Skills/PyPI/uns-mcp

uns-mcp@0.1.8

VERIFIED· not started

Publisher claims: "MCP server implementation providing structured tools for interacting with the Unstructured API, managing sources, destinations, workflows, and jobs" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher pypi · publishing for 729 daysInstalls 183Last detonated 22 min ago
$claude mcp add uns-mcp -- uvx uns-mcp
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
ASTRA_DB_APPLICATION_TOKENAWS_SECRETAZURE_CONNECTION_STRINGAZURE_SAS_TOKENDATABRICKS_CLIENT_SECRETFIRECRAWL_API_KEYMONGO_DB_CONNECTION_STRINGNEO4J_PASSWORDPINECONE_API_KEYSALESFORCE_PRIVATE_KEYTOKENUNSTRUCTURED_API_KEYWEAVIATE_CLOUD_API_KEYConfiguration, not credentials: ASTRA_DB_API_ENDPOINT, AWS_KEY, AZURE_ACCOUNT_KEY, AZURE_ACCOUNT_NAME, DATABRICKS_CLIENT_ID, DEBUG_API_REQUESTS, ENDPOINT_URL, GOOGLEDRIVE_SERVICE_ACCOUNT_KEY, MCP_SERVER_URL, NEO4J_USERNAME, ONEDRIVE_CLIENT_CRED, ONEDRIVE_CLIENT_ID, ONEDRIVE_TENANT_ID, SALESFORCE_CONSUMER_KEY, SHAREPOINT_CLIENT_CRED, SHAREPOINT_CLIENT_ID, SHAREPOINT_TENANT_ID
Where it talks to
no vendor host named in the codeAlso microsoftonline.com, unstructured.io — not the publisher's domain; check what for before connecting.
What we saw when it ran
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names microsoftonline.com, unstructured.io as well as its own vendor. The guard injects ASTRA_DB_APPLICATION_TOKEN, AWS_SECRET, AZURE_CONNECTION_STRING, AZURE_SAS_TOKEN, DATABRICKS_CLIENT_SECRET, FIRECRAWL_API_KEY, MONGO_DB_CONNECTION_STRING, NEO4J_PASSWORD, PINECONE_API_KEY, SALESFORCE_PRIVATE_KEY, TOKEN, UNSTRUCTURED_API_KEY, WEAVIATE_CLOUD_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx uns-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-20 and scored it 83/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

HIGH
Collapsed <details> block carrying instructionsREADME.md:195 · Collapsed <details> block carrying instructions<summary> Using SSE Server Protocol </summary> **Note: Not supported by Claude Desktop.** For SSE protocol, you can debug more easily by decoupling the client aFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:220 · Collapsed <details> block carrying instructions<summary> Using Stdio Server Protocol </summary> Configure Claude Desktop to use stdio: ```json { "mcpServers": { "UNS_MCP": { "command": "ABSOLUTE/PATH/TO/.locFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsuns_mcp/server.py:58 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesLoad environment variables from .env file.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)example_clients/crew_ai_agent.py:62 · MCP server using network transport (SSE/HTTP) — data sent over network{"url": os.getenv("MCP_SERVER_URL", "http://127.0.0.1:8080/sse")},Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
HIGH
Access to sensitive file pathsexample_clients/crew_ai_agent.py:16 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files1. Configure UNSTRUCTURED_API_KEY, ANTHROPIC_API_KEY, AWS_KEY, AWS_SECRET keys in .env fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈71 tok
1 file · 37 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.