mcp-server-steam-backlog@0.1.0
CAUTION· not startedPublisher claims: "Enables MCP clients such as Claude to search and filter a Steam library, get explained Deck-friendly picks, and triage games into lanes, edit notes, reorder Up next, and refresh the library through a self-hosted Steam Backlog Triage dashboard." 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: Caution 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
GH_TOKENGITHUB_TOKENor--insecure-no-authConfiguration, not credentials: BACKLOG_DEBUG, BACKLOG_DRY_RUN, BACKLOG_LOG_UNREDACTED, GITHUB_ACTIONS- Where it talks to
- no vendor host named in the codeAlso githubusercontent.com, steampowered.com — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- 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 githubusercontent.com, steampowered.com as well as its own vendor. The guard injects GH_TOKEN, GITHUB_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.
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 2026-11-10 and scored it 77/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
out = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."GET http://10.0.0.5/api?volume=3&API_KEY=***&apikey=***#frag",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.assert mask_url("http://192.0.2.50:8480/") == "http://x.x.x.50:8480/"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.mcp: MCPServer, cfg: HttpConfig, *, health_check: HealthChecker | None = NoneFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.subprocess.run(["git", "-C", str(dest), "checkout", "-q", "FETCH_HEAD"], check=True, timeout=30)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.("http://127.0.0.1:[email protected]", "http://127.0.0.1:[email protected]"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.mkdir -p /home/steam && chmod 700 /home/steamFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.url_with_query = "http://192.0.2.50:8480/api/v1?device=tv#section"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.MCP server SDNick484/mcp-server-steam-backlog on Glama, built from https://github.com/SDNick484/mcp-server-steam-backlog.Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.out = subprocess.run([node, "-e", script, json.dumps(TAG_KEY_CASES)], capture_output=True, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "init", "-q", str(dest)], check=True, timeout=30)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.RUN pip install --no-cache-dir /wheels/*.whl && rm -rf /wheelsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.out = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.assert mask_url("http://192.0.2.5:abc/") == "http://x.x.x.5:abc/"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.url_with_query = "http://192.0.2.50:8480/api/v1?device=tv#section"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.assert mask_url("http://192.0.2.50:8480/") == "http://x.x.x.50:8480/"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.subprocess.check_output(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.ENTRYPOINT ["mcp-server-steam-backlog", "serve", "--http"]Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them."GET http://10.0.0.5/api?volume=3&API_KEY=abc&apikey=def#frag",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.# .env / shell style; names that aren't secrets stayFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.mcp-server-steam-backlog doctor [--json] | simulate [--api 1|2] | call <tool> k=v [--dry-run] | serve [--http]Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.assert mask_url("http://192.0.2.5:abc/") == "http://x.x.x.5:abc/"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.help_text = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.assert "192.0.2.10:*" in lan.allowed_hosts and "http://192.0.2.10:*" in lan.allowed_originsFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."\uff33\uff4f\uff55\uff4c\uff53\u2010\uff4c\uff49\uff4b\uff45", "Caf\u00e9", "", "+",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.# Shell/.env style, as a sibling might log its environment at debug: MQTT_PASSWORD=..., CF_ACCESS_AUD stays.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.for pkg in ("mcp-server-steam-backlog", "mcp", "httpx"):Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.proc = subprocess.Popen(cmd, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.MQTT_PASSWORD=hunter2 -> MQTT_PASSWORD=*** (.env / shell style)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.("http://127.0.0.1:8000#frag@section", "http://127.0.0.1:8000#frag@section"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.assert "192.0.2.10:*" in lan.allowed_hosts and "http://192.0.2.10:*" in lan.allowed_originsFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.assert mask_url("http://user:[email protected]:8480/") == "http://user:[email protected]:8480/"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.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
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
3 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim sdnick484: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- URL using a raw public IP address≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
- MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
- URL with embedded credentials≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.