MCP App Store
by KeenEthics
Grain icon

Grain MCP Server for Claude and ChatGPT

By Grain

Overview

Grain captures and transcribes your meetings where you have them: Meet, Zoom, Teams, Slack, and more. Grain builds an AI Meeting Data Layer of transcripts, notes, and enriched context that Claude uses to power your work. Example prompts: "Draft a proposal for AcmeCo using context from every call we've had with them." "What pain points came up most across our user interviews this month?" "Summarize the team meetings I missed this week and flag anything I should weigh in on." "Find and clip recent moments where customers pushed back on pricing to share with sales." "Create a project for AcmeCo with every meeting we've had with them so I can prep for our QBR."

How to connect

  1. Claude: Open the Grain listing in the Claude connectors directory and choose Connect. Claude listing Grain exposes 21 tools here.
  2. ChatGPT: Open the Grain listing in the ChatGPT app directory and choose Connect. ChatGPT listing Grain exposes 55 tools here.

Tools

add_clips_to_story

ChatGPT
Adds one or more clips to an existing story. Use list_stories or fetch_story to find the story ID, and create_clip or list_clips to get clip IDs.

add_recordings_to_collection

ChatGPT
Adds one or more recordings to an existing playlist (collection) by recording ID. Use list_meetings or search_in_transcripts first to find recording IDs.

add_tag_to_meetings

ChatGPT
Add a tag to up to 50 Grain meetings you can access, using their meeting IDs. Creates the tag if it doesn't exist.

add_team_subscriber

ChatGPT
Subscribes a workspace user to a team, identified by user ID or email. Subscribers can see meetings shared with the team and stay members of their own team.

assign_paid_seat_to_users

ChatGPT
Assigns an unassigned paid seat to one or more workspace users. Use workspace_seat_info to check how many unassigned seats are available before calling this.

create_clip

ChatGPT
Creates a clip on a recording between the given timestamps. Use search_in_transcripts first to find the recording and relevant transcript timestamps, then call this tool with the meeting ID and start/end timestamps. Choose start_ms and end_ms to capture a complete thought or topic — avoid cutting off mid-sentence. Invalid ranges (start_ms >= end_ms, or end_ms past the recording's duration) returns an error.

create_collection

ChatGPT
Creates a new empty playlist (collection) with the given title. The playlist is created with restricted visibility (only you can see it). Use add_recordings_to_collection to add meetings, and update_collection_share_state to change visibility.

create_smart_topic

ChatGPT
Creates a new smart topic in your Grain workspace. A smart topic is a saved classifier that marks where meetings discuss a given subject, based on example keywords and phrases. Provide 1-50 examples: short examples (1-2 words) are treated as keywords, longer ones as semantic phrases. Only workspace admins can create smart topics. Pass team_id to scope the topic to a team, so it only matches meetings shared with that team. Omit it for a workspace-scoped topic that matches meetings shared with the whole workspace. Matching runs asynchronously: existing meetings are scored over the following minutes, so the new topic may return no meetings immediately when used with the smart_topics filter. To reconfigure an existing topic, use the Grain app — this tool only creates new topics.

create_story

ChatGPT
Creates a new story with the given title.

create_team

ChatGPT
Creates a new team in the workspace. Optionally seeds the team with initial members.

fetch_collection

ChatGPT
Fetches detailed information about a single Grain collection (also known as a playlist) by ID, including the list of recordings it contains with their URLs.

fetch_deal

ChatGPT
Fetches information about a single HubSpot deal by ID. In addition to returning the same data as returned by list_all_deals, this returns data about all the activity that has occurred on the deal.

fetch_meeting

ChatGPT
Fetches information about a single Grain meeting by ID. The response format is the same as is returned by list_meetings.

fetch_meeting_action_items

ChatGPT
Fetches the action items extracted from a single Grain meeting by ID. Each action item includes the task description, timestamp, status (pending or completed), the assignee (person_id and name, or null when unassigned), and the due date (or null when not set). end_timestamp_ms is null when the action item has no end time. In some cases, older meetings may not have had action items generated for them.

fetch_meeting_coaching_feedback

ChatGPT
Fetches AI-generated sales coaching feedback and scorecard for a single Grain meeting by ID. The response format is the same as is returned by list_coaching_feedback.

fetch_meeting_notes

ChatGPT
Fetches the AI notes payload from a single Grain meeting by ID. In some cases, older meetings may not have had notes generated for them. In these cases you can use fetch_meeting_transcript instead to determine the content of the meeting.

fetch_meeting_transcript

ChatGPT
Fetches the full transcript of a single Grain meeting by ID. Returns the entire conversation as markdown, which can be large for long meetings.

fetch_playlist

ChatGPT
Fetches detailed information about a single Grain playlist by ID, including the list of recordings it contains with their URLs.

fetch_story

ChatGPT
Fetches detailed information about a single Grain story by ID, including its items (clips and text sections). Use list_stories first to find story IDs.

fetch_user_recording_notes

ChatGPT
Fetches the current user's private notes for a single Grain meeting by ID. Returns the notes as markdown text, or a message if no notes exist.

get_dossier_for_company

ChatGPT
Fetches the Company Intelligence dossier for a single company by company_id (the id returned by search_companies). The dossier is returned as markdown plus metadata. If the company exists but has no dossier generated yet, markdown and the metadata fields are null. Read-only: this never triggers dossier generation. Use this for a standing company profile. For what was decided or discussed with the company across meetings, call recall_meeting_memory first.

invite_to_workspace

ChatGPT
Sends email invitations to the specified email addresses to join your Grain workspace. Requires a workspace admin and supports up to 50 email addresses per call. If an address has a pending workspace access request, approves that request instead. Invitations use free seats by default; selecting paid seats can incur charges when invitees join. An optional team assignment applies to a Grain team within the same workspace.

list_all_deals

ChatGPT
List status of hubspot-linked deals that are synced in Grain. If the list contains more than limit deals, the response will also contain a non-null cursor value that can be used to fetch the next page of deals in the list by calling the tool again and passing the cursor along with the same filters. The list will be empty if there are no deals matching the supplied filters.

list_attended_meetings

ChatGPT
Returns a filtered list of Grain meetings you have attended, ordered by most recent. If the list contains more than limit meetings, the response will also contain a non-null cursor value that can be used to fetch the next page of meetings in the list by calling the tool again and passing the cursor along with the same filters. The list will be empty if there are no meetings matching the supplied filters. If also looking to include meetings the user didn't attend, use list_meetings instead.

list_clips

ChatGPT
Returns a paginated list of Grain clips you have access to, ordered by most recent. Clips are short segments from meeting recordings. If the list contains more than limit clips, the response will also contain a non-null cursor value that can be used to fetch the next page by calling the tool again. Only returns clips whose media has finished processing, so newly-created clips may take a few minutes to appear.

list_coaching_feedback

ChatGPT
List AI-generated sales-coaching feedback and scorecards for a filtered set of meetings. If the list contains more than limit meetings, the response will also contain a non-null cursor value that can be used to fetch the next page of meetings in the list by calling the tool again and passing the cursor along with the same filters. The list will be empty if there are no meetings matching the supplied filters.

list_collections

ChatGPT
Returns a paginated list of Grain collections (also known as playlists) you have access to, ordered by most recent. A collection is a curated group of meetings (recordings) that belong together. If the list contains more than limit collections, the response will also contain a non-null cursor value that can be used to fetch the next page of collections in the list by calling the tool again and passing the cursor along with the same filters. The list will be empty if there are no collections matching the supplied filters.

list_meetings

ChatGPT
Returns a filtered list of Grain meetings you have access to, ordered by most recent. If the list contains more than limit meetings, the response will also contain a non-null cursor value that can be used to fetch the next page of meetings in the list by calling the tool again and passing the cursor along with the same filters. The list will be empty if there are no meetings matching the supplied filters. If only looking for meetings the user attended, use list_attended_meetings instead.

list_open_deals

ChatGPT
List status of open hubspot-linked deals that are synced in Grain. If the list contains more than limit deals, the response will also contain a non-null cursor value that can be used to fetch the next page of deals in the list by calling the tool again and passing the cursor along with the same filters. The list will be empty if there are no open deals matching the supplied filters. If also looking to include closed deals, use list_all_deals instead.

list_playlists

ChatGPT
Returns a paginated list of Grain playlists you have access to, ordered by most recent. If the list contains more than limit playlists, the response will also contain a non-null cursor value that can be used to fetch the next page of playlists in the list by calling the tool again and passing the cursor along with the same filters. The list will be empty if there are no playlists matching the supplied filters.

list_smart_topics

ChatGPT
Lists the smart topics configured in your Grain workspace. Smart topics are saved classifiers that mark where meetings discuss a given subject. Use the returned id values with the smart_topics filter on the meeting-listing tools (e.g. list_meetings) to find meetings matching a topic. Deactivated topics are hidden unless include_inactive is true.

list_stories

ChatGPT
Returns a paginated list of Grain stories you have access to, ordered by most recent. Stories are curated collections of clips and text sections created from meetings. If the list contains more than limit stories, the response will also contain a non-null cursor value that can be used to fetch the next page by calling the tool again.

list_team_settings

ChatGPT
Lists teams and a number of their settings. You can use update_team_settings to update these settings.

list_teams

ChatGPT
Lists team IDs and names in your workspace. Use these IDs in the teams meeting filter.

list_user_settings

ChatGPT
Lists a few basic information about users and a number of settings. Basic information may not be updated. Settings may be updated using update_user_settings For members of teams that disallow overrides (team_settings_overridable is false), team settings are always used and user settings are returned as null. For users without a team, a non-null value indicates their effective user setting. To achieve parity among overrideable user settings, prefer setting their team's team_settings_overridable to false instead of updating multiple users.

list_workspace_users

ChatGPT
Get information about all the users in the logged-in Grain user's workspace. Each user's person ID is also returned and can be used to list recordings attended by that person.

move_users_to_team

ChatGPT
Moves one or more users into a team. Users already on a different team will have their team changed to the new one.

my_settings

ChatGPT
Get your personal settings. For overrideable settings, a null value means the team (or workspace) setting is being applied. If your team does not allow overrides (team_settings_overridable is false), overrideable settings always return null. You can use update_my_settings to change these settings.

my_team

ChatGPT
Get the settings of the team you belong to. You can use my_settings to see your personal setting overrides.

myself

ChatGPT
Get information about the logged-in Grain user.

remove_tag_from_meetings

ChatGPT
Remove a tag from up to 50 Grain meetings you can access, using their meeting IDs. Detaches the tag from the selected meetings.

remove_team_subscriber

ChatGPT
Unsubscribes a user from a team, identified by user ID or email. Only removes subscriptions. Use remove_user_from_team for team members.

remove_user_from_team

ChatGPT
Removes a user from a team.

resolve_urls

ChatGPT
Resolves canonical shareable URLs for Grain entities (meetings, clips, playlists, stories) by ID. Always prefer this tool over constructing URLs yourself; hand-built URLs are frequently wrong. Supported media_type values: recording, clip, collection, story. Each returned item contains either a url on success or an error string if the entity is not accessible to the current user.

search_companies

ChatGPT
Returns a filtered list of companies that were participants of Grain meetings you have access to.

search_contacts

ChatGPT
Returns contacts in your workspace. Without a search string, returns contacts from your most recent meetings.

search_in_transcripts

ChatGPT
Searches transcripts of Grain meetings and returns the matching segments rather than the full transcript. Useful for locating specific content, topics, quotes, decisions, action items, or moments across one or many meetings without loading entire transcripts. Uses hybrid semantic + keyword search over transcript segments — coherent conversation chunks annotated with summaries, topics, entities, and speaker info. Results are grouped by meeting and ordered by relevance.

search_persons

ChatGPT
Returns a filtered list of persons that were participants of Grain meetings you have access to.

share_meetings

ChatGPT
Share up to 50 Grain meetings you can access with teams and/or your whole workspace, using their meeting IDs. Provide team_ids, workspace: true, or both. Existing sharing is kept. This does not change who can open the meeting's share link.

tag_meetings

ChatGPT
Add or remove a tag from one or more meetings by recording ID. Creates the tag if it doesn't exist (on add).

unassign_paid_seat_from_users

ChatGPT
Removes the paid seat from one or more workspace users. The unassigned seats remain available and can be reassigned at any time until the end of the current billing cycle.

unshare_meetings

ChatGPT
Stop sharing up to 50 Grain meetings you can access with teams and/or your whole workspace, using their meeting IDs. Provide team_ids, workspace: true, or both. Other sharing is kept; fetch_meeting shows a meeting's current sharing. Participants and people the meeting was shared with directly keep access. This does not change who can open the meeting's share link.

update_collection_share_state

ChatGPT
Changes the visibility of a playlist (collection). Options: 'restricted' (only shared users), 'workspace' (all workspace members), 'public' (anyone with the link).

update_my_settings

ChatGPT
Update your personal settings. Set a field to null to unset your override and fall back to your team's setting. Overrides only take effect when your team allows them (team_settings_overridable is true).

update_team_settings

ChatGPT
Update team settings

update_user_settings

ChatGPT
Updates settings for a user. Team settings take precedence for members of teams that disallow overrides (team_settings_overridable is false). To achieve parity among overrideable user settings, prefer setting their team's team_settings_overridable to false instead of updating multiple users.

update_workspace_settings

ChatGPT
Update workspace settings

workspace_seat_info

ChatGPT
Returns the number of total, assigned, and unassigned paid seats in the workspace.

workspace_settings

ChatGPT
Lists a number of settings that affect your entire workspace. Meeting capture and sharing settings are workspace-wide defaults; team settings (list_team_settings) and personal overrides (list_user_settings) take precedence where set. You can use update_workspace_settings to update these settings.

fetch

Claude

fetch_deal

Claude

fetch_meeting

Claude

fetch_meeting_coaching_feedback

Claude

fetch_meeting_notes

Claude

fetch_meeting_transcript

Claude

list_all_deals

Claude

list_attended_meetings

Claude

list_coaching_feedback

Claude

list_meetings

Claude

list_open_deals

Claude

list_workspace_users

Claude

myself

Claude

search_companies

Claude

search_meetings

Claude

search_persons

Claude

search_recording_segments

Claude

suggest_calendar_event

Claude

suggest_email_draft

Claude

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/grain"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/grain)