GAM MCP Server
Enables Google Workspace administration (Directory, Gmail, Drive, Sheets) via MCP using Domain-Wide Delegation for secure, schema-validated tool operations.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
undeadindustries
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
gam_admin_create_userCreates a new user account in the Google Workspace directory. If `password` is omitted on a non-dry-run, a secure random password is generated and returned ONCE in the response.
gam_admin_update_ouMoves a user to a different OU or re-parents an OU. The caller MUST set `targetType` explicitly.
gam_admin_sync_group_membersSynchronizes a Google Group's membership against a target list, adding/removing concurrently.
gam_admin_print_usersLists user profiles, paginating until exhaustion (capped at MAX_PAGES_LIMIT pages).
gam_admin_print_groupsLists groups, paginating until exhaustion (capped at MAX_PAGES_LIMIT pages).
gam_admin_print_group_membersLists active members of a group, paginating until exhaustion.
gam_gmail_search_messagesSearches a mailbox and returns metadata + snippets. The mailbox owner (`userEmail`) is the DWD impersonation subject.
gam_gmail_get_messageFetches details of a single email including recursively decoded body content.
gam_gmail_bulk_deletePurges emails matching a query in bulk. Defaults to dry-run with samples.
gam_drive_list_filesLists Drive file metadata matching a server-side query.
gam_drive_audit_permissionsMemory-safe Drive permissions audit. Streams results to a local file under GAM_MCP_OUTPUT_DIR (or cwd if unset).
gam_export_audit_to_sheetsStreams a local CSV audit to a Google Sheet tab in safe 2000-row chunks. CSV path must live under GAM_MCP_OUTPUT_DIR.
gam_read_admin_sheetReads a worksheet range to feed administrative execution scripts.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
GAM_MCP_CONFIGPath to a config file (same format as --config).GAM_MCP_CREDENTIALSPath to the service-account JSON key.GAM_MCP_DRY_RUNGAM_MCP_ENVStructured Logging: A stderr-only logger emits human-readable text in test mode and single-line JSON in prod mode (set via NODE_ENV or ). Log level is gated via --log-level / GAM_MCP_LOG_LEVEL.GAM_MCP_LOG_LEVELStructured Logging: A stderr-only logger emits human-readable text in test mode and single-line JSON in prod mode (set via NODE_ENV or GAM_MCP_ENV). Log level is gated via --log-level / .GAM_MCP_OUTPUT_DIRPath Allowlist: All tool I/O paths (audit outputs, CSV imports) are resolved under (or cwd if unset). Paths that escape the root are rejected, as are any paths whose ancestry contains a symlink.GAM_MCP_READ_ONLY1/true/yes to enable read-only mode.GOOGLE_APPLICATION_CREDENTIALSSame, but standard GCP env var.Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
13/13 tools missing one or more hints — gam_admin_create_user (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); gam_admin_update_ou (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); gam_admin_sync_group_members (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +10 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tests exist
No test files found
Add tests that exercise each declared tool.
Shell command execution
1 child_process call — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
0 critical, 2 high severity in production deps — @modelcontextprotocol/sdk@1.4.1 (high), @modelcontextprotocol/sdk@1.4.1 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/undeadindustries/gam-mcp)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check