--- title: "Deepgram MCP server for AI agents - actionlake" description: "Give Claude 50 Deepgram actions through one MCP server: agent configurations. Your agent never holds the credential. 100,000 calls a month free." canonical: https://actionlake.com/connectors/deepgram updated: 2026-10-23 --- Connectors · AI # Deepgram MCP server for AI agents. actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Deepgram and the rest of your systems. It gives your agent 50 Deepgram actions (28 reads, 14 writes and 8 that wait for a confirmation) and holds the Deepgram credential itself, so the agent never does. It paces Deepgram's limits and records every call. [Connect Deepgram 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: "deepgram.projects.list", intent: "check which Deepgram account is connected" } # List Projects · read · 1 upstream call ``` - 50 actions in one signed file - 28 read look, never change - 14 write create and update - 8 wait for a yes destructive, confirmed first Set up ## Connect Deepgram 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 Deepgram. 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_key` Deepgram API key (Console > Settings > API Keys) - `host` Where your Deepgram lives: your host ``` account { op: "connections.requirements", service: "deepgram" } # 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: "deepgram.projects.list" } # list projects · read · 1 upstream call check { action: "deepgram.keys.create", input: { … } } # free: inputs, permissions, cost and confirmations, nothing sent ``` Deepgram 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_key` **Setup fields** `host` **Limits we pace to** 100 calls a minute, per connection **API covered** Deepgram REST API 1.0.0`api.deepgram.com` **Built from** Deepgram's documentation, read 22 October 2026[developers.deepgram.com](https://developers.deepgram.com/openapi.json) [developers.deepgram.com](https://developers.deepgram.com/reference/deepgram-api-overview) **Service file** Version 1.0.0, signed (Ed25519) **Cached reads** 20 of 28 reads, for up to 5 minutes; a write clears what it affects **Shared entities** 3, so ask can line Deepgram up with your other systems **Data** Processed and stored in Sydney, Australia. No US region yet Capabilities ## What an AI agent can do in Deepgram. 50 actions in 21 areas. Every one carries its effect, so a key can allow the reads and hold the rest. - **28** read look, never change - **14** write create and update - **8** destructive wait for a confirmation 1. ### Agent configurations 5 2 read · 2 write · 1 destructive Create an Agent Configuration · List Agent Configurations · Get an Agent Configuration · Update Agent Metadata 2. ### Agent variables 5 2 read · 2 write · 1 destructive Create an Agent Variable · List Agent Variables · Get an Agent Variable · Update an Agent Variable 3. ### Projects 5 2 read · 1 write · 2 destructive List Projects · Get a Project · Update a Project · Delete a Project 4. ### Distribution credentials 4 2 read · 1 write · 1 destructive Create a Project Self-Hosted Distribution Credential · List Project Self-Hosted Distribution Credentials · Get a Project Self-Hosted Distribution Credential · Delete a Project Self-Hosted Distribution Credential 5. ### Keys 4 2 read · 1 write · 1 destructive List Project Keys · Create a Project Key · Get a Project Key · Delete a Project Key 6. ### Invites 3 1 read · 1 write · 1 destructive Create a Project Invite · List Project Invites · Delete a Project Invite 7. ### Usage 3 3 read · 0 write · 0 destructive Get Project Usage · Get Project Usage Breakdown · List Project Usage Fields 8. ### Balances 2 2 read · 0 write · 0 destructive Get Project Balances · Get a Project Balance **13 more areas · 19 actions** - Billing **2** - Member scopes **2** - Members **2** - Models **2** - Project models **2** - Requests **2** - Agent think models **1** - Listen **1** - Purchases **1** - Read **1** - Speak **1** - Speak V2 **1** - Tokens **1** Top actions ## The Deepgram API, shaped for agents. The ids your agent types, what each does, and the one name it shares with other systems. 7 of Deepgram's 7 action names are shared with at least one other connector, so an agent learns them once. | Action | What it does | Effect | Same name in | | --- | --- | --- | --- | | `deepgram.keys.list` List Project Keys | List Project Keys | read | `identity.api_key.list` 96 connectors | | `deepgram.keys.create` Create a Project Key | Create a Project Key | write | `identity.api_key.create` 100 connectors | | `deepgram.invites.create` Create a Project Invite | Create a Project Invite | write | `identity.invitation.create` 41 connectors | | `deepgram.invites.list` List Project Invites | List Project Invites | read | `identity.invitation.list` 33 connectors | | `deepgram.keys.delete` Delete a Project Key | Delete a Project Key | destructive | `identity.api_key.delete` 76 connectors | | `deepgram.members.list` List Project Members | List Project Members | read | this connector | | `deepgram.projects.list` List Projects | List Projects | read | this connector | | `deepgram.models.list` List Models | List Models | read | this connector | | `deepgram.speak.create` Text to Speech transformation | Text to Speech transformation | write | this connector | | `deepgram.balances.list` Get Project Balances | Get Project Balances | read | this connector | | `deepgram.requests.list` List Project Requests | List Project Requests | read | this connector | | `deepgram.speak_v2.create` Flux Text to Speech (batch) | Flux Text to Speech (batch) | write | this connector | Try it ## Prompts to paste into Claude. Each one names the Deepgram actions it will call, so you know what it reads and what it changes before you send it. 1. Read read Give me a one-line status for every active Deepgram project. calls `deepgram.projects.list` 2. Write write Create a Project Key in Deepgram. Show me exactly what you will send before you save it. calls `deepgram.keys.create` Governance for Deepgram ## Destructive actions wait for a yes. 8 Deepgram actions are destructive. These are all of them: - Delete a Project Key `deepgram.keys.delete` - Delete a Project Invite `deepgram.invites.delete` - Delete a Project Member `deepgram.members.delete` - Delete a Project `deepgram.projects.delete` - Delete an Agent Variable `deepgram.agent_variables.delete` - Delete an Agent Configuration `deepgram.agent_configurations.delete` - Delete a Project Self-Hosted Distribution Credential `deepgram.distribution_credentials.delete` - Leave a Project `deepgram.projects.leave` 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 deepgram.keys.delete confirm_policy: **human** Delete a Project Key? **intent:** the user asked me to delete a Project Key run suspended · waiting for a named person · key _deepgram-agent_ cannot confirm itself In the console, or from an emailed signed link. a key for this connector ``` account { op: "keys.create", name: "deepgram-agent", allowed_actions: ["deepgram.*"], cap_calls: 2000, confirm_policy: "human_for_writes", approval_rules: [ { match: "deepgram.keys.delete", approver: "lead@example.com" }, { match: "deepgram.invites.delete", approver: "lead@example.com" }, { match: "deepgram.members.delete", approver: "lead@example.com" } ] } ``` Illustrative. Scoped to Deepgram only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person. Cost ## What Deepgram costs on actionlake. Every Deepgram action is one upstream call, the only thing actionlake bills. Searching, `check`, `cost`, `account` and any call Deepgram 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 50 Deepgram actions - 14 actions page each page of a long list is one call - 20 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 Deepgram action. 50 actions by area: the id your agent calls, what it does, and its effect. **Agent configurations 5** - `deepgram.agent_configurations.create` Create an Agent Configuration write - `deepgram.agent_configurations.delete` Delete an Agent Configuration destructive - `deepgram.agent_configurations.get` Get an Agent Configuration read - `deepgram.agent_configurations.list` List Agent Configurations read - `deepgram.agent_configurations.update` Update Agent Metadata write **Agent variables 5** - `deepgram.agent_variables.create` Create an Agent Variable write - `deepgram.agent_variables.delete` Delete an Agent Variable destructive - `deepgram.agent_variables.get` Get an Agent Variable read - `deepgram.agent_variables.list` List Agent Variables read - `deepgram.agent_variables.update` Update an Agent Variable write **Projects 5** - `deepgram.projects.delete` Delete a Project destructive - `deepgram.projects.get` Get a Project read - `deepgram.projects.leave` Leave a Project destructive - `deepgram.projects.list` List Projects read - `deepgram.projects.update` Update a Project write **Distribution credentials 4** - `deepgram.distribution_credentials.create` Create a Project Self-Hosted Distribution Credential write - `deepgram.distribution_credentials.delete` Delete a Project Self-Hosted Distribution Credential destructive - `deepgram.distribution_credentials.get` Get a Project Self-Hosted Distribution Credential read - `deepgram.distribution_credentials.list` List Project Self-Hosted Distribution Credentials read **Keys 4** - `deepgram.keys.create` Create a Project Key write - `deepgram.keys.delete` Delete a Project Key destructive - `deepgram.keys.get` Get a Project Key read - `deepgram.keys.list` List Project Keys read **Invites 3** - `deepgram.invites.create` Create a Project Invite write - `deepgram.invites.delete` Delete a Project Invite destructive - `deepgram.invites.list` List Project Invites read **Usage 3** - `deepgram.usage.get` Get Project Usage read - `deepgram.usage.get_breakdown` Get Project Usage Breakdown read - `deepgram.usage.get_fields` List Project Usage Fields read **Balances 2** - `deepgram.balances.get` Get a Project Balance read - `deepgram.balances.list` Get Project Balances read **Billing 2** - `deepgram.billing.get_breakdown` Get Project Billing Breakdown read - `deepgram.billing.get_fields` List Project Billing Fields read **Member scopes 2** - `deepgram.member_scopes.list` List Project Member Scopes read - `deepgram.member_scopes.update` Update Project Member Scopes write **Members 2** - `deepgram.members.delete` Delete a Project Member destructive - `deepgram.members.list` List Project Members read **Models 2** - `deepgram.models.get` Get a specific Model read - `deepgram.models.list` List Models read **Project models 2** - `deepgram.project_models.get` Get a Project Model read - `deepgram.project_models.list` List Project Models read **Requests 2** - `deepgram.requests.get` Get a Project Request read - `deepgram.requests.list` List Project Requests read **Agent think models 1** - `deepgram.agent_think_models.list` List Agent Think Models read **Listen 1** - `deepgram.listen.transcribe_url` Transcribe and analyze pre-recorded audio and video write **Purchases 1** - `deepgram.purchases.list` List Project Purchases read **Read 1** - `deepgram.read.analyze` Analyze text content write **Speak 1** - `deepgram.speak.create` Text to Speech transformation write **Speak V2 1** - `deepgram.speak_v2.create` Flux Text to Speech (batch) write **Tokens 1** - `deepgram.tokens.grant` Token-based Authentication write Questions ## The Deepgram MCP server, answered. **Is there a Deepgram MCP server for Claude?** Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 50 Deepgram actions across agent configurations, agent variables, projects and distribution credentials, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Deepgram. **What do I need to connect Deepgram?** Deepgram API key (Console > Settings > API Keys). Plus your host. The free call account { op: "connections.requirements", service: "deepgram" } lists exactly what to paste. **Can an AI agent delete or change things in Deepgram?** Only if its key allows it, and only with an explicit confirmation. 8 Deepgram actions are destructive, including delete a Project Key, delete a Project Invite and delete a Project Member. 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 Deepgram API limit?** actionlake paces every call to the limits in the Deepgram service file: 100 calls a minute per connection. Repeated reads are answered from cache (20 Deepgram actions can be), which never reaches Deepgram. **What does a Deepgram action cost?** One upstream call, the only unit actionlake bills. A list that pages bills one call per page (14 Deepgram actions page). Cache hits, searches, dry runs and calls Deepgram 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 Deepgram API does it cover?** The Deepgram REST API 1.0.0 at api.deepgram.com by default, or the base URL set when you connect. It is built from Deepgram's documentation as read on 22 October 2026. 50 actions in 21 areas, each one in the signed service file (version 1.0.0). **Does actionlake keep my Deepgram 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 Deepgram 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 Deepgram Shares the most action names with - [OpenAI Admin 7](https://actionlake.com/connectors/openai-admin) - [Mistral AI 6](https://actionlake.com/connectors/mistral-ai) - [Portkey 4](https://actionlake.com/connectors/portkey) - [Langfuse 3](https://actionlake.com/connectors/langfuse) - [Speechmatics 2](https://actionlake.com/connectors/speechmatics) - [Braintrust 2](https://actionlake.com/connectors/braintrust) Joins with, on shared entities - [Unleash 3](https://actionlake.com/connectors/unleash) - [HaloPSA 2](https://actionlake.com/connectors/halopsa) - [Microsoft 365 Users 2](https://actionlake.com/connectors/microsoft-365-users) - [Procore 2](https://actionlake.com/connectors/procore) - [Infisical 2](https://actionlake.com/connectors/infisical) - [Rubrik Security Cloud 2](https://actionlake.com/connectors/rubrik-security-cloud) Browse - [All AI connectors](https://actionlake.com/connectors/category/ai) - [All connectors](https://actionlake.com/connectors) - [How actionlake compares](https://actionlake.com/compare) actionlake is independent. It is not made or endorsed by Deepgram; the name is the vendor's own. Counts are from the Deepgram service file, version 1.0.0. ## Give your agent Deepgram today. [Connect Deepgram 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/deepgram More: https://actionlake.com/llms.txt