Skills/PyPI/trialmatch-mcp-bridge

trialmatch-mcp-bridge@0.1.18

VERIFIED· not started

Publisher claims: "Local stdio<->HTTPS bridge for Claude Desktop, per THI-882. Auth + relay only — no tool logic; the real MCP server lives in ../src/trialmatch_criteria_mcp, deployed to AgentCore Runtime behind the Gateway this bridge talks to." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher pypi · publishing for 728 daysInstalls 174Last detonated 1 h ago
$claude mcp add trialmatch-mcp-bridge -- uvx trialmatch-mcp-bridge
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
no credential variables read in the code
Where it talks to
no vendor host named in the code
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 under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- uvx trialmatch-mcp-bridge

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 85/100 (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
Process kill commandtests/test_relay.py:366 · Process kill command — agent can terminate processeswatched only the immediate parent, so it could never fire. The kill happens right after theFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_relay.py:369 · Python subprocess execution detectedtop = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/test_settings.py:170 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# vars by default) -- e.g. a .env template, a container env-file, or an MCP host config's ownFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/test_relay.py:317 · Python subprocess execution detectedmiddle = subprocess.Popen([sys.executable, "-c", sys.argv[1], sys.argv[2], sys.argv[3]])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_relay.py:326 · Python subprocess execution detectedleaf = subprocess.Popen([sys.executable, "-c", sys.argv[1], sys.argv[2]])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_relay.py:394 · 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
Process kill commandsrc/trialmatch_mcp_bridge/ancestry.py:78 · Process kill command — agent can terminate processesdisappearance as "this connection is stale" would kill healthy bridges while Claude is stillFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_wmi_workaround.py:16 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/trialmatch_mcp_bridge/relay.py:113 · Process kill command — agent can terminate processes(`uvx.exe`) does not kill its descendants. The first version of this watchdog only checkedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/trialmatch_mcp_bridge/settings.py:151 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files`.env` template, a container/orchestrator env-file, or an MCP host config's ownFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandtests/test_relay.py:240 · Process kill command — agent can terminate processesrestarts without touching them -- watching it would kill healthy bridges on an ExplorerFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_relay.py:418 · Python subprocess execution detectedtop = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈98 tok
1 file · 23 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.