outlook-graph-mcp@1.31.4
VERIFIED· not startedPublisher claims: "MCP server for Microsoft Outlook via Microsoft Graph API" 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 codeAlso microsoft.com, evil.example — 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 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 2026-11-14 and scored it 83/100 (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
2. **Config-gated toolsets** — the full tool schemas cost chars/4 proxy tokensFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# feature here (~1.2k proxy tokens, ~8% of the default surface — mostlyFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# re-fetching ~13k chars/4 proxy tokens of schemas. The set is fixed at import —Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Ours to lock down. Never chmod a directory the user pointed us at.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.# has marked read-only used to have that attribute cleared here — chmod on Windows doesFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.# feature here (~1.2k proxy tokens, mostly `create_rule`'s argument list), andFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.def serve(server: MCPServer, settings: HttpSettings) -> None:Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.# The 0o700 directory and 0o600 file modes below are POSIX-only. On Windows os.chmod can setFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.# POSIX-only: on Windows os.chmod sets nothing but the read-only attribute, so thisFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.def build_app(server: MCPServer, settings: HttpSettings) -> ASGIApp:Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.def uvicorn_config(server: MCPServer, settings: HttpSettings) -> uvicorn.Config:Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.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
No advisories in OSV for outlook-graph-mcp@1.31.4 as of 7 h ago. This is the package itself, not its dependencies.