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.

C
Emerging
74/100

sqlite-memory-mcp

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

Code Verified⚡ Live Monitored: not connected

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

Is this your MCP?

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.

// key findings
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 2 credentials: CLOUDFLARE_API_TOKEN, NOTION_TOKEN
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes111 tools

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_entities

Create new entities in the knowledge graph.

add_observations

Add new observations to existing entities.

create_relations

Create relations between entities in the knowledge graph.

delete_entities

Delete entities and their associated observations and relations (CASCADE).

delete_observations

Delete specific observations from entities.

delete_relations

Delete specific relations from the knowledge graph.

read_graph

Read the full knowledge graph with pagination.

search_nodes

Search the knowledge graph using hybrid BM25 + semantic search.

open_nodes

Open specific entities and retrieve their inter-relations.

_compatfunction
bridge_push

Run the canonical locked bridge worker and return the MCP result envelope.

bridge_pull

Run the canonical locked bridge worker in import-only mode.

bridge_status

Show bridge sync status — local shared entities vs repo contents.

bridge_doctor

Inspect runtime parity and the active bridge surface contract.

assign_task

Assign a task or note to a GitHub user for collaboration.

review_shared_tasks

Review shared tasks pending approval from other users.

process_recurring_tasks

Process recurring tasks: recreate done recurring tasks if schedule matches today.

manage_collaborators

Manage the collaborator address book for P2P knowledge sharing.

share_knowledge

Queue entities for sharing with collaborators on next bridge_push.

review_shared_knowledge

Review incoming shared knowledge from collaborators.

request_publish

Request to publish entities/tasks as public knowledge.

cancel_publish

Cancel a pending publish request. Reverts pending_public → private.

search_public_knowledge

Search published public knowledge using FTS5 BM25-ranked search.

rate_public_knowledge

Rate a public knowledge entity's quality (Claude-only structured analysis).

get_knowledge_ratings

Get computed TruthScore and dimensional breakdown for a public entity.

update_verification

Update verification fields on your existing rating for a public entity.

_tool
link_task_entity

Link a task to a knowledge graph entity.

unlink_task_entity

Remove a task↔entity link.

get_task_links

Get all knowledge graph entities linked to a task.

get_entity_tasks

Get all tasks linked to a knowledge graph entity.

suggest_task_links

Suggest knowledge graph entities that may be related to a task.

find_entity_overlaps

Find overlapping/duplicate entities in the knowledge graph.

merge_entities

Merge one entity into another, combining observations, relations, and task links.

assess_context

Classify context chunk, detect signals, determine state transition.

queue_clarification

Generate AWAITING_HUMAN block with focused clarification questions.

record_human_answer

Ingest human answer, update chunk state, resolve open questions.

extract_candidate_claims

Extract typed (subject, predicate, object, scope) claims from a context chunk.

promote_candidate

Governance gate: promote candidate claim to canonical fact.

build_context_pack

Compile role-specific context pack with token budget optimization.

explain_impact

Show downstream impact of a knowledge change via bounded BFS.

audit_memory

Run the persistent self-repair audit loop over facts, packs, provenance, and sync drift.

replay_memory

Replay append-only memory events for a task/fact/chunk or for the whole ledger.

govern_fact

Apply truth-maintenance to a fact: supersede, contradict, invalidate, or revalidate.

list_memory_issues

List persisted memory audit issues after the latest audit run.

enrich_context

Compatibility wrapper: enriches context at different depth levels.

reflect_audit

Find consolidation candidates without mutating. Read-only, no LLM, no API.

reflect_start

Create a Phase 1 run and execute the Extract stage synchronously.

reflect_status

Return run state, inputs, and decision counts for a given run_id.

reflect_history

Paginated newest-first list of reflection runs (Dreams list parity).

reflect_cancel

Cancel a pending or running run. Rejects terminal states.

reflect_archive

Archive a terminal run. Rejects pending/running. Idempotent.

reflect_decide

Record human accept/reject/defer decision on a candidate.

reflect_apply

Apply accepted candidates from a completed run.

reflect_review

Paginated, filterable list of candidates for human review.

reflect_discard

Hard-delete a terminal run; cascades to inputs/candidates/snapshots.

export_to_gbrain

Export entities/observations/relations to GBrain-compatible Markdown.

import_from_gbrain

Import a GBrain-compatible Markdown brain repo into the local KG.

debate_init

Bootstrap a new debate. Idempotent on (topic_id, roles).

debate_post

Append a message to a debate. Validates kind-specific semantics BEFORE the INSERT (atomic — failed validation leaves no row).

debate_read

Read messages with compound (ts, msg_id) cursor.

debate_search

Search a debate topic's messages by substring of ``body``.

debate_context_search

Rank relevant debate context without dumping full message bodies.

debate_protocol_state

Return the debate/v1 micro-state for one topic.

debate_judge_prepare

Create immutable AB and BA judge projections for adjudication.

debate_judge_verdict

Record one immutable judge verdict; AB/BA agreement stops the debate.

debate_protocol_maintain

Run deterministic phase-timeout and missing-role recovery sweeps.

debate_state

Transition 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_escalate

Force-write an H-priority PING tagged for target_role (default HUMAN).

debate_compact

Write 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_watermark

Advance (topic_id, role) cursor to a specific msg_id.

debate_post_with_recipients

Post an addressed message: debate_messages + debate_message_recipients in a single atomic transaction.

debate_signal_check

Return messages addressed to (role OR session_id) past the caller's compound (ts, msg_id) cursor.

debate_signal_advance

Advance the (session_id, role, topic_id) compound cursor to a specific msg_id.

debate_binding_list

List role/session bindings and cursor state for a debate topic.

debate_bind_role

Bind, diagnose, or retire a role/session binding.

debate_add_role

Add a NEW role to an existing topic after debate_init (flexible roster).

debate_rotate_binding

Atomically rotate a role owner with explicit cursor mode.

debate_close_topic

Close a topic through the authoritative debate_state transition path.

debate_wake_dry_run

Resolve wake targets and audit them without waking or posting.

debate_worker_claim

Idempotently allocate/reuse a derived -W<n> worker for one trigger.

debate_worker_reap

Retire old completed worker claims and leave audit evidence.

debate_message_claim_reclaim

Reclaim stale active standing=false DECISION claims with audit rows.

debate_worker_no_action

Complete a wake worker claim without posting when no work remains.

debate_worker_recover_stale

Retire dead worker claims without hiding their parent trigger.

debate_set_topic_priority

Set a CONDUCTOR-owned P0..P7 priority lane in topic metadata.

debate_work_queue

List open debate topics in deterministic CONDUCTOR priority order.

create_task_or_note

Create a task or note (n8n origin-tagged). Returns the UUID.

update_task

Update an existing task/note by id (n8n origin-tagged).

tool
session_save

Save or update a session snapshot.

session_recall

Recall the last N sessions, ordered by most recent first.

search_by_project

Search the knowledge graph scoped to a specific project.

knowledge_health

Run observation health scan and return findings.

resume_context

Session continuity: handoff pack + unresolved items + changed facts.

upsert_note_by_title_project

Create or update a note by exact normalized title + project.

query_tasks

Query tasks with optional filters. Returns markdown table.

find_by_title

Find tasks, notes, or entities by partial title or remembered phrase.

task_digest

Generate a formatted task digest for session start.

archive_done_tasks

Archive completed tasks older than N days.

11 further tools are not listed here. The complete surface is in the source.

// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configGITHUB_USER
configSQLITE_MEMORY_N8N_PORT
configBRIDGE_GH_REPO
🔐 secretCLOUDFLARE_API_TOKEN
configMACHINE_ID
configSQLITE_MEMORY_LOG_DIR
configSQLITE_MEMORY_DASH_TOPIC_ID
configDEBATE_WORKER_MAX_REQUEUES
configDEBATE_PUMP_TASK_NAME
configDEBATE_PUMP_PROGRESS_STALL_SECONDS
configDEBATE_PUMP_WORKER_LEASE_GRACE_SECONDS
configSQLITE_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.
configDEBATE_WAKE_EVENT_NAME
🔐 secretNOTION_TOKEN
configCODEX_DEBATE_CODEX_BIN
configSQLITE_MEMORY_TRAY_AUTO_SYNC
configSQLITE_MEMORY_TRAY_BACKGROUND_AUDIT
configWAYLAND_DISPLAY
configDISPLAY
configDEBATE_REPO
configDEBATE_PUMP_LOG_MAX_BYTES
configDEBATE_PUMP_LOG_KEEP
configDEBATE_WAKE_ACTION_NAME
configDEBATE_RESOURCE_BUDGET
configDEBATE_PUMP_WINDOWS_SWEEP_SECONDS
configDEBATE_PUMP_WINDOWS_MAX_SWEEP_SECONDS
configDEBATE_PUMP_TOPICS
configDEBATE_PUMP_MAX_WORKERS_PER_SCAN
configDEBATE_PUMP_MAX_CONCURRENT_WORKERS
configDEBATE_MESSAGE_CLAIM_RECLAIM_SECONDS
configDEBATE_MESSAGE_CLAIM_RECLAIM_INTERVAL
configDEBATE_MESSAGE_CLAIM_RECLAIM_MIN_AGE_SECONDS
configDEBATE_WORKER_CLAIM_RECOVERY_SECONDS
configDEBATE_WORKER_CLAIM_RECOVERY_INTERVAL
configDEBATE_WORKER_CLAIM_RECOVERY_MIN_AGE_SECONDS
configDEBATE_WAKE_MCP_PREFIX
configDEBATE_WAKE_BUDGET
configDEBATE_RESOURCE_HYSTERESIS
configDEBATE_WAKE_LOG_MAX_BYTES
configDEBATE_WAKE_LOG_KEEP
configDEBATE_WAKE_MCP_PYTHON
configDEBATE_WAKE_MCP_SERVER
configDEBATE_WAKE_CLAUDE_MODEL
configDEBATE_WAKE_CLAUDE_EFFORT
configDEBATE_WAKE_CODEX_EFFORT
configDEBATE_WAKE_SPAWN_ACTION_NAME
configDEBATE_WAKE_AGENT_LOG_KEEP
configDEBATE_WAKE_ACTION
// quality suggestions

Tool 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.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 2 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/rmanov/sqlite-memory-mcp)](https://m8ven.ai/mcp/rmanov/sqlite-memory-mcp)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 7ae27380774cce5d456b78c8e9dbb7e62c30151e
code hash: cf238fe8fce3a8ee68380ed82f54cf1bd12bb7cf77a3110568c2925d2f301186
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

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
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client