remind-mcp@0.14.0
VERIFIED· not startedPublisher claims: "Agent-driven memory layer for LLMs with temporal facts, semantic retrieval, and structured curation" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
AZURE_OPENAI_API_KEYOPENAI_API_KEYConfiguration, not credentials: AZURE_OPENAI_API_BASE_URL, AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME, AZURE_OPENAI_EMBEDDING_SIZE, EMBEDDING_PROVIDER, LLM_PROVIDER, LOCAL_EMBEDDING_MODEL, OLLAMA_EMBEDDING_MODEL, OLLAMA_URL, OPENAI_BASE_URL, OPENAI_EMBEDDING_MODEL, OPENAI_EMBEDDING_SIZE, REMIND_CLI_OUTPUT_MODE, REMIND_CLI_RECALL_WORKER_ENABLED, REMIND_CLI_RECALL_WORKER_IDLE_SECONDS, REMIND_DB_URL, REMIND_DECAY_ENABLED, REMIND_DECAY_INTERVAL, REMIND_DECAY_RATE, REMIND_EPISODE_TYPES, REMIND_FACT_CLUSTER_JACCARD_THRESHOLD, REMIND_HYBRID_KEYWORD_WEIGHT, REMIND_LEXICAL_ENABLED, REMIND_LOGGING_ENABLED, REMIND_RECALL_INITIAL_CANDIDATES, REMIND_RECALL_MAX_CHARS, REMIND_RECALL_MIN_SCORE, REMIND_RECALL_TIMEOUT_MS, REMIND_REMEMBER_NEARBY_K, REMIND_RERANKING_ENABLED, REMIND_RERANKING_MODEL, REMIND_RRF_K, REMIND_STORE- Where it talks to
- no vendor host named in the codeAlso azure.com, svelte.dev — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names azure.com, svelte.dev as well as its own vendor. The guard injects AZURE_OPENAI_API_KEY, OPENAI_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.
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; not started: dependency install failed; the server itself was not observed) on 2026-11-15 and scored it 80/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
subprocess.run([sys.executable, "-c", script, str(directory), f"Worker {index}"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# Load environment variables from .env fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.process = subprocess.Popen(command, stdin=subprocess.PIPE, stdout=subprocess.PIPE,Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.…on",...n!=="GET"&&s?{"If-Match":s}:{},...t?.headers}});if(!o.ok){const l=await o.json().catch(()=>({error:o.statusText}));throw o.status===409?new Error("Memory changed since it was loaded. Refresh and review before saving."):new Error(l.e…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.return subprocess.run(["git", "-C", str(root), *args], capture_output=True, text=True, check=check)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.body = await request.json() if request.method == "POST" else {}Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.process = subprocess.Popen([sys.executable, "-m", "remind.mcp_server", "--port", str(port),Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.commit = subprocess.run(["git", "-C", str(root), "rev-parse", "HEAD"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.(transcripts / f"session-{number}.json").write_text(canonical_json(output))Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.version = subprocess.run([resolved, "--version"], capture_output=True, text=True, check=True, timeout=10).stdout.strip()Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.…t Ic=1,Fc=2,Ro=4,Oc=8,qc=16,Vc=1,Hc=2,Io=4,Bc=8,Uc=16,Yc=1,jc=2,Yt=Symbol(),Gc="http://www.w3.org/1999/xhtml",Xc="http://www.w3.org/2000/svg",Kc="@attach",Ys=!1;var fi=Array.isArray,Wc=Array.prototype.indexOf,gs=Array.from,Fo=O…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.from remind.mcp_server import run_server_sse, register_db_aliasFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.result = subprocess.run([sys.executable, "-c", script, str(directory)], env=environment(), capture_output=True, timeout=30)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.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
Not checked against OSV yet; the weekly check has not reached this version.