dial-pptx-mcp (photonn/dial-pptx-mcp) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 38 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Caution
74/100

dial-pptx-mcp

DIAL-aware remote MCP server for PowerPoint generation — extends GongRzhe/Office-PowerPoint-MCP-Server with streamable-http transport, per-session state, and DIAL Core file storage integration

→ photonn/dial-pptx-mcp· listed on glama

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

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

photonn

Source: Glama · also listed on github_code

Is this your MCP?

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 →

⚡ Connect GitHub for Live Monitored

Install from

Glamanot scored hereGitHub

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.

// key findings
✅
38 tools verified — handlers match their declared behaviour
9 read-only tools verified — handlers contain no write/delete/exec
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
✅
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 2 credentials: DIAL_API_KEY, VISION_LLM_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configPPT_TEMPLATE_PATHno — Extra local directories searched by the local-path template tools (:-separated)
configPPT_MCP_ALLOWED_HOSTS
configPPT_MCP_TRANSPORTno stdio http (streamable-http, recommended for DIAL), sse, or stdio
configPPT_MCP_PORTno 8000 Listen port for http/sse
configPPT_MCP_HOSTno 127.0.0.1 Bind address; set 0.0.0.0 in containers (the Dockerfile does)
configVISUAL_QA_EXPOSE_TOOL
configDIAL_AUTH_MODE
🔐 secretDIAL_API_KEYno — Server's own DIAL API key — the fallback identity in auto mode, the only identity in server mode
configDIAL_CORE_URLfor DIAL export — Base URL of DIAL Core, e.g. https://dial.example.com. Unset → DIAL upload/download tools return a clear error; local-path tools still work
configDIAL_UPLOAD_FOLDERno pptx-mcp Folder inside the bucket for exported decks
configPPT_MCP_STATE_TTL_SECONDSno 3600 Idle time before an in-memory presentation expires
configPPT_MCP_STATE_MAX_PRESENTATIONSno 50 Max concurrently held presentations (LRU eviction)
configSOFFICE_PATHno soffice on PATH LibreOffice binary used to render slides (the Docker image includes LibreOffice)
configVISION_LLM_PROVIDERno auto Force the backend: direct or dial (default: direct when VISION_LLM_ENDPOINT is set, else dial)
configVISION_LLM_ENDPOINTVISION_LLM_PROVIDER no auto Force the backend: direct or dial (default: direct when is set, else dial)
configVISION_LLM_MODELfor visual QA — Vision model: the model name (direct endpoint) or the DIAL deployment name (DIAL provider); must accept image input
🔐 secretVISION_LLM_API_KEYdirect provider — Key for the direct endpoint (sent as api-key and Authorization: Bearer)
configVISION_LLM_API_VERSIONno — Optional ?api-version= for the DIAL-routed call
configVISUAL_QA_ON_UNRESOLVED
configVISUAL_QA_ON_ERROR
configVISION_LLM_MAX_SLIDESno 15 Cap on slides sent per inspection
configVISUAL_QA_MAX_ITERATIONS3. The deck is re-rendered and re-inspected; the loop repeats up to (default 10) inspections, stopping early if no repair makes progress.
// quality suggestions

Tool annotations

10/38 tools have annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

38/38 tools missing one or more hints — get_server_info (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); update_chart_data (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); add_connector (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +35 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.

Destructive tools are labelled

1 tool perform destructive updates without destructiveHint — manage_image deletes at line 562 (os.unlink(temp_path))

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Tool test coverage

Only 5/38 tools referenced in tests (13%)

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.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/photonn/dial-pptx-mcp?variant=verified)](https://m8ven.ai/mcp/photonn/dial-pptx-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 1222c6db46f3790228e984beeddc6ded566aba50
code hash: b860c17234ed12f3924746b8c9ab0ae023a62e98ce5ad85ef90c14d3fde7fb67
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

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
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client