Skills/Glama/dine-mcp

dine-mcp@0.3.0

VERIFIED· not started

Publisher claims: "Enables MCP clients, the command line, and Python to find restaurants and check read-only table availability across SevenRooms, TableCheck, ResDiary, and other booking systems. It returns provider booking links and prefilled pages without booking, holding, or cancelling tables." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher benjamin-di · publishing for 24 daysInstalls 0Last detonated 3d ago
$npx skills add dine-mcp
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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
MCP_BEARER_TOKENConfiguration, not credentials: DINE_EXPECTED_PROVIDER_KEYS, DINE_EXPECTED_SURFACE, DINE_HOST, DINE_PORT, DINE_SMOKE_STATE, DINE_STATE_DIR
Where it talks to
no vendor host named in the codeAlso formitable.com, zenchef.com, example.invalid, catchtable.co.kr, resdiary.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 formitable.com, zenchef.com, example.invalid, catchtable.co.kr, resdiary.com as well as its own vendor. The guard injects MCP_BEARER_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- <the server's command>

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 (3 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-12 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 · 3 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessexec /usr/bin/dirname
0.0sprocessexited 127: ./scripts/bootstrap.sh: line 5: uv: command not found
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocesssecond launch, clock +45 days, CI unset
0.2sprocessexec /usr/bin/dirname
0.2sprocessexited 127: ./scripts/bootstrap.sh: line 5: uv: command not found

Static findings

MEDIUM
Python subprocess execution detectedscripts/smoke.py:87 · Python subprocess execution detectedinvalid = subprocess.run(["dine-mcp", "--port", "invalid"], capture_output=True, text=True, timeout=15)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionscripts/qualify-protocol.py:34 · File type combined with upload action — agent may exfiltrate local data files(reports / f"{name}.log").write_bytes(output)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)SKILL.md:5 · MCP server using network transport (SSE/HTTP) — data sent over networkMCP server benjamin-di/dine-mcp-server on Glama, built from https://github.com/benjamin-di/dine-mcp-server.Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Destructive file system command detectedDockerfile:32 · Destructive file system command detected&& rm -rf /app/src /tmp/embed-build-identity.pyFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedDockerfile:18 · Destructive file system command detected&& rm -f /tmp/requirements-runtime.lock \Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/source-identity.py:17 · Python subprocess execution detectedreturn subprocess.check_output(["git", *args], cwd=root)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedevals/run.py:61 · Python subprocess execution detectedproc = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Destructive file system command detectedDockerfile:10 · Destructive file system command detectedRUN python /tmp/runtime-installer.py && rm /tmp/runtime-installer.pyFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandDockerfile:36 · File permission modification command — agent changes file ownership/permissionsRUN mkdir -p /state && chown 1000:1000 /stateFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedscripts/smoke.py:85 · Python subprocess execution detectedhelp_result = subprocess.run(["dine-mcp", "find", "--help"], capture_output=True, text=True, timeout=15)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈508 tok
2 files · 81 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

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.