--- title: "Glean MCP server for AI agents - actionlake" description: "Give Claude 180 Glean actions through one MCP server: agents, admin usage, governance. Your agent never holds the credential. 100,000 calls a month free." canonical: https://actionlake.com/connectors/glean updated: 2026-10-23 --- Connectors · Developer & infrastructure # Glean MCP server for AI agents. actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Glean and the rest of your systems. It gives your agent 180 Glean actions (87 reads, 66 writes and 27 that wait for a confirmation) and holds the Glean credential itself, so the agent never does. It paces Glean's limits and records every call. [Connect Glean free](https://actionlake.com/console?start=sandbox) [See pricing](https://actionlake.com/pricing) 100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you. `claude mcp add --transport http actionlake https://connect.actionlake.com/mcp` the first call ``` do { action: "glean.users.list", intent: "check which Glean account is connected" } # List users · read · 1 upstream call ``` - 180 actions in one signed file - 87 read look, never change - 66 write create and update - 27 wait for a yes destructive, confirmed first Set up ## Connect Glean in three steps. 1. 01 ### Add actionlake to Claude. Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us. `https://connect.actionlake.com/mcp` 2. 02 ### Connect Glean. API key. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key. - `api_token` Glean API token (Admin Console > Platform > API Tokens; an Indexing API token for the index_* actions) - `act_as` Your Glean act as - `auth_type` Your Glean auth type - `host` Where your Glean lives: your host ``` account { op: "connections.requirements", service: "glean" } # free: exactly what to paste, and what is found for you ``` 3. 03 ### Make the first call. Check before a write. Ask in plain words; Claude picks the action. Before anything changes, `check` validates the call and prices it, for free. ``` do { action: "glean.users.list" } # list users · read · 1 upstream call check { action: "glean.answers.create", input: { … } } # free: inputs, permissions, cost and confirmations, nothing sent ``` Glean at a glance **Sign-in** API key. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. **You provide** `api_token` **Setup fields** `act_as` `auth_type` `host` **Limits we pace to** 300 calls a minute, per connection **API covered** Glean Client API v1, Indexing API v1 and Platform API (gleanwork/open-api final_specs), at your Glean instance's API base URL, which you enter when connecting **Built from** Glean's documentation, read 23 October 2026[OpenAPI spec (GitHub)](https://raw.githubusercontent.com/gleanwork/open-api/main/final_specs/client_rest.yaml) [OpenAPI spec (GitHub)](https://raw.githubusercontent.com/gleanwork/open-api/main/final_specs/indexing.yaml) [OpenAPI spec (GitHub)](https://raw.githubusercontent.com/gleanwork/open-api/main/final_specs/platform.yaml) **Service file** Version 1.0.0, signed (Ed25519) **Cached reads** 59 of 87 reads, for up to 5 minutes; a write clears what it affects **Shared entities** 3, so ask can line Glean up with your other systems **Data** Processed and stored in Sydney, Australia. No US region yet Capabilities ## What an AI agent can do in Glean. 180 actions in 37 areas. Every one carries its effect, so a key can allow the reads and hold the rest. - **87** read look, never change - **66** write create and update - **27** destructive wait for a confirmation 1. ### Agents 13 7 read · 2 write · 4 destructive Create an agent · Search agents · Search agents · Get agent 2. ### Admin usage 11 5 read · 5 write · 1 destructive Submit an editable-agent limit-increase request · List the billing limit-increase request queue · List usage limits · Get a billing limit-increase request 3. ### Governance 11 5 read · 5 write · 1 destructive Lists policies · Creates new policy · Gets specified policy · Updates an existing policy 4. ### Index permissions 11 0 read · 8 write · 3 destructive Schedules the processing of group memberships · Beta users · Delete group · Delete membership 5. ### Chat 10 4 read · 3 write · 3 destructive Retrieves all saved Chats · Retrieves a Chat · Deletes saved Chats · Create a chat response 6. ### Index troubleshooting 9 9 read · 0 write · 0 destructive Check document access · Beta: Get datasource status · Beta: Get document lifecycle events · Beta: Get document information 7. ### Skills 9 5 read · 3 write · 1 destructive Import skills from GitHub · List skills · List skill versions · Retrieve skill 8. ### Collections 8 2 read · 4 write · 2 destructive Add Collection item · Create Collection · List Collections · Read Collection **29 more areas · 98 actions** - Index people **7** - Search **7** - Tools **7** - Index documents **6** - Triggers **6** - Answers **5** - Index custom metadata **5** - Pins **5** - Shortcuts **5** - Datasources **4** - Documents **4** - Trigger presets **4** - Usage **4** - Announcements **3** - Index datasources **3** - Verification **3** - Activity **2** - Auth **2** - Departments **2** - Idp groups **2** - Index shortcuts **2** - Oauth clients **2** - Users **2** - Admin agents **1** - Entities **1** - Index auth **1** - Insights **1** - Messages **1** - People **1** Top actions ## The Glean API, shaped for agents. The ids your agent types, what each does, and the one name it shares with other systems. 25 of Glean's 25 action names are shared with at least one other connector, so an agent learns them once. | Action | What it does | Effect | Same name in | | --- | --- | --- | --- | | `glean.users.list` List users | List users. | read | `identity.user.list` 474 connectors | | `glean.idp_groups.list` List IdP groups | List IdP groups. | read | `identity.group.list` 262 connectors | | `glean.departments.list` List departments | List departments. | read | `hr.department.list` 40 connectors | | `glean.users.get` Get user | Get user. | read | `identity.user.get` 399 connectors | | `glean.idp_groups.get` Get an IdP group | Get an IdP group. | read | `identity.group.get` 212 connectors | | `glean.departments.get` Get a department | Get a department. | read | `hr.department.get` 33 connectors | | `glean.triggers.list` List triggers | List triggers. | read | `automation.trigger.list` 7 connectors | | `glean.answers.create` Create Answer | Create Answer. | write | `knowledge.article.create` 28 connectors | | `glean.answers.list` List Answers | List Answers. | read | `knowledge.article.list` 26 connectors | | `glean.triggers.create` Create trigger | Create trigger. | write | `automation.trigger.create` 5 connectors | | `glean.governance.create_policy` Creates new policy | Creates new policy. | write | `security.policy.create` 25 connectors | | `glean.triggers.delete` Delete trigger | Delete trigger. | destructive | `automation.trigger.delete` 6 connectors | Try it ## Prompts to paste into Claude. Each one names the Glean actions it will call, so you know what it reads and what it changes before you send it. 1. Read read Who has access in Glean? List every user and their role. calls `glean.users.list` 2. Write write Create Answer in Glean. Show me exactly what you will send before you save it. calls `glean.answers.create` Governance for Glean ## Destructive actions wait for a yes. 27 Glean actions are destructive. These are all of them: - Delete trigger `glean.triggers.delete` - Delete Answer `glean.answers.delete` - Deletes saved Chats `glean.chat.delete` - Delete pin `glean.pins.delete` - Delete skill `glean.skills.delete` - Deletes all saved Chats owned by a user `glean.chat.delete_all` - Delete shortcut `glean.shortcuts.delete` - Create agent run `glean.agents.create_run` - Delete files uploaded by a user for chat `glean.chat.delete_files` - Delete Collection `glean.collections.delete` - Delete Announcement `glean.announcements.delete` - Respond to agent run approvals `glean.agents.respond_to_run` - Delete document `glean.index_documents.delete` - Reset a usage limit `glean.admin_usage.reset_limit` - Delete Collection item `glean.collections.delete_item` - Rotate token `glean.index_auth.rotate_token` - Delete team `glean.index_people.delete_team` - Create an agent run and wait for the response `glean.agents.legacy_run_and_wait` - Delete employee `glean.index_people.delete_employee` - Delete user `glean.index_permissions.delete_user` - Rotate datasource instance credentials `glean.datasources.rotate_credentials` - Delete group `glean.index_permissions.delete_group` - Deletes findings export `glean.governance.delete_findings_export` - Remove metadata schema `glean.index_custom_metadata.delete_schema` - Delete membership `glean.index_permissions.delete_membership` - Remove custom metadata `glean.index_custom_metadata.delete_document_metadata` - Cancel an agent run `glean.agents.cancel_run` A destructive action runs only with `confirm: true`. Under the `human` policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after. do glean.triggers.delete confirm_policy: **human** Delete trigger? **intent:** the user asked me to delete trigger run suspended · waiting for a named person · key _glean-agent_ cannot confirm itself In the console, or from an emailed signed link. a key for this connector ``` account { op: "keys.create", name: "glean-agent", allowed_actions: ["glean.*"], cap_calls: 2000, confirm_policy: "human_for_writes", approval_rules: [ { match: "glean.triggers.delete", approver: "lead@example.com" }, { match: "glean.answers.delete", approver: "lead@example.com" }, { match: "glean.chat.delete", approver: "lead@example.com" } ] } ``` Illustrative. Scoped to Glean only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person. Cost ## What Glean costs on actionlake. Every Glean action is one upstream call, the only thing actionlake bills. Searching, `check`, `cost`, `account` and any call Glean refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000. - 1 upstream call per action all 180 Glean actions - 180 actions page each page of a long list is one call - 59 reads can be cached a cache hit costs nothing - 100,000 calls a month, free paid plans from US$49 a month for 250,000 [See pricing](https://actionlake.com/pricing) Action index ## Every Glean action. 180 actions by area: the id your agent calls, what it does, and its effect. **Agents 13** - `glean.agents.cancel_run` Cancel an agent run destructive - `glean.agents.create` Create an agent write - `glean.agents.create_run` Create agent run destructive - `glean.agents.get` Get agent read - `glean.agents.get_run` Get agent run read - `glean.agents.get_schemas` Get agent schemas read - `glean.agents.legacy_get` Retrieve an agent read - `glean.agents.legacy_get_schemas` List an agent's schemas read - `glean.agents.legacy_run_and_wait` Create an agent run and wait for the response destructive - `glean.agents.legacy_search` Search agents read - `glean.agents.respond_to_run` Respond to agent run approvals destructive - `glean.agents.search` Search agents read - `glean.agents.update` Edit an agent write **Admin usage 11** - `glean.admin_usage.batch_upsert_limits` Apply usage limit policies write - `glean.admin_usage.create_limit_increase_request` Submit an editable-agent limit-increase request write - `glean.admin_usage.evaluate_limits` Evaluate administrative usage limit headroom read - `glean.admin_usage.get_limit_increase_request` Get a billing limit-increase request read - `glean.admin_usage.get_settings` Get usage settings read - `glean.admin_usage.list_limit_increase_requests` List the billing limit-increase request queue read - `glean.admin_usage.list_limits` List usage limits read - `glean.admin_usage.reset_limit` Reset a usage limit destructive - `glean.admin_usage.update_limit_increase_request` Resolve a billing limit-increase request write - `glean.admin_usage.update_settings` Update usage settings write - `glean.admin_usage.upsert_limit` Upsert a usage limit write **Governance 11** - `glean.governance.create_findings_export` Creates findings export write - `glean.governance.create_policy` Creates new policy write - `glean.governance.create_report` Creates new one-time report write - `glean.governance.delete_findings_export` Deletes findings export destructive - `glean.governance.get_policy` Gets specified policy read - `glean.governance.get_report_status` Fetches report run status read - `glean.governance.get_visibility_overrides` Fetches documents visibility read - `glean.governance.list_findings_exports` Lists findings exports read - `glean.governance.list_policies` Lists policies read - `glean.governance.set_visibility_overrides` Hide or unhide docs write - `glean.governance.update_policy` Updates an existing policy write **Index permissions 11** - `glean.index_permissions.bulk_index_groups` Bulk index groups write - `glean.index_permissions.bulk_index_memberships` Bulk index memberships for a group write - `glean.index_permissions.bulk_index_users` Bulk index users write - `glean.index_permissions.delete_group` Delete group destructive - `glean.index_permissions.delete_membership` Delete membership destructive - `glean.index_permissions.delete_user` Delete user destructive - `glean.index_permissions.index_group` Index group write - `glean.index_permissions.index_membership` Index membership write - `glean.index_permissions.index_user` Index user write - `glean.index_permissions.process_all_memberships` Schedules the processing of group memberships write - `glean.index_permissions.set_beta_users` Beta users write **Chat 10** - `glean.chat.create_response` Create a chat response write - `glean.chat.delete` Deletes saved Chats destructive - `glean.chat.delete_all` Deletes all saved Chats owned by a user destructive - `glean.chat.delete_files` Delete files uploaded by a user for chat destructive - `glean.chat.get` Retrieves a Chat read - `glean.chat.get_application` Gets the metadata for a custom Chat application read - `glean.chat.get_files` Get files uploaded by a user for Chat read - `glean.chat.list` Retrieves all saved Chats read - `glean.chat.rename` Update a chat write - `glean.chat.send` Chat write **Index troubleshooting 9** - `glean.index_troubleshooting.check_document_access` Check document access read - `glean.index_troubleshooting.datasource_status` Beta: Get datasource status read - `glean.index_troubleshooting.document_events` Beta: Get document lifecycle events read - `glean.index_troubleshooting.document_status` Beta: Get document information read - `glean.index_troubleshooting.documents_status` Beta: Get information of a batch of documents read - `glean.index_troubleshooting.get_document_count` Get document count read - `glean.index_troubleshooting.get_document_status` Get document upload and indexing status read - `glean.index_troubleshooting.get_user_count` Get user count read - `glean.index_troubleshooting.user_status` Beta: Get user information read **Skills 9** - `glean.skills.delete` Delete skill destructive - `glean.skills.get` Retrieve skill read - `glean.skills.get_version` Retrieve skill version read - `glean.skills.import` Import skills from GitHub write - `glean.skills.list` List skills read - `glean.skills.list_versions` List skill versions read - `glean.skills.preview_source` Preview a GitHub skill source read - `glean.skills.sync` Sync a GitHub-imported skill write - `glean.skills.update` Update skill write **Collections 8** - `glean.collections.add_items` Add Collection item write - `glean.collections.create` Create Collection write - `glean.collections.delete` Delete Collection destructive - `glean.collections.delete_item` Delete Collection item destructive - `glean.collections.get` Read Collection read - `glean.collections.list` List Collections read - `glean.collections.update` Update Collection write - `glean.collections.update_item` Update Collection item write **Index people 7** - `glean.index_people.bulk_index_employees` Bulk index employees write - `glean.index_people.bulk_index_teams` Bulk index teams write - `glean.index_people.delete_employee` Delete employee destructive - `glean.index_people.delete_team` Delete team destructive - `glean.index_people.index_employee` Index employee write - `glean.index_people.index_team` Index team write - `glean.index_people.process_all` Schedules the processing of uploaded employees and teams write **Search 7** - `glean.search.admin_search` Search the index (admin) read - `glean.search.autocomplete` Autocomplete read - `glean.search.feed` Feed of documents and events read - `glean.search.list_filters` List search filters read - `glean.search.platform_search` Search read - `glean.search.query` Search read - `glean.search.recommendations` Recommend documents read **Tools 7** - `glean.tools.authorize_action_pack` Start the OAuth authorization flow for an action pack write - `glean.tools.authorize_tool_server` Start the OAuth authorization flow for a tool server write - `glean.tools.call` Execute the specified tool write - `glean.tools.get_action_pack_auth` Get end-user authentication status for an action pack read - `glean.tools.get_tool_server_auth` Get end-user authentication status for a tool server read - `glean.tools.list` List available tools read - `glean.tools.list_tool_server_tools` Get tool definitions from a tool server read **Index documents 6** - `glean.index_documents.bulk_index` Bulk index documents write - `glean.index_documents.delete` Delete document destructive - `glean.index_documents.index` Index document write - `glean.index_documents.index_many` Index documents write - `glean.index_documents.process_all` Schedules the processing of uploaded documents write - `glean.index_documents.update_permissions` Update document permissions write **Triggers 6** - `glean.triggers.create` Create trigger write - `glean.triggers.delete` Delete trigger destructive - `glean.triggers.get` Get trigger read - `glean.triggers.list` List triggers read - `glean.triggers.search_events` Search events for a trigger read - `glean.triggers.update` Update trigger write **Answers 5** - `glean.answers.create` Create Answer write - `glean.answers.delete` Delete Answer destructive - `glean.answers.get` Read Answer read - `glean.answers.list` List Answers read - `glean.answers.update` Update Answer write **Index custom metadata 5** - `glean.index_custom_metadata.delete_document_metadata` Remove custom metadata destructive - `glean.index_custom_metadata.delete_schema` Remove metadata schema destructive - `glean.index_custom_metadata.get_schema` Retrieve metadata schema read - `glean.index_custom_metadata.set_document_metadata` Add or update custom metadata write - `glean.index_custom_metadata.set_schema` Create or update metadata schema write **Pins 5** - `glean.pins.create` Create pin write - `glean.pins.delete` Delete pin destructive - `glean.pins.get` Read pin read - `glean.pins.list` List pins read - `glean.pins.update` Update pin write **Shortcuts 5** - `glean.shortcuts.create` Create shortcut write - `glean.shortcuts.delete` Delete shortcut destructive - `glean.shortcuts.get` Read shortcut read - `glean.shortcuts.list` List shortcuts read - `glean.shortcuts.update` Update shortcut write **Datasources 4** - `glean.datasources.get_credential_status` Get datasource instance credential status read - `glean.datasources.get_instance_configuration` Get datasource instance configuration read - `glean.datasources.rotate_credentials` Rotate datasource instance credentials destructive - `glean.datasources.update_instance_configuration` Update datasource instance configuration write **Documents 4** - `glean.documents.get` Read documents read - `glean.documents.get_permissions` Read document permissions read - `glean.documents.list_by_facets` Read documents by facets read - `glean.documents.summarize` Summarize documents read **Trigger presets 4** - `glean.trigger_presets.get` Get trigger preset read - `glean.trigger_presets.list` List trigger presets read - `glean.trigger_presets.list_input_values` Search trigger preset input values read - `glean.trigger_presets.search_events` Search events for a trigger preset read **Usage 4** - `glean.usage.create_limit_increase_request` Submit a personal limit-increase request write - `glean.usage.evaluate_limits` Evaluate usage limit headroom read - `glean.usage.get_limit_increase_request` Get a personal limit-increase request read - `glean.usage.list_limit_increase_requests` List personal limit-increase requests read **Announcements 3** - `glean.announcements.create` Create Announcement write - `glean.announcements.delete` Delete Announcement destructive - `glean.announcements.update` Update Announcement write **Index datasources 3** - `glean.index_datasources.add` Add or update datasource write - `glean.index_datasources.get_config` Get datasource config read - `glean.index_datasources.submit` Submit datasource data write **Verification 3** - `glean.verification.add_reminder` Create verification write - `glean.verification.list` List verifications read - `glean.verification.verify` Update verification write **Activity 2** - `glean.activity.feedback` Report client activity write - `glean.activity.report` Report document activity write **Auth 2** - `glean.auth.check_datasource_auth` Check datasource authorization read - `glean.auth.create_token` Create authentication token write **Departments 2** - `glean.departments.get` Get a department read - `glean.departments.list` List departments read **Idp groups 2** - `glean.idp_groups.get` Get an IdP group read - `glean.idp_groups.list` List IdP groups read **Index shortcuts 2** - `glean.index_shortcuts.bulk_index` Bulk index external shortcuts write - `glean.index_shortcuts.upload` Upload shortcuts write **Oauth clients 2** - `glean.oauth_clients.get` Get an OAuth client read - `glean.oauth_clients.list` List OAuth clients read **Users 2** - `glean.users.get` Get user read - `glean.users.list` List users read **Admin agents 1** - `glean.admin_agents.list` List all agents read **Entities 1** - `glean.entities.list` List entities read **Index auth 1** - `glean.index_auth.rotate_token` Rotate token destructive **Insights 1** - `glean.insights.get` Get insights read **Messages 1** - `glean.messages.get` Read messages read **People 1** - `glean.people.get` Read people read Questions ## The Glean MCP server, answered. **Is there a Glean MCP server for Claude?** Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 180 Glean actions across agents, admin usage, governance and index permissions, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Glean. **What do I need to connect Glean?** Glean API token (Admin Console > Platform > API Tokens; an Indexing API token for the index_* actions). Plus your act as, your auth type and your host. The free call account { op: "connections.requirements", service: "glean" } lists exactly what to paste. **Can an AI agent delete or change things in Glean?** Only if its key allows it, and only with an explicit confirmation. 27 Glean actions are destructive, including delete trigger, delete Answer and deletes saved Chats. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it. **Will an AI agent use up my Glean API limit?** actionlake paces every call to the limits in the Glean service file: 300 calls a minute per connection. Repeated reads are answered from cache (59 Glean actions can be), which never reaches Glean. **What does a Glean action cost?** One upstream call, the only unit actionlake bills. A list that pages bills one call per page (180 Glean actions page). Cache hits, searches, dry runs and calls Glean refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000. **Which Glean API does it cover?** The Glean Client API v1, Indexing API v1 and Platform API (gleanwork/open-api final_specs) at your Glean instance's API base URL, which you enter when connecting. It is built from Glean's documentation as read on 23 October 2026. 180 actions in 37 areas, each one in the signed service file (version 1.0.0). **Does actionlake keep my Glean data, and where?** actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 5 minutes, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your Glean credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models. **Which AI clients can use it?** Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names. ## More connectors like Glean Shares the most action names with - [CircleCI 7](https://actionlake.com/connectors/circleci) - [CockroachDB Cloud 4](https://actionlake.com/connectors/cockroachdb-cloud) - [Spacelift 4](https://actionlake.com/connectors/spacelift) - [Veeam Backup for Microsoft 365 4](https://actionlake.com/connectors/veeam-backup-for-microsoft-365) - [Discourse 4](https://actionlake.com/connectors/discourse) - [Scalr 2](https://actionlake.com/connectors/scalr) Joins with, on shared entities - [Odoo 3](https://actionlake.com/connectors/odoo) - [Freshservice 3](https://actionlake.com/connectors/freshservice) - [Lark Suite 3](https://actionlake.com/connectors/lark-suite) - [Rippling 3](https://actionlake.com/connectors/rippling) - [Absorb LMS 3](https://actionlake.com/connectors/absorb-lms) - [15Five 3](https://actionlake.com/connectors/15five) Browse - [All Developer & infrastructure connectors](https://actionlake.com/connectors/category/developer-and-infrastructure) - [All connectors](https://actionlake.com/connectors) - [How actionlake compares](https://actionlake.com/compare) actionlake is independent. It is not made or endorsed by Glean; the name is the vendor's own. Counts are from the Glean service file, version 1.0.0. ## Give your agent Glean today. [Connect Glean free](https://actionlake.com/console?start=sandbox) [See pricing](https://actionlake.com/pricing) Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free. --- Source: https://actionlake.com/connectors/glean More: https://actionlake.com/llms.txt