--- title: "Tally MCP server for AI agents - actionlake" description: "Give Claude 38 Tally actions through one MCP server: analytics, forms, workspaces, folders. Your agent never holds the credential. 100,000 calls a month free." canonical: https://actionlake.com/connectors/tally updated: 2026-10-23 --- Connectors · Marketing & media # Tally MCP server for AI agents. actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Tally and the rest of your systems. It gives your agent 38 Tally actions (19 reads, 12 writes and 7 that wait for a confirmation) and holds the Tally credential itself, so the agent never does. It paces Tally's limits and records every call. [Connect Tally 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: "tally.workspaces.list", intent: "check which Tally account is connected" } # Retrieve a list of workspaces · read · 1 upstream call ``` - 38 actions in one signed file - 19 read look, never change - 12 write create and update - 7 wait for a yes destructive, confirmed first Set up ## Connect Tally 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 Tally. Bearer token. 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` Tally API key ``` account { op: "connections.requirements", service: "tally" } # 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: "tally.workspaces.list" } # retrieve a list of workspaces · read · 1 upstream call check { action: "tally.folders.create", input: { … } } # free: inputs, permissions, cost and confirmations, nothing sent ``` Tally at a glance **Sign-in** Bearer token. 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` **Limits we pace to** 100 calls a minute, per connection **API covered** Tally API (OpenAPI 1.0.0)`api.tally.so` **Built from** Tally's documentation, read 23 October 2026[developers.tally.so](https://developers.tally.so/api-reference/openapi.json) [developers.tally.so](https://developers.tally.so/api-reference/introduction) **Service file** Version 1.0.0, signed (Ed25519) **Cached reads** 19 of 19 reads, for up to 5 minutes; a write clears what it affects **Shared entities** 3, so ask can line Tally up with your other systems **Data** Processed and stored in Sydney, Australia. No US region yet Capabilities ## What an AI agent can do in Tally. 38 actions in 12 areas. Every one carries its effect, so a key can allow the reads and hold the rest. - **19** read look, never change - **12** write create and update - **7** destructive wait for a confirmation 1. ### Analytics 5 5 read · 0 write · 0 destructive Retrieve form dimensions · Retrieve form drop-off · Retrieve form metrics · Retrieve form submission analytics 2. ### Forms 5 2 read · 2 write · 1 destructive Retrieve a list of forms · Retrieve a form · Create a new form · Update a form 3. ### Workspaces 5 2 read · 2 write · 1 destructive Retrieve a list of workspaces · Retrieve a workspace · Create a new workspace · Update a workspace 4. ### Folders 4 1 read · 2 write · 1 destructive List folders · Create a new folder · Update a folder · Delete a folder 5. ### Webhooks 4 1 read · 2 write · 1 destructive List webhooks · Create a webhook · Update a webhook · Delete a webhook 6. ### Organization invites 3 1 read · 1 write · 1 destructive List organization invites · Create organization invites · Cancel an organization invite 7. ### Submissions 3 2 read · 0 write · 1 destructive List form submissions · Retrieve a form submission · Delete a form submission 8. ### Blocks 2 1 read · 1 write · 0 destructive List form blocks · Update form blocks **4 more areas · 7 actions** - Organization users **2** - Questions **2** - Webhook events **2** - Users **1** Top actions ## The Tally API, shaped for agents. The ids your agent types, what each does, and the one name it shares with other systems. 23 of Tally's 23 action names are shared with at least one other connector, so an agent learns them once. | Action | What it does | Effect | Same name in | | --- | --- | --- | --- | | `tally.users.me` Retrieve current user information | Retrieve current user information. | read | `identity.current_user.get` 307 connectors | | `tally.workspaces.list` Retrieve a list of workspaces | Retrieve a list of workspaces. | read | `work.workspace.list` 50 connectors | | `tally.folders.list` List folders | List folders. | read | `content.folder.list` 62 connectors | | `tally.forms.list` Retrieve a list of forms | Retrieve a list of forms. | read | `content.form.list` 36 connectors | | `tally.submissions.list` List form submissions | List form submissions. | read | `content.form_response.list` 20 connectors | | `tally.forms.get` Retrieve a form | Retrieve a form. | read | `content.form.get` 35 connectors | | `tally.workspaces.get` Retrieve a workspace | Retrieve a workspace. | read | `work.workspace.get` 41 connectors | | `tally.folders.create` Create a new folder | Create a new folder. | write | `content.folder.create` 62 connectors | | `tally.webhook_events.list` List webhook events | List webhook events. | read | `automation.webhook_delivery.list` 33 connectors | | `tally.forms.create` Create a new form | Create a new form. | write | `content.form.create` 26 connectors | | `tally.folders.delete` Delete a folder | Delete a folder. | destructive | `content.folder.delete` 46 connectors | | `tally.webhooks.create` Create a webhook | Create a webhook. | write | `automation.webhook.create` 209 connectors | Try it ## Prompts to paste into Claude. Each one names the Tally 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 Tally? List every user and their role. calls `tally.organization_users.list` 2. Write write Create a new folder in Tally. Show me exactly what you will send before you save it. calls `tally.folders.create` Governance for Tally ## Destructive actions wait for a yes. 7 Tally actions are destructive. These are all of them: - Delete a folder `tally.folders.delete` - Delete a form `tally.forms.delete` - Delete a workspace `tally.workspaces.delete` - Delete a form submission `tally.submissions.delete` - Delete a webhook `tally.webhooks.delete` - Remove user from organization `tally.organization_users.remove` - Cancel an organization invite `tally.organization_invites.cancel` 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 tally.folders.delete confirm_policy: **human** Delete a folder? **intent:** the user asked me to delete a folder run suspended · waiting for a named person · key _tally-agent_ cannot confirm itself In the console, or from an emailed signed link. a key for this connector ``` account { op: "keys.create", name: "tally-agent", allowed_actions: ["tally.*"], cap_calls: 2000, confirm_policy: "human_for_writes", approval_rules: [ { match: "tally.folders.delete", approver: "lead@example.com" }, { match: "tally.forms.delete", approver: "lead@example.com" }, { match: "tally.workspaces.delete", approver: "lead@example.com" } ] } ``` Illustrative. Scoped to Tally only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person. Cost ## What Tally costs on actionlake. Every Tally action is one upstream call, the only thing actionlake bills. Searching, `check`, `cost`, `account` and any call Tally 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 38 Tally actions - 38 actions page each page of a long list is one call - 19 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 Tally action. 38 actions by area: the id your agent calls, what it does, and its effect. **Analytics 5** - `tally.analytics.dimensions` Retrieve form dimensions read - `tally.analytics.drop_off` Retrieve form drop-off read - `tally.analytics.metrics` Retrieve form metrics read - `tally.analytics.submissions` Retrieve form submission analytics read - `tally.analytics.visits` Retrieve form visits read **Forms 5** - `tally.forms.create` Create a new form write - `tally.forms.delete` Delete a form destructive - `tally.forms.get` Retrieve a form read - `tally.forms.list` Retrieve a list of forms read - `tally.forms.update` Update a form write **Workspaces 5** - `tally.workspaces.create` Create a new workspace write - `tally.workspaces.delete` Delete a workspace destructive - `tally.workspaces.get` Retrieve a workspace read - `tally.workspaces.list` Retrieve a list of workspaces read - `tally.workspaces.update` Update a workspace write **Folders 4** - `tally.folders.create` Create a new folder write - `tally.folders.delete` Delete a folder destructive - `tally.folders.list` List folders read - `tally.folders.update` Update a folder write **Webhooks 4** - `tally.webhooks.create` Create a webhook write - `tally.webhooks.delete` Delete a webhook destructive - `tally.webhooks.list` List webhooks read - `tally.webhooks.update` Update a webhook write **Organization invites 3** - `tally.organization_invites.cancel` Cancel an organization invite destructive - `tally.organization_invites.create` Create organization invites write - `tally.organization_invites.list` List organization invites read **Submissions 3** - `tally.submissions.delete` Delete a form submission destructive - `tally.submissions.get` Retrieve a form submission read - `tally.submissions.list` List form submissions read **Blocks 2** - `tally.blocks.list` List form blocks read - `tally.blocks.replace` Update form blocks write **Organization users 2** - `tally.organization_users.list` List organization users read - `tally.organization_users.remove` Remove user from organization destructive **Questions 2** - `tally.questions.list` List form questions read - `tally.questions.update` Update a form question write **Webhook events 2** - `tally.webhook_events.list` List webhook events read - `tally.webhook_events.retry` Retry webhook event write **Users 1** - `tally.users.me` Retrieve current user information read Questions ## The Tally MCP server, answered. **Is there a Tally MCP server for Claude?** Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 38 Tally actions across analytics, forms, workspaces and folders, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Tally. **What do I need to connect Tally?** Tally API key. The free call account { op: "connections.requirements", service: "tally" } lists exactly what to paste. **Can an AI agent delete or change things in Tally?** Only if its key allows it, and only with an explicit confirmation. 7 Tally actions are destructive, including delete a folder, delete a form and delete a workspace. 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 Tally API limit?** actionlake paces every call to the limits in the Tally service file: 100 calls a minute per connection. Repeated reads are answered from cache (19 Tally actions can be), which never reaches Tally. **What does a Tally action cost?** One upstream call, the only unit actionlake bills. A list that pages bills one call per page (38 Tally actions page). Cache hits, searches, dry runs and calls Tally 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 Tally API does it cover?** The Tally API (OpenAPI 1.0.0) at api.tally.so. It is built from Tally's documentation as read on 23 October 2026. 38 actions in 12 areas, each one in the signed service file (version 1.0.0). **Does actionlake keep my Tally 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 Tally 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 Tally Shares the most action names with - [Formstack 16](https://actionlake.com/connectors/formstack) - [Jotform 12](https://actionlake.com/connectors/jotform) - [SurveySparrow 11](https://actionlake.com/connectors/surveysparrow) - [Typeform 10](https://actionlake.com/connectors/typeform) - [Vimeo 9](https://actionlake.com/connectors/vimeo) - [Fillout 7](https://actionlake.com/connectors/fillout) Joins with, on shared entities - [Gitea 3](https://actionlake.com/connectors/gitea) - [Forgejo 3](https://actionlake.com/connectors/forgejo) - [Mistral AI 3](https://actionlake.com/connectors/mistral-ai) - [Toggl Track 3](https://actionlake.com/connectors/toggl-track) - [Discord 3](https://actionlake.com/connectors/discord) - [Clockify 3](https://actionlake.com/connectors/clockify) Browse - [All Marketing & media connectors](https://actionlake.com/connectors/category/marketing-and-media) - [All connectors](https://actionlake.com/connectors) - [How actionlake compares](https://actionlake.com/compare) actionlake is independent. It is not made or endorsed by Tally; the name is the vendor's own. Counts are from the Tally service file, version 1.0.0. ## Give your agent Tally today. [Connect Tally 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/tally More: https://actionlake.com/llms.txt