claude-engram (20alexl/claude-engram) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 16 tools. No publisher has claimed this listing.

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

claude-engram

Persistent memory and session intelligence for AI coding assistants. Auto-tracks mistakes, decisions, and context via hooks. Mines your full session history for patterns, predictions, and cross-session search.

→ 20alexl/claude-engram· listed on glama

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

20alexl

Source: Glama

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

Glamanot scored here

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.
// 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_ENGRAM_DIRStorage location (also the test-isolation seam)
configCLAUDE_ENGRAM_ARCHIVE_DAYSDays until inactive memories archive
configCLAUDE_ENGRAM_SCORER_TIMEOUTScorer daemon idle timeout (seconds)
configCLAUDE_PROJECT_DIR
configCLAUDE_ENGRAM_EMBED_MODELEmbedding model (~1.1GB scorer RAM). all-MiniLM-L6-v2 for a ~90MB setup at lower accuracy
configCLAUDE_ENGRAM_EMBED_DIMMatryoshka truncation dim. Stores are signature-stamped — model changes rebuild them automatically
configCLAUDE_ENGRAM_DEVICEUnset: daemon stays on cpu, bulk jobs use a transient GPU worker (full VRAM release). cuda/cpu forces one device
configCLAUDE_ENGRAM_GPU_BATCHRows per forward pass on the GPU. Raise it on a card with headroom; the peak scales linearly (~26 MiB/row)
configCLAUDE_ENGRAM_GPU_BULK_MINJob size (texts) that routes to the GPU worker
configCLAUDE_ENGRAM_MODELOllama model — only scout_search, memory(consolidate), session_mine(reflect) use it
configCLAUDE_ENGRAM_TIMEOUT
configCLAUDE_ENGRAM_KEEP_ALIVE
configCLAUDE_ENGRAM_HOOK_DEBUG1 prints a stderr breadcrumb per hook
configCLAUDE_CODE_SESSION_ID
configCLAUDE_ENGRAM_LIVE_MINELive mining tick interval (seconds); 0 disables
configCLAUDE_ENGRAM_LAST_FILE_PATHMirror last-read file path to this file (statusline integration)
configCLAUDE_ENGRAM_SESSION_RETENTION_DAYSPrune session-search shards older than N days
// 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

16/16 tools missing one or more hints — claude_engram_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); session_start (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); session_end (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +13 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

9/16 tools referenced in tests (56%)

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/20alexl/claude-engram)](https://m8ven.ai/mcp/20alexl/claude-engram)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 414fa469f4b2e2eb426a6fd95b4def0d66a53e6d
code hash: b15e4a542d0e6ad52ea5482eb59e19b74805d6e4b7a68710921a1a565b422b0c
verified: 9/3/2026, 11:29:11 AM
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