Skills/PyPI/uc-mcp-proxy

uc-mcp-proxy@0.6.0

VERIFIED· not started

Publisher claims: "MCP stdio-to-Streamable-HTTP proxy with Databricks OAuth" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher icerhymers · publishing for 262 daysInstalls 4,638Last detonated 22 min ago
$claude mcp add uc-mcp-proxy -- uvx uc-mcp-proxy
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
DATABRICKS_TOKENConfiguration, not credentials: DATABRICKS_CONFIG_FILE, DATABRICKS_CONFIG_PROFILE, DATABRICKS_HOST
Where it talks to
no vendor host named in the codeAlso databricks.com — 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 databricks.com as well as its own vendor. The guard injects DATABRICKS_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx uc-mcp-proxy

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 84/100 (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

MEDIUM
Python subprocess execution detectedscripts/probe_token_exchange.py:90 · Python subprocess execution detectedresult = subprocess.run(command, capture_output=True, text=True, timeout=60)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Hidden zero-width characters detectedtests/unit/test_http_errors.py:869 · Hidden zero-width characters detected — may conceal contentresult = scrub_body("safe ‮ evil ⁦x⁩ ​  end", [])Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Hidden zero-width characters detectedtests/unit/test_http_errors.py:871 · Hidden zero-width characters detected — may conceal contentfor char in ("‮", "⁦", "⁩", "​", ""):Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
URL with embedded credentialstests/unit/test_token_exchange.py:683 · URL with embedded credentials — may be phishing or credential leakingmake_config(host="https://someone:[email protected]"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
URL with embedded credentialstests/unit/test_token_exchange.py:673 · URL with embedded credentials — may be phishing or credential leakingA ``https://user:password@host`` profile entry would otherwise put thatFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Bidirectional text override characters detectedtests/unit/test_http_errors.py:823 · Bidirectional text override characters detected — may hide content direction"bidi_override": "‮",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedtests/unit/test_http_errors_e2e.py:1130 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Bidirectional text override characters detectedtests/unit/test_http_errors.py:871 · Bidirectional text override characters detected — may hide content directionfor char in ("‮", "⁦", "⁩", "​", ""):Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Authorization escalation languageCLAUDE.md:52 · Authorization escalation languageand `SessionMessage.message` (no longer wrapped in a `JSONRPCMessage` rootFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
URL with embedded credentialssrc/uc_mcp_proxy/token_exchange.py:351 · URL with embedded credentials — may be phishing or credential leaking# so a ``https://user:password@host`` entry would otherwise put thatFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Hidden zero-width characters detectedtests/unit/test_http_errors.py:822 · Hidden zero-width characters detected — may conceal content"zero_width_space": "​",Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Bidirectional text override characters detectedtests/unit/test_http_errors.py:869 · Bidirectional text override characters detected — may hide content directionresult = scrub_body("safe ‮ evil ⁦x⁩ ​  end", [])Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07

Cost to the agent

Instructions loaded
≈4,548 tok
2 files · 43 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

No advisories in OSV for uc-mcp-proxy@0.6.0 as of 10 min ago. This is the package itself, not its dependencies.

uc-mcp-proxy@0.6.0 safety verdict: Verified (not started) — KillerSkills