total-agent-memory (vbcherepanov/total-agent-memory) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 74 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Emerging
74/100
6 days ago

total-agent-memory

Persistent local memory for AI coding agents — Claude Code, Codex CLI, Cursor, any MCP client. Temporal knowledge graph, procedural memory, AST codebase ingest, cross-project analogy. LongMemEval R@5 95.1%, LoCoMo 0.607, BEAM 1M 0.448. 74 MCP tools, 9 IDEs, 100% local.

→ vbcherepanov/total-agent-memory· listed on github_topic

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

⚡ 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

vbcherepanov

Source: github_topic · also listed on Glama, github_code

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 →

⚡ Connect GitHub for Live Monitored

Install from

GitHubGlamaGitHub

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// 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 6 credentials: ANTHROPIC_API_KEY, GITHUB_TOKEN, OPENAI_API_KEY, MEMORY_LLM_API_KEY, COHERE_API_KEY, MEMORY_EMBED_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// 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.
configEMBEDDING_MODEL
configFASTEMBED_MODEL
configOLLAMA_EMBED_MODEL
configOLLAMA_URLOllama endpoint
configUSE_OLLAMA_EMBED
configDECAY_HALF_LIFE
configARCHIVE_AFTER_DAYS
configPURGE_AFTER_DAYS
configOBSERVATION_RETENTION_DAYS
configUSE_ADVANCED_RAG
configUSE_BINARY_SEARCH
configMEMORY_EPISODE_TIER
configMEMORY_TEMPORAL_INDEX
configMEMORY_TEMPORAL_FILTER
configMEMORY_RELATIONAL_BOOST
configMEMORY_GRAPH_EXPAND
configMEMORY_MODEdeep. Selects hot-path profile. See [Performance tuning](#performance-tuning).
configMEMORY_USE_LLM_IN_HOT_PATHMaster switch for sync LLM stages in save_knowledge / Recall.search. MEMORY_MODE=deep flips this to true.
configMEMORY_ALLOW_OLLAMA_IN_HOT_PATHRe-enables the silent FastEmbed → Ollama fallback ladder when FastEmbed is unavailable.
configMEMORY_RERANK_ENABLEDHonour caller's rerank=true. When false, CrossEncoder rerank is hard-disabled even if a tool call requests it.
configMEMORY_ENRICHMENT_ENABLEDRun the async enrichment worker. Default-ON in balanced / deep.
configMEMORY_LLM_ENABLEDforce — LLM enrichment toggle
configMCP_TRANSPORT
configMCP_HTTP_HOST
configMCP_HTTP_PORT
configCLAUDE_MEMORY_DIR
configUPDATE_GH_REPO
🔐 secretANTHROPIC_API_KEY
configREFLECT_DEBOUNCE_SEC
🔐 secretGITHUB_TOKEN
🔐 secretOPENAI_API_KEY
configV11_PIPELINE
configV11_SKIP_NLI
configV9_RERANKER_BACKENDReranker backend stays on ce-marco by default. =bge-v2-m3 (or off) switches at runtime.
configLME_STORE_DIR
configMEMORY_LLM_PROVIDER
configMEMORY_LLM_MODELOllama model for enrichment
configMEMORY_TRIPLE_PROVIDER
configMEMORY_TRIPLE_MODEL
🔐 secretMEMORY_LLM_API_KEY
configMEMORY_ASYNC_ENRICHMENTv10.1 — move quality gate / contradiction / entity dedup / episodic / wiki to a background worker. See [Performance tuning](#performance-tuning)
configMEMORY_QUALITY_GATE_ENABLED
configMEMORY_CONTRADICTION_DETECT_ENABLED
configMEMORY_OUTBOX_ENABLED
configMEMORY_EPISODIC_ENABLED
configREFLECT_INTERVAL_SEC
configCLAUDE_TOTAL_MEMORY_SRC
configDASHBOARD_PORTHTTP dashboard port
configDASHBOARD_BIND
configTAM_SUPERVISOR_SERVICES
configTAM_MEMORY_DIR
configTAM_SUPERVISOR_MAX_RESTARTS
configTAM_SUPERVISOR_RESTART_WINDOW
configMEMORY_ACTIVECONTEXT_VAULT
configV9_CACHE_L1_ENABLED
configV9_CACHE_L2_ENABLED
configV9_CACHE_L1_SIZE
configV9_CACHE_L1_TTL_SEC
configMEMORY_TAG_VOCAB_PATH
configMEMORY_TAG_SIM_THRESHOLD
configMEMORY_TAG_LEVENSHTEIN_THRESHOLD
configMEMORY_LLM_PROBE_TTL_SECCache TTL for Ollama availability probe
configMEMORY_RECALL_EXCLUDE
configMEMORY_RECALL_EXCLUDED_TAGS
🔐 secretCOHERE_API_KEY
configMEMORY_LLM_API_BASE
configMEMORY_EMBED_PROVIDERKeep =fastembed (default 384d) and only change the LLM provider, OR
configMEMORY_EMBED_API_BASE
🔐 secretMEMORY_EMBED_API_KEYEmbedding backends stay on fastembed by default. Switch via V9_EMBED_BACKEND=openai-3-large (set ) — costs ~$0.10/5k rows for re-embed, expected R@5 lift on conversational data.
configMEMORY_EMBED_MODEL
configMEMORY_ACTIVECONTEXT_DISABLE
configV9_EMBED_BACKENDEmbedding backends stay on fastembed by default. Switch via =openai-3-large (set MEMORY_EMBED_API_KEY) — costs ~$0.10/5k rows for re-embed, expected R@5 lift on conversational data.
configV9_LOCOMO_TUNED_PATH
configV9_RERANKER_MODEL
configV9_RERANKER_FP16
configMEMORY_TEXT_EMBED_MODELModel for embedding_space=text.
configMEMORY_CODE_EMBED_MODELModel for embedding_space=code. The row still records space=code so a future swap is config-only.
configMEMORY_LOG_EMBED_MODELModel for embedding_space=log.
configMEMORY_CONFIG_EMBED_MODELModel for embedding_space=config.
configMEMORY_DEFAULT_EMBEDDING_SPACESpace for unclassified content.
configMEMORY_CONTRADICTION_TYPES
configMEMORY_CONTRADICTION_TOP_K
configMEMORY_CONTRADICTION_MIN_COSINE
configMEMORY_CONTRADICTION_LLM_THRESHOLD
configMEMORY_CONTRADICTION_FLAG_THRESHOLD
configMEMORY_CONTRADICTION_TIMEOUT_SEC
configMEMORY_CONTRADICTION_MODEL
configMEMORY_COREF_ENABLED
configMEMORY_COREF_HISTORY_LIMIT
configMEMORY_COREF_TIMEOUT_SEC
configMEMORY_COREF_MODEL
configFASTEMBED_CACHE_PATH
configMEMORY_ENRICH_TICK_SECWorker tick interval (clamp 0.01..5)
configMEMORY_ENRICH_BATCHRows claimed per tick (clamp 1..50)
configMEMORY_ENRICH_MAX_ATTEMPTSRetries before flipping a row to failed
configMEMORY_ENRICH_STALE_AFTER_SECSeconds before a processing row is reclaimed (worker crash recovery)
configMEMORY_ENTITY_DEDUP_ENABLED
configMEMORY_ENTITY_DEDUP_THRESHOLD
configMEMORY_ENTITY_DEDUP_MAX_CANDIDATES
configMEMORY_ENTITY_DEDUP_TYPES
configMEMORY_ENTITY_DEDUP_LOG_ALL
configMEMORY_EPISODIC_MAX_ENTITIES_PER_EVENT
configMEMORY_OUTBOX_GRACE_SEC
configMEMORY_OUTBOX_MAX_ATTEMPTS
configTAM_MODEL_CACHE
configMEMORY_WIKI_ENABLED
configMEMORY_WIKI_DIR
configMEMORY_WIKI_RECENT_DAYS
configMEMORY_WIKI_AUTO_REFRESH_EVERY_N
configMEMORY_QUALITY_THRESHOLD
configMEMORY_QUALITY_MIN_CHARS
configMEMORY_QUALITY_BYPASS_TYPES
configMEMORY_QUALITY_LOG_ALL
configMEMORY_QUALITY_TIMEOUT_SEC
configMEMORY_QUALITY_MODEL
configMEMORY_QUERY_REWRITE
configMEMORY_SMART_ROUTER
configMEMORY_SMART_ROUTER_FORCE
configRERANKER_MODEL
configHYDE_MODEL
configCROSS_ENCODER_MODEL
configMEMORY_NLI_MODEL
configMEMORY_NLI_CALIBRATION_PATH
// 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

74/74 tools missing one or more hints — memory_recall (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); memory_timeline (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); memory_save (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +71 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.

Tool test coverage

43/74 tools referenced in tests (58%)

Write tests that reference each tool by name so every tool has at least one test.

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 3 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/vbcherepanov/total-agent-memory)](https://m8ven.ai/mcp/vbcherepanov/total-agent-memory)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 6279a90370d32b8af5311816919fb2a6f5f6948d
code hash: a10927a3ec427206036900058f4d103d1df958da315e5f3546f816f32a60a075
verified: 9/4/2026, 7:31:50 PM
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