Back to MCP Trust Indexm8ven
C
Limited view
73/100
14 days ago

mem0-mcp-toggle

A local Mem0 MCP server for macOS with a menu bar toggle, storing memories locally in Chroma and using any OpenAI-compatible LLM for fact extraction.

→ ost527/mem0-mcp-toggle· listed on glama

Limited view. Automated analysis covers part of this stack. Findings reflect what we verified. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

Limited view: static analysis for Python is partially covered.

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

ost527

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

Glama

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.
// 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.
configMEM0_CHROMA_PATH~/.only-my-mem0ry/chroma vector store location
configMEM0_DEFAULT_USERdeveloper_workspace default user_id
configMEM0_RELATED_TOPK3 nearest memories add_memory surfaces
configMEM0_IDLE_TIMEOUTMEM0_MCP_PORT=8800 =900 ./install.sh
configMEM0_EMBEDDER_MODELand cross-lingual recall. Swapping on a populated store
configMEM0_EMBEDDER_DIMSMEM0_EMBEDDER_MODEL=sentence-transformers/all-MiniLM-L6-v2 =384 \
configMEM0_COLLECTIONmem0 Chroma collection name
configMEM0_SEARCH_TOPK10 results search_memories returns
configMEM0_DUP_THRESHOLD, computed locally over the stored embeddings — no LLM) as prime
configMEM0_DUP_MAX_DOCS2000 skip the O(n²) duplicate scan in curate_memories above this many memories
configMEM0_HISTORY_DEPTHcapped at entries per memory (default 5; 0 disables). A
configMEM0_CONFLICT_LOW([, MEM0_DUP_THRESHOLD)) that disagree on a number, weekday,
configMEM0_RECENCY_BIAS0 opt-in recency tie-break weight over the fused ranking; 0 = off (a value <1 only breaks near-ties; measure before raising)
configMEM0_CONFIDENCE_BIAS0 opt-in confidence tie-break weight; 0 = off
configMEM0_HYBRID_SEARCHwith =0. No extra dependency; all local and deterministic.
configMEM0_RRF_K60 RRF constant (used only when MEM0_FUSION=rrf)
configMEM0_FUSIONrrf (it can reorder dense results — measure first). Turn hybrid off
configMEM0_BM25_MAX_DOCS5000 cap on lexical scan size for very large stores
configMEM0_META_FILE~/.only-my-mem0ry/memory_meta.json sidecar: pin state + per-memory usage stats
configMEM0_CORE_FILE~/.only-my-mem0ry/CORE_MEMORY.md always-on core mirror file (rules files read this)
configMEM0_CORE_BUDGETpin_memory(id) Pin a memory into always-on core (mirrored to a file your rules load every session). Bounded by .
configMEM0_MCP_TRANSPORT
configMEM0_MCP_HOST
configMEM0_MCP_PORT8800 MEM0_IDLE_TIMEOUT=900 ./install.sh
configEVAL_VERBOSE1 .venv/bin/python server/eval_recall.py # per-query first-hit ranks
configMEM0_SERVER_LABELcom.only-my-mem0ry.server launchd label to start on demand
configMEM0_PROXY_KEEPALIVEclamp(IDLE/3, 5, 120) seconds between keepalive pings
configMEM0_BACKEND_READY_TIMEOUT40 seconds to wait for the backend to come up
configMEM0_BACKUP_KEEP
// 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

14/14 tools missing one or more hints — add_memory (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); add_memories (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); update_memory (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +11 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.

Tests exist

No test files found

Add tests that exercise each declared tool.

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/ost527-mem0-mcp-toggle-10kerw)](https://m8ven.ai/mcp/ost527-mem0-mcp-toggle-10kerw)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 067cbc133a9da3b3d1c728448814f500898b3e2c
code hash: cbebbfa19b64d75b6bed3a6bf697c7a8429724424269f2393311ec2c93b572d0
verified: 8/5/2026, 6:42:16 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