memory-mcp@0.1.0
VERIFIEDPublisher claims: "Provides conversational memory with short/long-term layering, consolidation, and time-decay/capacity/soft-archive forgetting, alongside rule-based slang and internet-slang discovery with optional LLM explanations. Exposes append, query, touch, forget, restore, consolidate, context-render, and slang operations over stdio MCP and a token-guarded loopback HTTP API." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Server started and answered tools/list.- Tested
- MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
- Not tested
- what the tools do when called with real credentials
Before you give it your token
- It will ask for
MEMORY_MCP_GATEWAY_SECRETMEMORY_MCP_LLM_API_KEYMEMORY_MCP_TOKENConfiguration, not credentials: DSH_HOME, DSH_PROFILE, MEMORY_LAYERS_V2, MEMORY_MCP_DATA_DIR, MEMORY_MCP_EMOTION_FRESH_HOURS, MEMORY_MCP_GATEWAY_ID, MEMORY_MCP_GATEWAY_TRANSPORT, MEMORY_MCP_GATEWAY_WS_URL, MEMORY_MCP_HEAD_QUIET_MINUTES, MEMORY_MCP_HTTP_PORT, MEMORY_MCP_LLM_BASE_URL, MEMORY_MCP_LLM_ENABLED, MEMORY_MCP_LLM_MODEL, MEMORY_MCP_LLM_TIMEOUT_MS, MEMORY_MCP_PLATFORM_STRICT, MEMORY_MCP_PLATFORMS, MEMORY_MCP_RAW_RETENTION_DAYS, MEMORY_MCP_RECALL_CROSS_PLATFORM, MEMORY_MCP_RECALL_MAX_CHARS, MEMORY_MCP_RECALL_MAX_ROWS, MEMORY_MCP_RELATION_IDENTITY, MEMORY_MCP_SESSION_IDLE_MINUTES, MEMORY_MCP_STATE_DIR, MEMORY_MCP_SUMMARY_QUIET_MINUTES, MEMORY_MCP_SUMMARY_TICK_MINUTES, QQ_BRIDGE_DIR- Where it talks to
- no vendor host named in the code
- What the honeypot saw
- no credential files read · no network
- What we could not test
- what the tools do when called with real credentials
Connect it with a scoped credential, under the guard. It asks for MEMORY_MCP_GATEWAY_SECRET, MEMORY_MCP_LLM_API_KEY, MEMORY_MCP_TOKEN and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-10 and scored it 91/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 23 s · 2 scenarios · 0 deviationsStatic findings
/* Windows 上 chmod 可能不支持，忽略 */Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.No other findings across 14,439 lines in 67 files.
Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.