Back to MCP Trust Indexm8ven
C
Emerging
74/100
8 days ago

UNS-MCP

An MCP server implementation that allows interaction with the Unstructured API, providing tools to list, create, update, and manage document processing sources, destinations, and workflows.

→ unstructured-io/uns-mcp· listed on modelscope

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

unstructured-io

Source: modelscope

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

modelscope

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
🔐
You'll be asked for 15 credentials: UNSTRUCTURED_API_KEY, ASTRA_DB_APPLICATION_TOKEN, DATABRICKS_CLIENT_SECRET, NEO4J_PASSWORD, PINECONE_API_KEY, AWS_KEY, AWS_SECRET, TOKEN, WEAVIATE_CLOUD_API_KEY, FIRECRAWL_API_KEY, AZURE_ACCOUNT_KEY, AZURE_SAS_TOKEN, GOOGLEDRIVE_SERVICE_ACCOUNT_KEY, SALESFORCE_CONSUMER_KEY, SALESFORCE_PRIVATE_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.
🔐 secretUNSTRUCTURED_API_KEY"": "<your-key>"
configLOG_LEVELUsed to set logging level for our minimal_client, e.g. set to ERROR to get everything
configCONFIRM_TOOL_USEset to true so that minimal_client can confirm execution before each tool call
🔐 secretASTRA_DB_APPLICATION_TOKEN, ASTRA_DB_API_ENDPOINT required to create Astradb connector via uns-mcp server, see how in [documentation](https://docs.unstructured.io/ui/destinations/astradb)
configASTRA_DB_API_ENDPOINTASTRA_DB_APPLICATION_TOKEN, required to create Astradb connector via uns-mcp server, see how in [documentation](https://docs.unstructured.io/ui/destinations/astradb)
configDATABRICKS_CLIENT_ID
🔐 secretDATABRICKS_CLIENT_SECRET
configNEO4J_USERNAME
🔐 secretNEO4J_PASSWORDrequired to create Neo4j connector via uns-mcp server, see how in [documentation](https://docs.unstructured.io/ui/destinations/neo4j)
🔐 secretPINECONE_API_KEYrequired to create Pinecone vector DB connector via uns-mcp server, see how in [documentation](https://docs.unstructured.io/ui/destinations/pinecone)
🔐 secretAWS_KEY
🔐 secretAWS_SECRET
🔐 secretTOKEN
configENDPOINT_URL
🔐 secretWEAVIATE_CLOUD_API_KEYrequired to create Weaviate vector db connector, see how in [documentation](https://docs.unstructured.io/api-reference/workflow/destinations/weaviate)
🔐 secretFIRECRAWL_API_KEYrequired to use Firecrawl tools in external/firecrawl.py, sign up on [Firecrawl](https://www.firecrawl.dev/) and get an API key.
configAZURE_ACCOUNT_NAME
🔐 secretAZURE_ACCOUNT_KEY
🔐 secretAZURE_SAS_TOKEN
🔐 secretGOOGLEDRIVE_SERVICE_ACCOUNT_KEY
configONEDRIVE_CLIENT_CREDONEDRIVE_CLIENT_ID, ,ONEDRIVE_TENANT_ID required to create One Drive connector via uns-mcp server, see how in [documentation](https://docs.unstructured.io/ui/destinations/onedrive)
configONEDRIVE_CLIENT_ID, ONEDRIVE_CLIENT_CRED,ONEDRIVE_TENANT_ID required to create One Drive connector via uns-mcp server, see how in [documentation](https://docs.unstructured.io/ui/destinations/onedrive)
configONEDRIVE_TENANT_IDONEDRIVE_CLIENT_ID, ONEDRIVE_CLIENT_CRED, required to create One Drive connector via uns-mcp server, see how in [documentation](https://docs.unstructured.io/ui/destinations/onedrive)
🔐 secretSALESFORCE_CONSUMER_KEY
🔐 secretSALESFORCE_PRIVATE_KEY
configSHAREPOINT_CLIENT_ID, SHAREPOINT_CLIENT_CRED,SHAREPOINT_TENANT_ID required to create One Drive connector via uns-mcp server, see how in [documentation](https://docs.unstructured.io/ui/sources/sharepoint)
configSHAREPOINT_CLIENT_CREDSHAREPOINT_CLIENT_ID, ,SHAREPOINT_TENANT_ID required to create One Drive connector via uns-mcp server, see how in [documentation](https://docs.unstructured.io/ui/sources/sharepoint)
configSHAREPOINT_TENANT_IDSHAREPOINT_CLIENT_ID, SHAREPOINT_CLIENT_CRED, required to create One Drive connector via uns-mcp server, see how in [documentation](https://docs.unstructured.io/ui/sources/sharepoint)
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployMONGO_DB_CONNECTION_STRING
deployAZURE_CONNECTION_STRING
// 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

25/25 tools missing one or more hints — list_sources (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_source_info (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_destinations (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +22 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.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Tool test coverage

Only 7/25 tools referenced in tests (28%)

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 Score](https://m8ven.ai/badge/mcp/unstructured-io-uns-mcp-1lotmr)](https://m8ven.ai/mcp/unstructured-io-uns-mcp-1lotmr)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: fa52862ec7fc4b028f5506c52afe01eb34a2f85f
code hash: 90fb9b4fac00bfd4e96540a3ccff15ef575e34a245c50a23f5cd77acddfdd3f4
verified: 8/13/2026, 10:04:08 PM
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