Skills/PyPI/ms-graph-mcp

ms-graph-mcp@0.3.0

CAUTION· not started

Publisher claims: "Microsoft Graph MCP server — 85 tools across mail, calendar, meetings, Teams chat, files, search, people, directory, tasks and OneNote, over stdio or Streamable HTTP." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher nitin27may · publishing for 101 daysInstalls 248Last detonated 3d ago
What would fix thisWatchDispute verdict

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
GRAPH_MCP_ACCESS_TOKENConfiguration, not credentials: DISPLAY, GRAPH_MCP_CACHE_DIR, GRAPH_MCP_FORCE_DEVICE_CODE, GRAPH_MCP_LOG_LEVEL, GRAPH_MCP_PORT, GRAPH_MCP_USER_EMAIL, GRAPH_MCP_WRITE_SCOPE, SSH_CONNECTION, SSH_TTY
Where it talks to
no vendor host named in the codeAlso microsoft.com, microsoftonline.com, windows.net — 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 microsoft.com, microsoftonline.com, windows.net as well as its own vendor. The guard injects GRAPH_MCP_ACCESS_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx ms-graph-mcp

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 2026-11-12 and scored it 79/100 (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; 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 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
Access to sensitive file pathstests/test_odata.py:39 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesvalidate_graph_id("../../etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/ms_graph_mcp/config.py:34 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_file=".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_odata.py:62 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesvalidate_mail_folder("../../etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandDockerfile:93 · Process kill command — agent can terminate processes# through a shell that would swallow it and force a 10-second kill on everyFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedDockerfile:62 · Destructive file system command detected&& rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/check_docs.py:164 · Python subprocess execution detectedout = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/ms_graph_mcp/entra/config.py:29 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_file=("../.env.local", ".env"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/ms_graph_mcp/config.py:12 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesA ``.env`` file in the working directory is loaded if present.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)src/ms_graph_mcp/app.py:125 · MCP server using network transport (SSE/HTTP) — data sent over networkapplication = mcp_server.streamable_http_app(Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
File type combined with upload actionsrc/ms_graph_mcp/email.py:337 · File type combined with upload action — agent may exfiltrate local data files# resp.json() cannot be used — graph_post_no_content exists for exactly thisFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈3,386 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

No advisories in OSV for ms-graph-mcp@0.3.0 as of 3d ago. This is the package itself, not its dependencies.

What would make this Verified

1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim nitin27may: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. 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.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim nitin27mayPropose a patch to the maintainer