Open source memory infrastructure for AI and humans. Turn scattered knowledge into AI-ready context across Claude, Cursor, ChatGPT, and any MCP client.
- capability exposure inferred + 35
- tool safety inferred + 12
- trust mitigators mixed − 3
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 1w ago · see ecosystem CVEs →
- D · 64 → C · 44
- C · 57 → D · 64
- C · 49 → C · 57
- C · 56 → C · 49
No known CVEs for this server.
- high dangerous code
dynamic exec: new Function(), vm exec · obfuscated payload: dynamic require()/import()
analyzed commit 3176449 · analyzer v33 · 9h ago
skills & prompt files 6
- agent-rules streamient-streamient-3176449/.cursor/rules/streamient-mcp-agent-workflow.mdc
- agent-rules streamient-streamient-3176449/AGENTS.md
- skill streamient-streamient-3176449/SKILL.md
- agent-rules streamient-streamient-3176449/docs/AGENTS.md
- agent-rules streamient-streamient-3176449/docs/mcp/agents.md
- skill streamient-streamient-3176449/streamient-memory.zip!/SKILL.md
danger signals4
- dynamic code execution new Function() streamient-streamient-3176449/public/js/vendor.js :12672
result[paramName] = new Function(`return ${value}`)(); - dynamic code execution vm exec streamient-streamient-3176449/test/account-deletion-ui.test.js :37
await vm.runInNewContext(source, context); - dynamic code execution vm exec streamient-streamient-3176449/test/profile-settings-ui.test.js :99
vm.runInNewContext(dateFormatSource, context); - dynamic code execution new Function() streamient-streamient-3176449/test/session-writes.test.js :38
const middleware = new Function('session', 'MongoStore', 'config', 'process', `${configuration}; return sessionMiddleware;`)((settings) => { options = settings; return session(settings); }, { create:
[](https://mcpobservatory.com/servers/github:streamient/streamient/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of streamient.