trialmatch-mcp-bridge@0.1.18
VERIFIED· not startedPublisher 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.
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.
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 deviationsStatic findings
watched 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.top = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# 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.middle = 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.leaf = 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.proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.disappearance 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.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.(`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.`.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.restarts 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.top = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
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.