doc-graph (markus7h/doc-graph) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 12 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Emerging
74/100

doc-graph

→ markus7h/doc-graph· listed on github_code

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

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

markus7h

Source: 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

GitHub

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
✅
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: LLM_API_KEY, PAPERLESS_TOKEN
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.
configLLM_BASE_URLSetup /EMBED_BASE_URL bzw.
configEMBED_BASE_URLSetup LLM_BASE_URL/ bzw.
🔐 secretLLM_API_KEYDer Router braucht (Master-Key) — server.py schickt ihn im LLM-
configLLM_MODELdelete_project + erneuter Ingest mit geändertem .
configEMBED_MODEL
configEMBED_DIMdarf sich nachträglich nicht ändern — Embedding-Modell pro
configMAX_ASYNCLightRAGs Chunk-Parallelität () auch bei vielen kleinen Docs aus;
configEMBED_MAX_ASYNC6144 Zeichen = 100 s für einen einzigen Request, mal
configEMBED_TIMEOUTparallel deutlich über . Der Server bricht dann die Verbindung
configEMBED_MAX_TOKENS(default 1800): Obergrenze pro Embedding-Input, muss
configINGEST_IGNORE_TAGS(default paperless-ai): Paperless-Tags, die nicht
configEMBED_BATCH(default 64): Obergrenze für die Anzahl Inputs pro
configLLM_TIMEOUT(default 480 s): Timeout je einzelnem LLM-Call. Bei CPU-Offload/
configCHUNK_TOKEN_SIZE(, default 1200 Token). Gemessen 2026-08-20 auf dem
configINGEST_BATCHnach dem aktuellen Batch ( Docs, default 5 — ein Batch wird
configPDFTOTEXT_TIMEOUT(default 120 s): Deckel je pdftotext-Aufruf beim
configMAX_DOC_CHARS(default 300000 ≈ 125 Chunks): Sicherheits-Guard beim
configMAX_DOC_ATTEMPTS(default 3, 0 schaltet ab): Failure-Deckel.
configQUERY_MAX_TOKENS(default 12000): globaler Default für das Kontext-Budget je
configGRAPH_LANGUAGE(default German): Sprache der extrahierten Entitäten/
configGRAPH_MAX_NODESEndpoint GET /<project_id>/nodes — serverseitig auf
configPAPERLESS_URL
🔐 secretPAPERLESS_TOKEN
configMCP_PORTIPv4-Port. Der MCP-Port () ist davon nicht betroffen.
configVIEWER_PORTViewers (Port ) unter ihrer Projekt-Karte mit Buttons. Pro Doc gilt
configPUBLIC_HOST
configINGEST_SWAPAbschaltbar via =0 (z. B. lokale Dev-Umgebung).
configMAX_RESTORE_UPLOAD
configPROJECTS_DIRjede mit eigenem workspace=<project> (Store unter /<project>/).
configBACKUP_DIR
configMAX_BACKUPSRotation je Projekt auf die letzten (Default 10) — ältere gelöscht.
// quality suggestions

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

12/12 tools missing one or more hints — list_projects (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); query (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ingest_paperless (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +9 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

4/12 tools referenced in tests (33%)

Write tests that reference each tool by name so every tool has at least one test.

Secrets not logged

2 secret values sent to log.info/log.warning

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.

// 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 Score](https://m8ven.ai/badge/mcp/markus7h/doc-graph)](https://m8ven.ai/mcp/markus7h/doc-graph)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 98d5471d22205cb615cd7418786d2d122f1b3fec
code hash: 96fb57709d3cbb1c0e2ebb13c504ef695bbb01f48a095dd0dd1966c30fff46bb
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