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
sekhardp
Source: github_repo_search
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.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
dynamic_tool_111run_queryExecute a read-only SQL query against BigQuery and return results formatted as CSV. Args: query: The standard SQL query to execute.
list_datasetsList all datasets in a GCP project.
list_tablesList all tables within a given dataset.
compile_deck_to_pptx_base64Compiles a structured SlideDeck JSON schema into a base64-encoded 16:9 widescreen PowerPoint (.pptx) presentation with native charts, KPI cards, and custom themes. Accepts either deck_json (string or dict) or direct slides list.
validate_presentation_schemaValidates that a JSON payload adheres to the required SlideDeck schema for PPTX compilation.
search_knowledge_baseSearch document knowledge base using cosine similarity retrieval. Returns the top matching raw text passages (default 10-15 chunks) directly.
check_document_vector_statusCheck if a document has been successfully vectorized and is ready for semantic retrieval.
list_available_documentsList all available documents in the knowledge base.
Gold_Account_Assignment_FactUse this tool to retrieve procurement account assignment information linking spend to cost centers, internal orders, WBS elements and financial ownership.
Gold_Content_Brand_InvestmentUse this tool to retrieve marketing, content, branding, agency and media-related spend data across the enterprise.
Gold_Cost_Center_IntelligenceUse this tool to retrieve cost-center spending intelligence, peer comparisons and purchasing behaviour patterns.
Gold_Enterprise_Spend_FactUse this tool to retrieve the canonical enterprise spend fact table at spend-line level for procurement and vendor analysis.
Gold_Executive_DashboardUse this tool to retrieve executive-ready aggregated KPIs and summary metrics for leadership reporting.
Gold_Financial_AttributionUse this tool to retrieve financial ownership information after FI/CO reallocations and internal repostings.
Gold_GL_Account_IntelligenceUse this tool to retrieve General Ledger account classifications and financial reporting structures that enrich spend data.
Gold_Invoice_FactUse this tool to retrieve canonical invoice-level analytical data that links invoices with purchase orders, vendors and accounting information.
Gold_Material_IntelligenceUse this tool to retrieve material-centric procurement intelligence for materials, commodities and categories.
Gold_Monthly_Spend_TrendUse this tool to retrieve pre-aggregated monthly spend trends optimized for executive reporting and time-series analysis.
Gold_Procurement_KPIUse this tool to retrieve procurement KPIs including purchasing performance, supplier counts, savings indicators and operational procurement metrics.
Gold_Savings_OpportunityUse this tool to get savings opportunity rows from the Doge MCP pilot dataset.
Gold_Shadow_ITUse this tool to detect technology-related purchases performed outside central IT governance using vendor classification, cost center ownership and technology indicators.
Gold_Supplier_RiskUse this tool to assess supplier dependency, concentration and procurement risk across the enterprise.
Gold_Supply_Chain_IntelligenceUse this tool to retrieve logistics, warehousing, packaging, manufacturing and operational procurement intelligence.
Gold_Vendor_IntelligenceUse this tool to retrieve business classifications of suppliers, including activity type, vendor family, technology indicators and business capability.
Gold_Vendor_SimilarityUse this tool to identify vendors providing similar or overlapping products or services by comparing classifications, purchasing patterns and business capabilities.
Gold_Vendor_Spend_ClassificationUse this tool to get vendor spend classification rows from the Doge MCP pilot dataset.
REGISTRY_CONFIG_PATHGOOGLE_CLOUD_PROJECTGCP_PROJECTMCP_HOSTMCP_PORTMCP_TRANSPORTBIGQUERY_PROJECT_IDBIGQUERY_AUDIENCESERVICE_ACCOUNT_FILEGOOGLE_APPLICATION_CREDENTIALSSERVICE_ACCOUNT_JSONSERVICE_ACCOUNT_INFOSERVICE_ACCOUNT_BASE64GOOGLE_CLOUD_LOCATIONEMBEDDING_MODELEMBEDDING_TIMEOUT_SECONDSDEFAULT_TOP_KMAX_TOP_KSERVER_HOSTPORTTool 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
27/27 tools missing one or more hints — dynamic_tool_111 (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); run_query (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_datasets (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +24 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.
No access to sensitive paths
Reads sensitive paths: /secrets/credentials.json, /secrets/sgs-bq-credentials
Remove reads of sensitive system paths. If you genuinely need them, document why in the README.
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/sekhardp/ai-plt-mcp-servers)?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