Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
sandst1
Source: github_topic
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
rememberStore an experience or observation in memory (fast, no LLM calls).
recallRetrieve relevant memories for a query.
applyApply a batch changeset to memory. All operations execute in a single transaction (all-or-nothing). Returns per-operation results including new IDs and any collisions. Input format (compact line format, one op per line): remember as=f1 t=fact e=concept:caching "Cache TTL is 600 seconds" supersede ol…
snapshotRead a snapshot of memory state as JSON. Combines one or more scopes into a single JSON document. Use to inspect memory before curating with apply. Scopes (space or comma separated): pending - Unprocessed episodes with their entities conflicts - Open conflicts with full fact details entity:<id> - Ep…
eventsRead the append-only change feed of writes.
list_conflictsList detected memory conflicts (contradictions) awaiting triage.
resolve_conflictResolve a conflict by declaring which fact is correct.
dismiss_conflictDismiss a conflict: both claims are valid (e.g. different contexts).
inspectInspect concepts or episodes in memory. Use this to examine what's stored in memory: - List all concepts (no concept_id) - View a specific concept (with concept_id) - View recent episodes (show_episodes=True) - Filter episodes by date range (show_episodes=True with start_date/end_date) Args: concept…
statsGet memory statistics.
episode_typesList configured episode types.
entitiesList entities (files, functions, people, etc.) in memory.
inspect_entityInspect an entity and its relationships.
update_episodeUpdate an existing episode in memory.
delete_episodeSoft delete an episode from memory.
restore_episodeRestore a previously deleted episode.
update_conceptUpdate an existing concept.
delete_conceptSoft delete a concept from memory.
restore_conceptRestore a previously deleted concept.
list_deletedList soft-deleted episodes and concepts.
LLM_PROVIDEREMBEDDING_PROVIDERLOCAL_EMBEDDING_MODELOPENAI_API_KEYOPENAI_BASE_URLOPENAI_EMBEDDING_MODELOPENAI_EMBEDDING_SIZEAZURE_OPENAI_API_KEYAZURE_OPENAI_API_BASE_URLAZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAMEAZURE_OPENAI_EMBEDDING_SIZEOLLAMA_URLOLLAMA_EMBEDDING_MODELREMIND_DECAY_ENABLEDREMIND_DECAY_INTERVALREMIND_DECAY_RATEREMIND_EPISODE_TYPESREMIND_DB_URLREMIND_HYBRID_KEYWORD_WEIGHTREMIND_RECALL_INITIAL_CANDIDATESREMIND_LEXICAL_ENABLEDREMIND_RRF_KREMIND_RECALL_MAX_CHARSREMIND_RECALL_MIN_SCOREREMIND_RECALL_TIMEOUT_MSREMIND_RERANKING_ENABLEDREMIND_RERANKING_MODELREMIND_CLI_RECALL_WORKER_ENABLEDREMIND_CLI_RECALL_WORKER_IDLE_SECONDSREMIND_FACT_CLUSTER_JACCARD_THRESHOLDREMIND_REMEMBER_NEARBY_KREMIND_LOGGING_ENABLEDREMIND_CLI_OUTPUT_MODETool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
20/20 tools missing one or more hints — remember (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); recall (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); apply (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +17 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Readable source code
1 file are minified or bundled, which is usually build output rather than concealment
Ship unminified, readable source.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/sandst1/remind)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check