sqlite-memory-mcp (RMANOV/sqlite-memory-mcp) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 116 tools. No publisher has claimed this listing.
SQLite-backed MCP Memory Server with WAL concurrent safety, FTS5 search, session tracking, task management, and cross-machine bridge sync
Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. 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
RMANOV
Source: Glama · also listed on github_repo_search
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.
create_entitiesCreate new entities in the knowledge graph.
add_observationsAdd new observations to existing entities.
create_relationsCreate relations between entities in the knowledge graph.
delete_entitiesDelete entities and their associated observations and relations (CASCADE).
delete_observationsDelete specific observations from entities.
delete_relationsDelete specific relations from the knowledge graph.
read_graphRead the full knowledge graph with pagination.
search_nodesSearch the knowledge graph using hybrid BM25 + semantic search.
open_nodesOpen specific entities and retrieve their inter-relations.
_compatfunctionbridge_pushRun the canonical locked bridge worker and return the MCP result envelope.
bridge_pullRun the canonical locked bridge worker in import-only mode.
bridge_statusShow bridge sync status — local shared entities vs repo contents.
bridge_doctorInspect runtime parity and the active bridge surface contract.
assign_taskAssign a task or note to a GitHub user for collaboration.
review_shared_tasksReview shared tasks pending approval from other users.
process_recurring_tasksProcess recurring tasks: recreate done recurring tasks if schedule matches today.
manage_collaboratorsManage the collaborator address book for P2P knowledge sharing.
share_knowledgeQueue entities for sharing with collaborators on next bridge_push.
review_shared_knowledgeReview incoming shared knowledge from collaborators.
request_publishRequest to publish entities/tasks as public knowledge.
cancel_publishCancel a pending publish request. Reverts pending_public → private.
search_public_knowledgeSearch published public knowledge using FTS5 BM25-ranked search.
rate_public_knowledgeRate a public knowledge entity's quality (Claude-only structured analysis).
get_knowledge_ratingsGet computed TruthScore and dimensional breakdown for a public entity.
update_verificationUpdate verification fields on your existing rating for a public entity.
_toollink_task_entityLink a task to a knowledge graph entity.
unlink_task_entityRemove a task↔entity link.
get_task_linksGet all knowledge graph entities linked to a task.
get_entity_tasksGet all tasks linked to a knowledge graph entity.
suggest_task_linksSuggest knowledge graph entities that may be related to a task.
find_entity_overlapsFind overlapping/duplicate entities in the knowledge graph.
merge_entitiesMerge one entity into another, combining observations, relations, and task links.
assess_contextClassify context chunk, detect signals, determine state transition.
queue_clarificationGenerate AWAITING_HUMAN block with focused clarification questions.
record_human_answerIngest human answer, update chunk state, resolve open questions.
extract_candidate_claimsExtract typed (subject, predicate, object, scope) claims from a context chunk.
promote_candidateGovernance gate: promote candidate claim to canonical fact.
build_context_packCompile role-specific context pack with token budget optimization.
explain_impactShow downstream impact of a knowledge change via bounded BFS.
audit_memoryRun the persistent self-repair audit loop over facts, packs, provenance, and sync drift.
replay_memoryReplay append-only memory events for a task/fact/chunk or for the whole ledger.
govern_factApply truth-maintenance to a fact: supersede, contradict, invalidate, or revalidate.
list_memory_issuesList persisted memory audit issues after the latest audit run.
enrich_contextCompatibility wrapper: enriches context at different depth levels.
reflect_auditFind consolidation candidates without mutating. Read-only, no LLM, no API.
reflect_startCreate a Phase 1 run and execute the Extract stage synchronously.
reflect_statusReturn run state, inputs, and decision counts for a given run_id.
reflect_historyPaginated newest-first list of reflection runs (Dreams list parity).
reflect_cancelCancel a pending or running run. Rejects terminal states.
reflect_archiveArchive a terminal run. Rejects pending/running. Idempotent.
reflect_decideRecord human accept/reject/defer decision on a candidate.
reflect_applyApply accepted candidates from a completed run.
reflect_reviewPaginated, filterable list of candidates for human review.
reflect_discardHard-delete a terminal run; cascades to inputs/candidates/snapshots.
export_to_gbrainExport entities/observations/relations to GBrain-compatible Markdown.
import_from_gbrainImport a GBrain-compatible Markdown brain repo into the local KG.
debate_initBootstrap a new debate. Idempotent on (topic_id, roles).
debate_postAppend a message to a debate. Validates kind-specific semantics BEFORE the INSERT (atomic — failed validation leaves no row).
debate_readRead messages with compound (ts, msg_id) cursor.
debate_searchSearch a debate topic's messages by substring of ``body``.
debate_context_searchRank relevant debate context without dumping full message bodies.
debate_protocol_stateReturn the debate/v1 micro-state for one topic.
debate_judge_prepareCreate immutable AB and BA judge projections for adjudication.
debate_judge_verdictRecord one immutable judge verdict; AB/BA agreement stops the debate.
debate_protocol_maintainRun deterministic phase-timeout and missing-role recovery sweeps.
debate_stateTransition debate to a new state. Validates VALID_TRANSITIONS. RESOLVED requires all open Qs to have a matching A reply (or A body starting `[DEFERRED:` to count as resolution-equivalent).
debate_escalateForce-write an H-priority PING tagged for target_role (default HUMAN).
debate_compactWrite a COMPACTION snapshot. Body must contain OBSERVE / ORIENT / DECIDE / ACT sections (regex-validated pre-INSERT). since_ts and until_ts are optional ISO 8601 UTC bounds for the snapshotted range.
debate_advance_watermarkAdvance (topic_id, role) cursor to a specific msg_id.
debate_post_with_recipientsPost an addressed message: debate_messages + debate_message_recipients in a single atomic transaction.
debate_signal_checkReturn messages addressed to (role OR session_id) past the caller's compound (ts, msg_id) cursor.
debate_signal_advanceAdvance the (session_id, role, topic_id) compound cursor to a specific msg_id.
debate_binding_listList role/session bindings and cursor state for a debate topic.
debate_bind_roleBind, diagnose, or retire a role/session binding.
debate_add_roleAdd a NEW role to an existing topic after debate_init (flexible roster).
debate_rotate_bindingAtomically rotate a role owner with explicit cursor mode.
debate_close_topicClose a topic through the authoritative debate_state transition path.
debate_wake_dry_runResolve wake targets and audit them without waking or posting.
debate_worker_claimIdempotently allocate/reuse a derived -W<n> worker for one trigger.
debate_worker_reapRetire old completed worker claims and leave audit evidence.
debate_message_claim_reclaimReclaim stale active standing=false DECISION claims with audit rows.
debate_worker_no_actionComplete a wake worker claim without posting when no work remains.
debate_worker_recover_staleRetire dead worker claims without hiding their parent trigger.
debate_set_topic_prioritySet a CONDUCTOR-owned P0..P7 priority lane in topic metadata.
debate_work_queueList open debate topics in deterministic CONDUCTOR priority order.
create_task_or_noteCreate a task or note (n8n origin-tagged). Returns the UUID.
update_taskUpdate an existing task/note by id (n8n origin-tagged).
toolsession_saveSave or update a session snapshot.
session_recallRecall the last N sessions, ordered by most recent first.
search_by_projectSearch the knowledge graph scoped to a specific project.
knowledge_healthRun observation health scan and return findings.
resume_contextSession continuity: handoff pack + unresolved items + changed facts.
upsert_note_by_title_projectCreate or update a note by exact normalized title + project.
query_tasksQuery tasks with optional filters. Returns markdown table.
find_by_titleFind tasks, notes, or entities by partial title or remembered phrase.
task_digestGenerate a formatted task digest for session start.
archive_done_tasksArchive completed tasks older than N days.
11 further tools are not listed here. The complete surface is in the source.
GITHUB_USERSQLITE_MEMORY_N8N_PORTBRIDGE_GH_REPOCLOUDFLARE_API_TOKENMACHINE_IDSQLITE_MEMORY_LOG_DIRSQLITE_MEMORY_DASH_TOPIC_IDDEBATE_WORKER_MAX_REQUEUESDEBATE_PUMP_TASK_NAMEDEBATE_PUMP_PROGRESS_STALL_SECONDSDEBATE_PUMP_WORKER_LEASE_GRACE_SECONDSSQLITE_MEMORY_DBThe environment variable controls where the database is stored. If omitted, it defaults to ~/.claude/memory/memory.db. BRIDGE_REPO is only needed for bridge/collab flows.DEBATE_WAKE_EVENT_NAMENOTION_TOKENCODEX_DEBATE_CODEX_BINSQLITE_MEMORY_TRAY_AUTO_SYNCSQLITE_MEMORY_TRAY_BACKGROUND_AUDITWAYLAND_DISPLAYDISPLAYDEBATE_REPODEBATE_PUMP_LOG_MAX_BYTESDEBATE_PUMP_LOG_KEEPDEBATE_WAKE_ACTION_NAMEDEBATE_RESOURCE_BUDGETDEBATE_PUMP_WINDOWS_SWEEP_SECONDSDEBATE_PUMP_WINDOWS_MAX_SWEEP_SECONDSDEBATE_PUMP_TOPICSDEBATE_PUMP_MAX_WORKERS_PER_SCANDEBATE_PUMP_MAX_CONCURRENT_WORKERSDEBATE_MESSAGE_CLAIM_RECLAIM_SECONDSDEBATE_MESSAGE_CLAIM_RECLAIM_INTERVALDEBATE_MESSAGE_CLAIM_RECLAIM_MIN_AGE_SECONDSDEBATE_WORKER_CLAIM_RECOVERY_SECONDSDEBATE_WORKER_CLAIM_RECOVERY_INTERVALDEBATE_WORKER_CLAIM_RECOVERY_MIN_AGE_SECONDSDEBATE_WAKE_MCP_PREFIXDEBATE_WAKE_BUDGETDEBATE_RESOURCE_HYSTERESISDEBATE_WAKE_LOG_MAX_BYTESDEBATE_WAKE_LOG_KEEPDEBATE_WAKE_MCP_PYTHONDEBATE_WAKE_MCP_SERVERDEBATE_WAKE_CLAUDE_MODELDEBATE_WAKE_CLAUDE_EFFORTDEBATE_WAKE_CODEX_EFFORTDEBATE_WAKE_SPAWN_ACTION_NAMEDEBATE_WAKE_AGENT_LOG_KEEPDEBATE_WAKE_ACTIONTool 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
116/116 tools missing one or more hints — create_entities (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); add_observations (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); create_relations (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +113 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.
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/rmanov/sqlite-memory-mcp)?variant=verified to the badge 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