Skills/npm/ms-365-mcp-server

ms-365-mcp-server@0.186.0

VERIFIED· not started

Publisher claims: " A Model Context Protocol (MCP) server for interacting with Microsoft 365 and Office services through the Graph API" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher softeria · publishing for 593 daysInstalls 321KLast detonated 48 min ago
$claude mcp add ms-365-mcp-server -- npx -y @softeria/ms-365-mcp-server
WatchReport an issue

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
MS365_MCP_ALLOW_UNAUTHENTICATED_DISCOVERYMS365_MCP_CLIENT_SECRETMS365_MCP_FEDERATED_TOKEN_FILEMS365_MCP_OAUTH_TOKENMS365_MCP_PKCE_SECRETMS365_MCP_TOKEN_CACHE_PATHMS365_MCP_TRUST_PROXY_AUTHPKCE_SECRET_MIN_LENGTH or --trust-proxy-auth / --enable-auth-tools / --allow-unauthenticated-discoveryConfiguration, not credentials: CACHE_KEY_BYTES, ENABLED_TOOLS, ENABLED_TOOLS_FILE, MS365_MCP_ALLOW_PAGINATION, MS365_MCP_ALLOWED_REDIRECT_URIS, MS365_MCP_ALLOWED_SCOPES, MS365_MCP_APP_MODE, MS365_MCP_ATTACHMENT_HOST, MS365_MCP_ATTACHMENT_PORT, MS365_MCP_ATTACHMENT_URL_BASE, MS365_MCP_ATTACHMENT_URL_KEY, MS365_MCP_ATTACHMENT_URL_KEY_FILE, MS365_MCP_ATTACHMENT_URL_KEY_ID, MS365_MCP_ATTACHMENT_URL_TTL_S, MS365_MCP_AUDIT_LOG, MS365_MCP_BASE_URL, MS365_MCP_BLOB_MAX_BYTES, MS365_MCP_BLOB_OUTPUT, MS365_MCP_BODY_FORMAT, MS365_MCP_CLIENT_CERTIFICATE_PATH, MS365_MCP_CLIENT_ID, MS365_MCP_CLOUD_TYPE, MS365_MCP_CORS_ORIGIN, MS365_MCP_EAGER_TOOLS, MS365_MCP_ENABLE_MCP_APPS, MS365_MCP_EXPECTED_HOME_ACCOUNT_ID, MS365_MCP_EXPECTED_USERNAME, MS365_MCP_EXTRA_SCOPES, MS365_MCP_FORCE_WORK_SCOPES, MS365_MCP_GRAPH_CIRCUIT_DISABLED, MS365_MCP_HTTP_LOCAL_FILE_TOOLS, MS365_MCP_KEYVAULT_URL
Where it talks to
no vendor host named in the codeAlso microsoft.com, githubusercontent.com, microsoftonline.com, azure.com, chinacloudapi.cn, azure.cn, microsoftonline.us, microsoft.us, azure.us, graph.invalid — 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, githubusercontent.com, microsoftonline.com, azure.com, chinacloudapi.cn, azure.cn, microsoftonline.us, microsoft.us, azure.us, graph.invalid as well as its own vendor. The guard injects MS365_MCP_ALLOW_UNAUTHENTICATED_DISCOVERY, MS365_MCP_CLIENT_SECRET, MS365_MCP_FEDERATED_TOKEN_FILE, MS365_MCP_OAUTH_TOKEN, MS365_MCP_PKCE_SECRET, MS365_MCP_TOKEN_CACHE_PATH, MS365_MCP_TRUST_PROXY_AUTH, PKCE_SECRET_MIN_LENGTH only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- npx -y @softeria/ms-365-mcp-server

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 0.185.1

vet-skills diff ms-365-mcp-server 0.185.1 0.186.0

In the sandbox, this version reached for nothing 0.185.1 did not. Compared from the two recorded runs, not from source.

0.185.1 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 2026-11-17 and scored it 80/100 (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 · 22 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
22sprocessdependency install exit 1 · (Use `node --trace-warnings ...` to show where the warning was created) npm error Cannot read properties of null (reading 'edgesOut') npm error A complete log of this run can be found in: /tmp/ks-detonate-heQH51/task/home/.npm/_logs/2026-11-17T21_51_57_607Z-debug-0.log
22sclaimednot started: dependency install failed (exit 1); the server itself was not observed
22sprocessscript backend runs setup only
22sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actiondist/__tests__/graph-tools.test.js:2336 · File type combined with upload action — agent may exfiltrate local data filesit("honors endpoints.json contentType override on binary uploads", async () => {Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Unicode escape sequence detecteddist/lib/attachment-url-config.js:11 · Unicode escape sequence detected — may contain obfuscated payloadsconst PYTHON_WHITESPACE = " \n\v\f\r \x85\xA0\u1680\u2000\u2001\u2002\u2003\u2004\u2005\u2006\u2007\u2008\u2009\u200A\u2028\u2029\u202F\u205F\u3000";Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Access to sensitive file pathsdist/load-env.js:22 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst file = options.path ?? path.resolve(process.cwd(), ".env");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Destructive file system command detectedbin/modules/simplified-openapi.mjs:24 · Destructive file system command detected// Microsoft's published OpenAPI metadata (e.g. range(address='{address}')/formatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagebin/modules/generate-mcp-tools.mjs:52 · npx invocation of non-well-known package — may execute untrusted code`npx -y openapi-zod-client "${openapiTrimmedFile}" -o "${clientFilePath}" --with-description --strict-objects --additional-props-default-value=false`,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Unicode escape sequence detecteddist/lib/mail-text.js:235 · Unicode escape sequence detected — may contain obfuscated payloads…u05D1\u05E8\u05D4|\u0625\u0639\u0627\u062F\u0629 \u062A\u0648\u062C\u064A\u0647|\u0BAE\u0BC1\u0BA9\u0BCD\u0BA9\u0BA9\u0BC1\u0BAA\u0BCD\u0BAA\u0BC1)\\s*[:\uFF1A]", "iu" ); function isForwardSubject(subject) { return FORWARD…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Access to sensitive file pathsdist/app-mode.js:139 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filessecrets.clientSecret && "a client secret (MS365_MCP_CLIENT_SECRET, .env or Key Vault)",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 pathsdist/load-env.js:47 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…console.error( `[ms365-mcp] Ignored ${ignoredOwn.length} variable(s) from .env: ${[...ignoredOwn].sort().join(", ")}. Only ${ENV_FILE_ALLOWLIST.join(", ")} ar…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionbin/modules/generate-mcp-tools.mjs:48 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Created directory: ${outputDir}`);Fix: 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
≈71 tok
1 file · 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

Not checked against OSV yet; the weekly check has not reached this version.