google-chat-mcp

google-chat-mcp

Google Chat as MCP tools. Read, search and write to your spaces, DMs and sidebar.

A single Go binary that speaks MCP over stdio. It runs as a subprocess of your client, on your own machine, against your own Google account. There is no server to host, no shared deployment and no service account: you create a Google OAuth client, log in once, and the refresh token stays in your OS keyring. Claude Code, Claude Desktop and any other MCP client can drive it.

Why google-chat-mcp

Chat integrations are normally apps: they post as a bot, see only the spaces somebody added them to, and need a service account an administrator provisions. This one runs as you. It reaches what your account already reaches, and messages you send are from you, not from an app with your name on it.

That also puts the user-scoped half of Chat in reach, which an app identity cannot get to at all: your sidebar sections, how far you have read in a space or a thread, your availability and custom status, and your organization's custom emoji. Fifty-eight tools cover it, most writes take dry_run, and nothing is requested at login beyond the scopes the tools you are actually using need.

Install

go install github.com/mmedum/google-chat-mcp/v8/cmd/google-chat-mcp@latest

Or take a signed archive from the latest release — Linux, macOS and Windows, on amd64 and arm64 — and verify it before you run it:

sha256sum -c checksums.txt --ignore-missing

# The checksum file is signed with a keyless Sigstore certificate tied to
# the release workflow's identity. The bundle carries both.
cosign verify-blob checksums.txt \
  --bundle checksums.txt.bundle \
  --certificate-identity-regexp 'https://github\.com/mmedum/google-chat-mcp/' \
  --certificate-oidc-issuer https://token.actions.githubusercontent.com

# And the archive itself carries build provenance.
gh attestation verify google-chat-mcp_*.tar.gz --repo mmedum/google-chat-mcp

Every archive also ships an SBOM, so you can see what is inside a binary you did not build.

Claude Desktop

Every release also carries a .mcpb bundle. Open it and Claude Desktop installs the server and asks for the settings a config file would carry, with no file to edit: your OAuth client JSON, which may be left empty to use the one login recorded, the profile, read-only, the toolsets and the attachment folder. The tools that cannot be taken back (enable_destructive) stay off unless you turn them on, and so does attachment transfer until you pick a folder. This server asks nobody before a call. Claude Desktop approves each tool, and a tool you always allow then runs unasked, so leave enable_destructive off unless you need its tools.

It covers macOS, Windows and Linux on both architectures each: macOS through a universal binary, Windows through amd64, and Linux through a small launcher that picks the right binary at start, because a bundle manifest has no key for the architecture. Its SHA-256 is in the same signed checksums.txt. The release is listed in the MCP registry as io.github.mmedum/google-chat-mcp.

The bundle does not log you in. Install the binary as well, run google-chat-mcp login once, and the bundle picks up the same credentials. Claude Code does not install .mcpb files, so it uses the command below.

Set up Google

You need your own OAuth client. It takes about fifteen minutes once, and docs/gcp-setup.md walks through it. In short: create a project, enable the Google Chat API, the People API and the Cloud Identity API, configure the consent screen with the scopes this server asks for, and create an OAuth 2.0 Client ID of type Desktop app. Download the JSON.

Then log in:

google-chat-mcp login --client-secret ./client_secret.json

Login opens your browser, or prints the URL when there is no browser to open (--no-browser forces that). The callback lands on 127.0.0.1 on a random port, with PKCE and state throughout. The refresh token goes into your OS keyring; if there is no keyring, it goes into a 0600 file and the command tells you so. On Windows a Go file mode only sets the read-only attribute, so what protects that file there is the ACL its directory inherits, not the mode.

google-chat-mcp status says which account is signed in and where the token lives. google-chat-mcp logout revokes the token at Google and deletes the local copy.

google-chat-mcp status --json prints the same state as one JSON object on stdout, for a script that needs to know whether this server is authorized before starting it. credentials.resolved is the field to branch on, credentials.signed_in distinguishes "no profile yet" from "profile but no token", schema_version changes only when a field is removed or its meaning changes, and the account is masked to its domain exactly as the text output masks it. A label in the human output is free to be reworded in any release; the object is not.

Logging in over SSH

The callback goes to the remote host's loopback address, and your browser is local, so forward the port. It is chosen at random and printed only once login is already waiting, so read it out of the printed URL — it appears percent-encoded, as 127.0.0.1%3A<port> — and in a second local terminal:

ssh -N -L <port>:127.0.0.1:<port> user@remote-host

Then open the URL locally. If ssh reports bind: Address already in use, cancel the login with Ctrl-C and run it again to draw another port.

Connect a client

Claude Code:

claude mcp add google-chat -- google-chat-mcp

Or, in a client config file:

{
  "mcpServers": {
    "google-chat": {
      "command": "google-chat-mcp"
    }
  }
}

Claude Desktop reads the same shape from its own config file. Use the binary's absolute path there if it is not on the app's PATH, or install the .mcpb bundle above and edit nothing.

Every setting is an environment variable, listed in docs/configuration.md. The four worth knowing now: GCM_READ_ONLY=true leaves out every tool that changes anything in Chat, GCM_ENABLE_DESTRUCTIVE=true adds the tools that cannot be taken back, GCM_PROFILE lets one machine hold a work account and a personal one, and GCM_LOCAL_DIR names the one directory files may be written to and read from. Without that last one the server touches no files at all, and the three tools that move them say so.

Tools

Tool	What it does	Scope
whoami	Which account the stored credentials belong to	openid email profile
list_spaces	Spaces, group chats and direct messages you are in	chat.spaces.readonly
get_space	One space by resource name	chat.spaces.readonly
search_spaces	Named spaces you are in, by display name; every space with use_admin_access	chat.spaces.readonly; chat.admin.spaces.readonly for use_admin_access
find_group_chats	The group chats holding exactly you and the people you name	chat.memberships.readonly, chat.spaces.readonly
find_direct_message	The direct message with one person, created if there is none yet	chat.spaces.readonly, chat.spaces.create
get_messages	Recent messages in a space, newest first, senders resolved to names	chat.messages.readonly
get_message	One message, with its reaction counts, what its text links to and what it quotes	chat.messages.readonly
get_thread	Every message in one thread, oldest first	chat.messages.readonly
download_attachment	Save a message's attachment into the server's local directory	chat.messages.readonly
search_messages	Google's search across every space you can see, or a regular-expression scan of one	chat.messages.readonly; chat.users.readstate.readonly for unread_only; chat.spaces.readonly for space_type and space_name
search_people	Turn a name into an email address, from the directory and your contacts	directory.readonly, contacts.readonly
find_group	Turn a Google Group's email address into the id add_member takes	cloud-identity.groups.readonly
list_members	Who is in a space, people and groups resolved to names and addresses, and on request who is in each group	chat.memberships.readonly, directory.readonly, cloud-identity.groups.readonly
get_member	One membership: who or what it is, their role, whether they have joined	chat.memberships.readonly, directory.readonly, cloud-identity.groups.readonly
update_member_role	Make a manager an ordinary member again	chat.memberships
promote_member	Make someone a manager or an assistant manager, with GCM_ENABLE_DESTRUCTIVE	chat.memberships
list_reactions	Reactions on a message	chat.messages.readonly
list_pinned_messages	What a space has pinned	chat.spaces.pins.readonly
pin_message	Pin a message, which everyone in the space sees	chat.spaces.pins
unpin_message	Remove a pin	chat.spaces.pins
get_space_read_state	How far you have read in a space	chat.users.readstate.readonly
get_thread_read_state	How far you have read in a thread	chat.users.readstate.readonly
mark_space_read	Clear a space's unread badge, for you only	chat.users.readstate
mark_space_unread	Rewind your read mark, for you only	chat.users.readstate
list_space_events	What changed in a space over the last 28 days	the read scope of each event type asked for
get_space_event	One of those changes by resource name	chat.spaces.readonly
get_space_notification_setting	What Chat tells you about a space; not under GCM_READ_ONLY	chat.users.spacesettings
update_space_notification_setting	Change it, or mute the space	chat.users.spacesettings
get_availability	Your own presence and custom status	chat.users.availability.readonly
set_availability	Active, away, or do not disturb until a time	chat.users.availability
set_custom_status	Set or clear the text and emoji beside your name	chat.users.availability
list_custom_emojis	Your organization's own emoji	chat.customemojis.readonly
get_custom_emoji	One of them by resource name	chat.customemojis.readonly
create_custom_emoji	Add one from a local image	chat.customemojis
delete_custom_emoji	Remove one, for everyone, with GCM_ENABLE_DESTRUCTIVE	chat.customemojis
delete_space	Delete a space and everything in it, with GCM_ENABLE_DESTRUCTIVE	chat.delete
list_sections	Your own sidebar sections	chat.users.sections.readonly
list_section_items	What a section holds, or which section a space sits in	chat.users.sections.readonly
send_message	Post text, exactly as given, in Chat's syntax or Markdown. Optionally into a thread, quoting a message, or carrying an uploaded file	chat.messages.create; chat.messages.readonly to quote
upload_attachment	Send a local file to a space and get the token that attaches it	chat.messages.create
update_message	Edit the text of a message you sent	chat.messages
delete_message	Delete one message, with GCM_ENABLE_DESTRUCTIVE. Already gone counts as success	chat.messages
delete_thread	Delete a thread's first message and every reply, with GCM_ENABLE_DESTRUCTIVE	chat.messages
add_reaction	React to a message with a Unicode emoji	chat.messages.reactions
remove_reaction	Remove a reaction, by resource name or by message, emoji and person	chat.messages.reactions
create_group_chat	Start an unnamed group chat with 2 to 20 people	chat.spaces.create
create_space	Create a private named space with up to 20 people	chat.spaces.create
update_space	Rename a space, change its description, or make it private	chat.spaces
set_space_audience	Open a space to a target audience, with GCM_ENABLE_DESTRUCTIVE	chat.spaces
add_member	Invite someone in your organization to a space by email, or add a Google Group to a space that admits nobody from outside	chat.memberships; chat.spaces.readonly, directory.readonly to check the address
add_external_member	Invite someone from outside your organization, or add a Google Group where outsiders are admitted, with GCM_ENABLE_DESTRUCTIVE	chat.memberships; cloud-identity.groups.readonly to check a group's address
remove_member	Remove a membership, with GCM_ENABLE_DESTRUCTIVE. Already gone counts as success	chat.memberships
create_section	Add a sidebar section	chat.users.sections
rename_section	Rename a sidebar section	chat.users.sections
delete_section	Delete a sidebar section, with GCM_ENABLE_DESTRUCTIVE; its spaces fall back to the defaults	chat.users.sections
position_section	Reorder a section, by absolute rank or by moving it to the start or end	chat.users.sections
move_space_to_section	File a space under a section. A space already there is left alone	chat.users.sections

Sections are your own sidebar. Nothing there changes a space, and nobody else sees it.

Three resources carry the same content as the matching tools, for a client that includes resources in its context:

• gchat://spaces/{space_id}
• gchat://spaces/{space_id}/messages/{message_id}
• gchat://spaces/{space_id}/threads/{thread_id}

Safety

• dry_run on 29 write tools. It returns the request body that would have been sent, and the call cannot write: the flag puts the request on a context the HTTP client refuses to write under, so a tool that forgot its own preview branch fails loudly instead of posting. A preview may still read what it shows or checks, such as the quoted message a quote names or the text a delete repeats.

• GCM_READ_ONLY=true leaves the write tools unregistered. A tool that is not registered cannot be called, whatever permission mode the client is in or whatever a model asks for. It is set where you start the server, so it binds the whole session rather than one call. A google-chat-mcp login run with it set asks for read-only scopes, so that token cannot write either. A token from an earlier login keeps its write scopes until you log in again, and turning writes back on takes another login.

• What cannot be taken back is not registered unless you say so. The deletes, delete_thread, set_space_audience, promote_member and add_external_member exist only with GCM_ENABLE_DESTRUCTIVE=true. Each call then says confirm: true. delete_message, delete_thread, delete_space, delete_custom_emoji and set_space_audience also repeat what they act on: how the message begins, or the space's or the emoji's name. The server reads the target first and refuses [stale] when it differs, so the call your client shows you says which message or space goes.

• Your client approves each call; the server asks you nothing. Claude Code asks for the tools you list under permissions.ask. claude.ai and Codex prompt for a tool marked destructiveHint, which every tool in the list above that needs GCM_ENABLE_DESTRUCTIVE carries. VS Code prompts for every tool that changes anything, download_attachment included. In Claude Code, put the writes that post, invite, share or delete under permissions.ask in your settings, with the name you gave the server in place of google-chat:

  {
    "permissions": {
      "ask": [
        "mcp__google-chat__send_message", "mcp__google-chat__update_message",
        "mcp__google-chat__upload_attachment",
        "mcp__google-chat__create_space", "mcp__google-chat__create_group_chat",
        "mcp__google-chat__find_direct_message",
        "mcp__google-chat__add_member", "mcp__google-chat__add_external_member",
        "mcp__google-chat__update_member_role", "mcp__google-chat__promote_member",
        "mcp__google-chat__remove_member", "mcp__google-chat__update_space",
        "mcp__google-chat__pin_message", "mcp__google-chat__create_custom_emoji",
        "mcp__google-chat__delete_message", "mcp__google-chat__delete_thread",
        "mcp__google-chat__delete_section"
      ]
    }
  }
  

  delete_space, set_space_audience and delete_custom_emoji need no rule: they carry Claude Code's requiresUserInteraction mark, so Claude Code 2.1.199 or later asks on every call in every interactive mode, and refuses them where nobody can be asked.

• Nothing reaches the whole space or past it by default. A post or an edit that mentions everyone, <users/all>, is refused. A space is created private, and update_space does not open one. In a space that admits people from outside your organization, add_member refuses an address your organization's directory does not know and every Google Group, and update_member_role makes nobody a manager: those are add_external_member and promote_member.

• send_message posts the body verbatim. No prefix, no suffix, no "sent by an assistant" footer.

• A retried post cannot land twice. Each message carries a client-chosen id, so a retry after a timeout returns what already landed instead of posting again.

• Logs never carry the payload. They record which call was made, to which resource, and how it ended. Message text, addresses, names and search terms stay out, and a test fails the build if one appears.

How it works

MCP client ──stdio──► google-chat-mcp
                       ├── tools      one handler per tool; shapes the reply
                       ├── service    the rules: idempotency, degrading, search
                       ├── gchat      REST client for Chat, People and OIDC
                       ├── directory  email cache, so a page of messages costs one lookup
                       └── auth       refresh token → access token

Every space, message and thread is addressed by its resource name, never by position, and a listing keeps paging while Google returns a token — including past an empty page, which Chat returns when it applies the page size before the filter.

Getting help

If something does not work, run google-chat-mcp doctor. It checks the credentials, the granted scopes and what Google actually answers, and names what is missing — most first-run trouble is an API that was never enabled or a consent screen without you on it.

If that does not explain it, open an issue. Never paste a space or message resource name, message text, a client_secret.json or a token into one; describe the shape instead. Security problems go through SECURITY.md, privately.

Versioning

Tool names and their output fields are stable within a major version. A change needing you to act — a new scope, another login, a different command in your client config — is marked Breaking: in CHANGELOG.md, which is also what each release's notes are made from.

Development

make build     # the binary
make test      # race detector, coverage floor
make check     # everything CI runs

make check is the definition of done: formatting, go vet, golangci-lint, race tests with a per-package coverage floor, govulncheck, a license check, a stdio smoke test, a schema diff against the released tool surface, an API-coverage gate that fails when a Google API method has no verdict on it or a call this server makes has no row, and a staleness gate that fails when this README, the docs or the changelog drift from the code.

Documentation

• docs/architecture.md — the request flow, the package layout, the evidence log behind the conventions, and the design decisions a contributor should not undo.
• docs/configuration.md — every environment variable.
• docs/gcp-setup.md — the Google Cloud project and OAuth client, step by step.
• docs/security.md — the threat model.
• docs/runbook.md — rotating or recovering credentials.

Contributing

Questions and bugs go in issues; pull requests are welcome. CONTRIBUTING.md covers the branch and review flow, and make check is what has to pass.

Security

SECURITY.md says how to report a vulnerability.

Code of conduct

CODE_OF_CONDUCT.md — Contributor Covenant 3.0.

License

Apache 2.0 — see LICENSE.