smartdatabrokers-slideforge
mcpsmitheryGenerate consulting-quality PowerPoint slides via API and MCP. Real editable .pptx files with 27 tools. - Template rendering: 50 consulting frameworks (SWOT, KPI, timeline, waterfall, org chart, data table). $0.03/slide, <1s. - Creative AI design: Describe any slide in plain English. AI designs the layout with visual QA. $0.20/slide, ~30s. - Deck generation: Multi-slide decks in parallel. Mix template + creative slides. - PDF to PPTX: Convert PDF back to editable PowerPoint via vector extraction. $0.01/page. - Translation: Translate .pptx files into 8 languages preserving all formatting. $0.02/slide. - 24 design system components: Compose slides from Metric, BarList, Table, Steps, etc. via JSON spec. - Iterate and refine: Improve slides with text feedback. $0.10/iteration. - Brand themes: 8 built-in + custom themes from JSON or .pptx upload. - From Image: Recreate a slide from a screenshot or photo. Free $3 trial on signup. No subscription. Pay per slide. OAuth 2.1 for zero-config MCP setup.
By Smithery | 47 findings | Scanned 4/19/2026 | tooltrust-scanner/v0.3.8
Risk Summary
Needs ApprovalDep Visibility plus Excessive Permissions raises enough risk that this tool should not be auto-trusted.
Potential impact: This finding indicates the tool should be reviewed before it is trusted.
Recommended action: Keep this tool behind manual approval and avoid unattended runs until the risky capabilities are narrowed or removed.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (47)
tool declares network permission
render_slideget_slide_statustranslate_decklist_jobssearch_templatessearch_componentstool declares exec permission
submit_feedbackget_agent_onboardingrender_codeFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
get_agent_onboarding:tool name "get_agent_onboarding" implies read-only operation but declares exec permission
Fix: Ensure tool names, descriptions, and permission declarations are internally consistent. Use explicit naming conventions that fully reflect actual capabilities.
tool declares fs permission
fork_deckupload_fileFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
render_slideget_slide_statustranslate_decklist_jobssearch_templatessearch_componentssubmit_feedbackget_agent_onboardingrender_codeFix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
render_slidegenerate_slideiterate_slideget_slide_statusgenerate_decktranslate_decklist_jobslist_themeslist_templatessearch_templateslist_componentssearch_componentsrender_specsuggest_layoutget_usageget_capabilitiessubmit_feedbacksuggest_templateassemble_deckfork_deckget_meconsulting_deckget_agent_onboardingupload_filerender_preflightrender_codeFix: Review and remediate the identified issue.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y smartdatabrokers-slideforge"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)