caura
Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
Warning. Serious findings were identified. Review the full report before connecting. 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
caura-ai
Source: github_topic
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.
MEMCLAW_AGENT_IDMEMCLAW_API_KEYyour-shared-keyMEMCLAW_API_PREFIXMEMCLAW_API_URLBase URL of the core-api server.MEMCLAW_AUTO_FIX_CONFIGMEMCLAW_AUTO_WRITE_TURNSAuto-write turn summaries (default true).MEMCLAW_DEPLOY_FAILURE_COOLDOWN_HOURSMEMCLAW_DISPLAY_NAME_OVERRIDEMEMCLAW_EDUCATION_PROMPTMEMCLAW_FLEET_IDDefault fleet id for writes/heartbeat.MEMCLAW_INTERVIEWERand submits windows (add =true to the plugin env).MEMCLAW_INTERVIEWER_TASKSMEMCLAW_KEYSTONES_ENABLEDMEMCLAW_KEYSTONES_TOKEN_CAPMEMCLAW_NODE_NAMEFleet node identifier reported on heartbeat.MEMCLAW_RECALL_DENY_SESSIONSMEMCLAW_RECALL_GATEMEMCLAW_RECALL_MACHINE_PATTERNSMEMCLAW_RECALL_MIN_PROMPT_CHARSMEMCLAW_RECALL_POLICYMEMCLAW_RECALL_TRIGGER_KEYWORDSMEMCLAW_REQUIRE_SIGNED_COMMANDSMEMCLAW_SKILL_TARGETSMEMCLAW_TASK_DB_PATHMEMCLAW_TENANT_IDOptional pre-resolved tenant id; bypasses lookup.TESTINGOPENAI_API_KEYOpenAI (default) EMBEDDING_PROVIDER=openai<br>ENTITY_EXTRACTION_PROVIDER=openaiGOOGLE_API_KEYPLATFORM_EMBEDDING_PROVIDER(empty) Platform-default embeddings: openai or empty to disablePLATFORM_EMBEDDING_API_KEYOpenAI API key for platform embeddingsPLATFORM_EMBEDDING_BASE_URLPLATFORM_EMBEDDING_TRUNCATE_TO_DIMPLATFORM_EMBEDDING_MODEL(empty) Embedding model override (e.g. text-embedding-3-small)OPENAI_EMBEDDING_BASE_URLSelf-hosted (TEI / bge-m3) --profile embed-local + =http://tei:80/v1<br>+ OPENAI_EMBEDDING_MODEL=BAAI/bge-m3<br>+ OPENAI_EMBEDDING_SEND_DIMENSIONS=false none — runs locallyEMBEDDING_QUERY_INSTRUCTIONOPENAI_EMBEDDING_TRUNCATE_TO_DIMEMBEDDING_PROVIDEROpenAI (default) =openai<br>ENTITY_EXTRACTION_PROVIDER=openai OPENAI_API_KEYOPENAI_EMBEDDING_MODELSelf-hosted (TEI / bge-m3) --profile embed-local + OPENAI_EMBEDDING_BASE_URL=http://tei:80/v1<br>+ =BAAI/bge-m3<br>+ OPENAI_EMBEDDING_SEND_DIMENSIONS=false none — runs locallyOPENAI_REQUEST_TIMEOUT_SECONDSEMBEDDING_RETRY_ATTEMPTSEMBEDDING_RETRY_DELAY_SEVENT_BUS_BACKENDGCP_PROJECT_IDEVENT_BUS_SUBSCRIPTION_PREFIXEVENT_BUS_TOPIC_PREFIXEVENT_BUS_ENVENVIRONMENTdevelopment development or productionEVENT_BUS_PUBSUB_MAX_MESSAGESANTHROPIC_API_KEYAnthropic EMBEDDING_PROVIDER=openai<br>ENTITY_EXTRACTION_PROVIDER=anthropic + OPENAI_API_KEYOPENROUTER_API_KEYOpenRouter EMBEDDING_PROVIDER=openai<br>ENTITY_EXTRACTION_PROVIDER=openrouter + OPENAI_API_KEYGEMINI_API_KEYGoogle Gemini EMBEDDING_PROVIDER=openai<br>ENTITY_EXTRACTION_PROVIDER=gemini + OPENAI_API_KEYENTITY_EXTRACTION_MODELgpt-5.4-nano LLM model for enrichment and entity extractionPLATFORM_LLM_PROVIDER(empty) Platform-default LLM: openai, vertex, or empty to disablePLATFORM_LLM_GCP_PROJECT_IDGCP project for platform Vertex LLMPLATFORM_LLM_GCP_LOCATIONus-central1 GCP region for platform Vertex LLMPLATFORM_LLM_MODEL(empty) Model override (e.g. gpt-5.4-nano, gemini-3.1-flash-lite-preview)PLATFORM_LLM_API_KEYOpenAI API key for the platform LLM singletonLLM_FALLBACK_MODEL_OPENAIRANK_API_KEYRANK_PROVIDERRANK_ENABLEDRANK_MODELRANK_MAX_LENGTHRANK_BASE_URLRANK_TIMEOUT_SECONDSRANK_RETRY_ATTEMPTSRANK_RETRY_DELAY_SRANK_CANDIDATE_LIMITRANK_REMOTE_MAX_BATCHMEMCLAW_VERSIONDependencies
1 dependencies, 1 flagged: @playwright/test
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
1/1 tools missing one or more hints — handler (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint). 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.
No access to sensitive paths
Reads sensitive paths: /tmp/e2e.env
Remove reads of sensitive system paths. If you genuinely need them, document why in the README.
Shell command execution
4 child_process/subprocess calls in production code — runs shell commands (plugin/src/deploy.ts:80, plugin/src/heartbeat.ts:135, plugin/src/heartbeat.ts:411)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Secrets stay with their owner
6 secret/sensitive values flow into network calls (MEMCLAW_API_KEY → dynamic, MEMCLAW_API_KEY → dynamic) (2 other flows matched canonical API hosts)
Audit where credentials are sent. A NOTION_TOKEN should only reach api.notion.com — never a third-party host.
Secrets not logged
10 secret values sent to console.log
Redact or omit secret values from log output.
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/caura-ai-caura-1w2oad)?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