mneme
Persistent long-term memory for AI agents via MCP, saving 80-90% memory-related token costs by enabling on-demand recall instead of always-injecting context.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
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
AgentGameLab
Source: Glama
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
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
Zod denial of service vulnerability
CLAUDE_BINPath to Claude CLI (for compression pipeline)EMBEDDING_API_BASE_URLOpenAI-compatible embedding API base URLEMBEDDING_API_KEYAPI key for embedding serviceEMBEDDING_DIMENSIONVector dimensionEMBEDDING_MODELEmbedding model nameEMBEDDING_TIMEOUT_MSENTITY_LLM_API_BASE_URLOpenAI-compatible chat base URL for the optional entity layer (v2.5; dormant if unset)ENTITY_LLM_API_KEYAPI key for entity extractionENTITY_LLM_MODELChat model for entity extractionMNEME_AUTHMNEME_DB_PATHMNEME_DEFAULT_HOSTMNEME_HOOK_HYBRID_TIMEOUT_MSMNEME_HOOK_OBSERVEMNEME_HOST_TOKENMNEME_HOST_TOKENSMNEME_HTTP_URLMNEME_INDEX_PATHMNEME_LEVELMNEME_MEMORY_DIRSMNEME_META_GATE_PERSON_NAMESMNEME_META_GATE_PROJECT_NAMESMNEME_PRIMARY_HOSTMNEME_PROXY_CLOSE_TIMEOUT_MSMNEME_PROXY_TIMEOUT_MSMNEME_QUARANTINE_HOSTSMNEME_RECALL_TRACE_MAX_ROWSMaximum retained recall traces; clamped to 100-100000MNEME_RECALL_TRACE_RETENTION_DAYSRecall trace retention; clamped to 1-365 days. Traces contain hashes/counts/rowids, never raw query or memory textMNEME_STATE_DIRMNEME_TOKEN_CODEXMNEME_TOOL_LEVELTOKENMEM_COMPACT_SESSIONSession ID for compact summaryTOKENMEM_COMPACT_SUMMARYCompact summary text (for SessionStart hook)TOKENMEM_DB_PATHDB path configurable via environment variableTool 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
15/15 tools missing one or more hints — recall_memory (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); recall_claude_memory (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_recall_trace (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +12 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
6/15 tools referenced in tests (40%)
Write tests that reference each tool by name so every tool has at least one test.
Secrets stay with their owner
1 secret sent to a request target we could not resolve (EMBEDDING_API_KEY → dynamic) — often a configured endpoint, not necessarily third-party
Audit where credentials are sent. A NOTION_TOKEN should only reach api.notion.com — never a third-party host.
Secrets not logged
11 secret values sent to error/log
Redact or omit secret values from log output.
Production dependencies are patched
0 critical, 1 high severity in production deps — @modelcontextprotocol/sdk@1.0.0 (high), zod@3.0.0 (low)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
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.
[](https://m8ven.ai/mcp/agentgamelab-mneme-2qewq3)?variant=verified from the URL.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