nxt-ai-assistant (nxtgrid/nxt-ai-assistant) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 112 tools. No publisher has claimed this listing.
A production-ready chat orchestrator using Google's Gemini API with dynamic system instructions from Google Docs, RAG knowledge retrieval, and MCP tool integration.
Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. 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
nxtgrid
Source: github_code
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
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
MCP_GATEWAY_TOKEN_SECRETTurning it off. Unset either MCP_GATEWAY_BASE_URL or . The gateway is then never mounted — no code change, no separate deploy, and nothing else in the service is affected.MCP_GATEWAY_BASE_URLTurning it off. Unset either or MCP_GATEWAY_TOKEN_SECRET. The gateway is then never mounted — no code change, no separate deploy, and nothing else in the service is affected.CHAT_DB_URLconversations, RAG chunks, prompts, skills, escalations, and anything this repo migratesCHAT_DB_SERVICE_KEYconversations, RAG chunks, prompts, skills, escalations, and anything this repo migratesSUPABASE_KEYVRM_MQTT_USERVRM_TOKENField/grid systems — VRM (, MQTT), ChirpStack, Calin v1/v2, metering and Tiamat APIsEQUIPMENT_CONTROL_ALLOWED_USERSORGANIZATION_NAMESTAFF_ORG_IDcontrols which organization_id in your accounts table gets staff-mode access (full tools, staff instructions). The default is 2 — change it to match your own database:EQUIPMENT_DIAGNOSTICS_DEFAULT_TIME_RANGEEQUIPMENT_DIAGNOSTICS_OUTAGE_THRESHOLD_WEQUIPMENT_DIAGNOSTICS_CHART_WIDTHEQUIPMENT_DIAGNOSTICS_CHART_HEIGHTDEFAULT_TIMEZONE✅ Natural language time parsing with timezone configurable via env varSUPABASE_SERVICE_KEYGRAFANA_URLGRAFANA_USERNAMEGRAFANA_PASSWORDGRAFANA_METADATA_TIMEOUTGRAFANA_VARIABLE_TIMEOUTGRAFANA_QUERY_TIMEOUTGRAFANA_ENABLED_PANELSGRAFANA_PANELS_METADATAGRAFANA_DASHBOARD_VARIABLESGRAFANA_ENABLEDGRAFANA_ACTIONS_ENABLEDGRID_DESIGN_APP_IDGRID_DESIGN_APP_KEYAPPSHEET_REGIONGRID_DESIGN_ACTIONS_ENABLEDGRID_DESIGN_BACKENDGRID_DESIGN_GRIDS_TABLEGRID_DESIGN_DESIGNS_TABLEGRID_DESIGN_BOM_TABLEGRID_DESIGN_ACTIONS_TABLEMAIN_SUPABASE_URLMAIN_SUPABASE_KEYGRID_DESIGN_COMPONENTS_DB_TABLEGRID_DESIGN_AUTOPOPULATE_WAITGRID_DESIGN_BOM_WAITCHAT_ORCHESTRATOR_URLAPI_KEYmust match the API_KEY env var. To verify:AUTH_DB_HOSTAUTH_DB_PORTAUTH_DB_USERAUTH_DB_PASSWORDAUTH_DB_NAMEJIRA_BASE_URLJIRA_USERNAMEJIRA_API_TOKENJIRA_OPS_CLOUD_IDJIRA_OPS_SCHEDULE_IDJIRA_ORGANIZATION_FIELD_IDTAVILY_API_KEYESCALATION_TELEGRAM_CHAT_IDMETA_ACTIONS_ENABLEDCALIN_V1_BASE_URLCALIN_V1_USERNAMECALIN_V1_PASSWORDCALIN_V1_COMPANYCALIN_V2_BASE_URLCALIN_V2_USERNAMECALIN_V2_PASSWORDCALIN_V2_COMPANYCHIRPSTACK_BASE_URLCHIRPSTACK_API_KEYCHIRPSTACK_TENANT_IDSUPABASE_JWT_SECRETSUPABASE_USER_EMAILSUPABASE_USER_PASSWORDPAYMENT_PROCESSOR_API_URLPAYMENT_PROCESSOR_SECRET_KEYNIGERIA_IMPORT_TARIFF_SHEET_IDNIGERIA_IMPORT_STANDARDS_PDF_IDSOLAR_ACTIONS_ENABLEDHOSTNICEGUI_RELOADIDENTITY_ASSERTION_KEYCORS_ALLOWED_ORIGINSAPP_URLMINI_APP_FORMS_ENABLEDMETRICS_ENABLEDMETRICS_TIMEZONEMETRICS_SCHEDULE_HOURJIRA_SWEEP_ENABLEDJIRA_WEBHOOK_SECRETthe same JIRA_WEBHOOK_SECRET valueTELEGRAM_BOT_TOKEN3. Copy the API token BotFather gives you — this is your .BOT_ENABLEDNOTIFY_SHARED_SECRETNOTIFY_ENDPOINT_ENABLEDDisable the endpoint entirely: =false — /notify 503s.VERIFICATION_ENABLEDGOOGLE_CLIENT_IDAUTH_CLIENT_IDGoogle Workspace — OAuth sign-in (/SECRET), plus Docs/Drive/Sheets via a service account (GOOGLE_SERVICE_ACCOUNT_JSON, _DOC_ID) and an Apps Script helper (ANANSI_HELPER_)GOOGLE_CLIENT_SECRETAUTH_CLIENT_SECRETAUTH_SUPABASE_URLAUTH_SUPABASE_KEYAUTH_SUPABASE_ANON_KEYMETERING_API_URLMETERING_BEARER_TOKENMETERING_API_KEYTIMESCALE_HOSTTIMESCALE_PORTTIMESCALE_DATABASETIMESCALE_USERTIMESCALE_PASSWORDVRM_BATCH_MAX_CONCURRENTCUSTOMER_METER_ACTIONS_ENABLEDCUSTOMER_METER_POWER_LIMIT_OPTIONSPLATFORM_BASE_URLMINI_APP_BASE_URLMINI_APP_HMAC_SECRETMCP_DISABLED_TOOLSVRM_USER_IDNO_REPLY_CHAT_IDSTELEGRAM_BOT_USERNAME4. Set to your bot's @handle (without the @).TOOLS_SERVICE_URLLLM_PROVIDERGOOGLE_API_KEYOPENROUTER_API_KEYGEMINI_TEMPERATUREFALLBACK_MODELALLOW_PARALLEL_CALLSMAX_TOOL_ROUNDSAUTH_COOKIE_SECRETAUTH_REDIRECT_URIGRID_DESIGN_DEV_NO_AUTHEPISODIC_DISTILL_ENABLEDEPISODIC_DISTILL_HOURGRAFANA_FOLDER_NAMEGRAFANA_ENABLED_DASHBOARDSGRAFANA_FORCE_FULL_REINDEXGRAFANA_SYNC_HOURDIGITALOCEAN_API_TOKENDIGITALOCEAN_APP_IDANANSI_BOT_HEALTH_URLOPEN_ROUTER_BEARER_TOKENSTAFF_ORG_NAMEOPENROUTER_MODELPORTSUPABASE_URLSUPABASE_ANON_KEYSUPABASE_SERVICE_ROLE_KEYTool 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
112/112 tools missing one or more hints — dynamic_tool_326 (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); _tool_meter_information (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); _tool_customer_get_meter_consumption (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +109 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
Only 24/112 tools referenced in tests (21%)
Write tests that reference each tool by name so every tool has at least one test.
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/nxtgrid/nxt-ai-assistant)?variant=verified to the badge 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