
`get_cluster_nodes`	read	Discover all nodes in the Valkey cluster — role (master/replica), address, health status, and slot ranges. Returns an error message if this instance is not running in cluster mode.
`get_cluster_slowlog`	read	Get the aggregated slowlog across ALL nodes in the cluster. This is the primary tool for finding slow commands in cluster mode — per-node slowlogs are incomplete. Returns an error message if not in cluster mode.
`get_commandlog`	read	Get the most recent entries from COMMANDLOG (Valkey 8+ only, superset of slowlog).
`get_commandlog_history`	read	Get persisted COMMANDLOG entries from storage (Valkey 8+ only). Supports time range filtering to investigate specific incidents. Returns empty with a note if COMMANDLOG is not supported on this instance.
`get_commandlog_patterns`	read	Get analyzed COMMANDLOG patterns from persisted storage (Valkey 8+ only). Like get_slowlog_patterns but includes large-request and large-reply patterns in addition to slow commands.
`get_connected_clients`	read	Get number of connected and blocked clients
`get_forecast`	read	Get a capacity forecast for one metric: current trajectory and projected time until the resource ceiling is hit. Metric kinds: opsPerSec, usedMemory, cpuTotal, memFragmentation. Use for capacity planning (
`get_health`	read
`get_hot_keys`	read
`get_inference_latency`	read
`get_info`	read	Get INFO stats for the active instance. Contains all health data: memory, clients, replication, keyspace, stats (hit rate, ops/sec), and server info. Optionally filter to a section: server\|clients\|memory\|stats\|replication\|keyspace.
`get_key_count`	read	Get total number of keys in the database
`get_largest_keys`	read
`get_latency`	read	Get latency event history for the active instance.
`get_latency_history`	read	Get the full latency history for a named event (e.g.
`get_latency_regressions`	read	Get detected latency regressions (sustained p99 command-latency degradations vs baseline) from persisted storage. Companion to get_anomalies: same event store, pre-filtered to latency regressions. Use when investigating
`get_memory`	read	Get memory diagnostics: MEMORY DOCTOR assessment and MEMORY STATS breakdown.
`get_memory_usage`	read	Get memory usage statistics
`get_server_status`	read	Get current server status: connected clients, memory usage, ops/sec, total keys, uptime
`get_slot_stats`	read	Get per-slot key counts and CPU usage (Valkey 8.0+ only). Use orderBy=
`get_slowlog`	read	Get the most recent slow commands from the slowlog.
`get_slowlog_patterns`	read	Get analyzed slowlog patterns from persisted storage. Groups slow commands by normalized pattern, showing frequency, average duration, and example commands. Survives slowlog buffer rotation — data goes back as far as BetterDB has been running.
`get_vector_indexes`	read	Get health details for every vector search index on the instance: document count, memory usage, indexing failures, and percent indexed. Requires the Search module (valkey-search / RediSearch) on the connection — errors clearly if absent. Use to diagnose incomplete indexing or index memory growth.
`get_weather`	read	Get current weather for a city
`id`	write	Connection ID to set as default
`list_ai_traces`	read	List recent AI application traces ingested via OpenTelemetry (LLM calls, cache lookups, memory recalls, retrieval spans). Not tied to a Valkey instance — traces come from instrumented AI apps. Use get_ai_trace for a full span waterfall and correlate_ai_trace to join a trace with live Valkey state.
`list_instances`	read	List all Valkey/Redis instances registered in BetterDB. Shows connection status and capabilities.
`memory_approve_forget`	read	Approve a pending forget proposal, applying the deletion against the live store.
`memory_forget`	read	Propose forgetting memories (by id, or by scope/tags). Creates a pending proposal that a human must approve before anything is deleted.
`memory_get`	read	Fetch a single memory by ID from a store.
`memory_list`	read	List memories in a store, newest first, with optional scope and tag filters.
`memory_list_pending_forgets`	read	List pending forget proposals awaiting approval on an instance.
`memory_recall`	read	Recall memories from a store by a precomputed query vector (the caller supplies the embedding).
`memory_reject_forget`	read	Reject a pending forget proposal without deleting anything.
`memory_stats`	read	Get item count, eviction count, and live config for a memory store.
`memory_stores`	read	List agent-memory stores discovered on an instance (name, capabilities, stats key).
`nodeId`	read	Node ID
`parameter`	read	Configuration parameter name
`remove_connection`	destructive	Remove a connection from BetterDB.
`run_latency_diagnosis`	write	Run latency diagnostic analysis
`run_memory_diagnosis`	write	Run memory diagnostic analysis
`search`	read	Search web
`select_instance`	read	Select which instance subsequent tool calls operate on.
`set_default_connection`	write	Set a connection as the active default for BetterDB.
`start_monitor`	write	Start the BetterDB monitor as a persistent background process. If already running, returns the existing URL. The monitor persists across MCP sessions and must be stopped explicitly with stop_monitor.
`stop_monitor`	write	Stop a persistent BetterDB monitor process that was previously started with start_monitor or --autostart --persist.
`test_connection`	read	Test a Valkey/Redis connection without persisting it. Use before add_connection to validate credentials.

Trust audit

BLOCKgrade F · trust 36/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

Layer	What it checks	Result
L0	Provenance & inventory	FAIL
L1	Static analysis of the code	FAIL
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	WARN
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: declared (11 observation(s))
Network: declared (8 observation(s))
Shell: declared (5 observation(s))
Dependencies: not all pinned
Secrets in source: found

Findings (25)

CRITICALHard-coded secrets · secret.private_key · CWE-798, CWE-321

proprietary/entitlement/.env.example:22

LICENSE_SIGNING_PRIVATE_KEY="-----BEGIN PRIVATE KEY-----\n...\n-----END PRIVATE KEY-----"

CRITICALHard-coded secrets · secret.private_key · CWE-798, CWE-321

proprietary/entitlement/.env.example:29

BROKER_SIGNING_PRIVATE_KEY="-----BEGIN PRIVATE KEY-----\n...\n-----END PRIVATE KEY-----"

HIGHInventory / provenance · inv.suspicious_name · CWE-1104

apps/api/src/webhooks/webhook-payload-formatter.ts

webhook-payload-formatter.ts

Why it matters. member named after an attack tool

Fix. remove or justify

HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95

apps/api/src/auth/better-auth-esm.ts:25

return new Function('specifier', 'return import(specifier)') as EsmImport;

Why it matters. evaluates text as code

Fix. remove; use a parser or a dispatch table

HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95

packages/cli/scripts/build.mjs:74

exec(

Why it matters. evaluates text as code

Fix. remove; use a parser or a dispatch table

HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95

packages/cli/scripts/build.mjs:101

exec(`npx esbuild src/index.ts --bundle --platform=node --target=node20 --outfile=dist/index.js --external:@inquirer/prompts --external:commander --external:picocolors --define:__CLI_VERSION__='"${cli

Why it matters. evaluates text as code

Fix. remove; use a parser or a dispatch table

HIGHFilesystem / path · fs.credential_store · CWE-22, CWE-59

apps/web/src/components/ConnectionSelector.tsx:722

placeholder="id_ed25519"

Why it matters. touches a credential store

MEDIUMInventory / provenance · inv.symlink · CWE-1104

proprietary/node_modules

proprietary/node_modules

Why it matters. link not followed