zmem (zaxbysauce/zmem) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 9 tools. No publisher has claimed this listing.

C
Emerging
74/100
9 days ago

zmem

Memory plugin for z.ai's ZCode

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

zaxbysauce

Source: 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 →

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 1 credential: ZMEM_MCP_TOKEN
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.
configCLAUDE_PLUGIN_OPTION_STOREDIRECTORY
configCLAUDE_PLUGIN_ROOT
configCLAUDE_PROJECT_DIR
configCLAUDE_SESSION_ID
configCODEX_PROJECT_DIR
configPLUGIN_ROOT
configZCODE_PLUGIN_ROOT
configZCODE_PROJECT_DIR
configZMEM_BASH_PATHbash
configZMEM_CTX_BUDGET25000 / 9000
configZMEM_DATA, ZMEM_TIER0, etc.) so the hook scripts and store.py never need
configZMEM_HOSTdetects which tool is running and sets a canonical env (,
configZMEM_SKILLS_DIRSderived
configZMEM_MCP_MAX_CONCURRENTCap on simultaneous store.py subprocesses the MCP server will run (overload protection). 8
configZMEM_MCP_QUEUE_TIMEOUT_SHow long a queued tool call waits for a concurrency slot before returning an overload error. 60
configZMEM_HOMEinactive — copy users must set to this repo's checkout path
configZMEM_MCP_DEFAULT_NSOpt-in configured default namespace for MCP add when the client omits it (issue #71 C; user:global otherwise — never a near-miss form like global). —
configZMEM_MCP_TOKEN_FILE
🔐 secretZMEM_MCP_TOKEN[nssm](https://nssm.cc/); set and ZMEM_HOME as system env
configZMEM_NAMESPACEchain as the prefetch (ZMEM_MCP_NAMESPACE → →
configZMEM_INJECT_FLOOR_RECENT
configZMEM_STOREOverride the store SQLite path directly (wins over ZMEM_DATA). —
configZMEM_EMBED_PROFILEprofiles"); profiles are selected with .
configZMEM_TEST_NOW
configGITHUB_OUTPUT
configZMEM_CONVENTION_INTERVALFire the convention nudge every N successful tool calls. 10
configZMEM_QUERY_CONTEXT
configZMEM_HERMES_CORRECTIONSuser:global). =0 disables.
configZMEM_MCP_NAMESPACEScoped-token deployments MUST set (issue #71
configZMEM_MCP_URLRemote mode (issue #71 A): point the Hermes pre_llm_call hook at the LAN MCP server; the passive prefetch rides session_start (--no-bump). Unset = local-store mode. —
configZMEM_MCP_TIMEOUTPrefetch subprocess timeout in seconds (the hook itself allows 15). 8
configZMEM_MCP_ALLOW_INSECURE_BIND1 is set. For Windows persistence, register
configZMEM_BG_LOG_MAX_BYTES
configCLAUDE_PLUGIN_DATA
configZCODE_PLUGIN_DATA
configZMEM_SESSION
configZCODE_SESSION_ID
configZMEM_NS_MIGRATION_MAPto a JSON object from each old namespace to a live
configZMEM_CROSS_ENCODER_MODEL
configZMEM_MODELS_DIR<checkout>/skills/memory/models
configZMEM_MODEL_URLXenova HF URL
configZMEM_MODEL_AUTODOWNLOADSet 1 to attempt a lazy download of the embedding model when absent. Defaults to 0 (off; the download is opt-in and the CI sets it to 0). 0
configZMEM_PROXY_FORGE_HOSTunset
configZMEM_BACKUP_DIR<store dir>/backups
configZMEM_AUTO_REKEY0 disables the automatic near-miss namespace rekey on store open (issue #71 C; --no-auto-rekey per invocation). 1
configZMEM_UNRECALLED_DAYS
configZMEM_NLI_CMD
configZMEM_CE_DEBUG_TRACEBACK
configZMEM_CODEX_MEMORY~/.codex/MEMORY.md
configZMEM_HERMES_SESSIONS~/.hermes/sessions
configZMEM_PROMOTION_REVIEW_DIRderived
configZMEM_CORE_MD<data dir>/core.md
configZMEM_ALLOW_NEWER_SCHEMA
configZMEM_CAPTURE_MODEmanual
// 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

9/9 tools missing one or more hints — recall (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); add (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +6 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.

Secrets not logged

1 secret value sent to print

Redact or omit secret values from log output.

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/zaxbysauce/zmem)](https://m8ven.ai/mcp/zaxbysauce/zmem)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 0cb93271f781fda922449ab8fa092b2240358ffb
code hash: e25f96dbd04da180400777e3cad8b13b9b8f1c357bedcfd6de2cd9f126d3d140
verified: 9/3/2026, 6:16:09 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