[Cotlet](https://cotlet.dev/index.md) · [Integrations](https://cotlet.dev/integrations.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Security](https://cotlet.dev/security.md) · [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md) · [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [Contact](https://cotlet.dev/contact.md) · [Pricing](https://cotlet.dev/pricing.md) · [Sign up](https://cotlet.dev/signup) # Mode Analytics MCP server: Let your AI agent refresh your Mode reports. > Mode has a REST API for reports, queries, runs, exports, schedules and subscriptions, and no MCP server of its own that we found (checked 6 Nov 2026). Cotlet gives your agent 14 Mode tools over MCP for chat apps and over REST for scripts. There is no API key or developer setup, it works inside the ChatGPT and Claude apps, and it runs 24/7 on our servers. Connect Mode to Claude, ChatGPT or a script. Your agent runs reports, reads the result tables and fixes failing queries. It also sets up the Slack and email digests, with no API key to create. [MCP setup](https://cotlet.dev/integrations/mode-analytics-api-mcp-server.md#connect) [REST API guide](https://cotlet.dev/integrations/mode-analytics-api-mcp-server.md#rest-api) - Free 7-day trial, no card - Unofficial, not affiliated with Mode - Page: https://cotlet.dev/integrations/mode-analytics-api-mcp-server ## What can you automate in Mode? - Run a report and read the numbers - Find the report that answers a question - Diagnose a failed scheduled run - Schedule a Slack or email digest - Share a report to a channel once - Describe reports that have no description ## Does Mode have an MCP server or an API? - Mode's plan page lists "API access" under Pro and none under Studio. Admins create Workspace tokens; once an Admin turns on Member keys, each user can create their own. Both expire after 90 days by default. - Mode webhooks post three events (report created, run started, run finished) to a URL you choose. The payload is the event name and a link to the run. - The API has no endpoint to share a report once to Slack or email. It has schedules and subscriptions, and the Share button in the app does the one-off send. | What you need | Mode REST API | mode-mcp on GitHub | Cotlet | |---|---|---|---| | List reports, read SQL and run results | Yes, you write the calls | Yes | Yes | | Start a report run | Yes | No, left out on purpose | Yes, after your OK | | Create a schedule with Slack or email | Yes, schedules and subscriptions | No | Yes, after your OK | | Share a report once to Slack or email | No | No | Yes, after your OK | | Works in the ChatGPT and Claude apps without a developer setup | No, you build the agent layer | Local install with a key and secret | Yes | | Runs 24/7 without your computer | If you host your script | No, runs on your computer | Yes, hosted | Checked 6 Nov 2026. Sources: [Mode Developer: API introduction](https://mode.com/developer/api-reference/introduction/), [Mode Help: API tokens](https://mode.com/help/articles/api-tokens/), [Mode: Compare plans](https://mode.com/compare-plans/), [Mode Help: Webhooks](https://mode.com/help/articles/webhooks/), [github.com/nataliemona/mode_mcp](https://github.com/nataliemona/mode_mcp) ## How does Cotlet connect to Mode? 1. **Sign in to Mode.** Use your own account in its Cotlet Cloud Browser. 2. **Choose MCP or REST.** Connect your agent or create a Cotlet API key. 3. **Run your workflow.** Ask your agent or send an HTTP request. We never keep your Mode password, and no query change, schedule or Slack post happens until you approve it. ## Connect Mode to your agent or workflow Use MCP with your AI agent, or HTTP requests in n8n, Make, Zapier and scripts. Follow the MCP setup below or jump to the REST guide. 1. **Sign in to Mode.** Sign up, sign in to Mode in its Cloud Browser, then press Enable for agents. 2. **Add the Cotlet address.** Add https://cotlet.dev/mcp/v1 as an MCP server or connector in your agent. 3. **Approve the connection.** Chat apps ask you to sign in to Cotlet. Editors, n8n and scripts use an API key from the console. One shared address, `https://cotlet.dev/mcp/v1`, also carries Mode next to your other apps. If you enable Mode after connecting, refresh the connector so the new tools show up. Claude: ``` Settings > Connectors > Add custom connector URL: https://cotlet.dev/mcp/v1/connect Claude Code: claude mcp add --transport http cotlet-mode-analytics \ https://cotlet.dev/mcp/v1 \ --header "Authorization: Bearer $COTLET_API_KEY" ``` ChatGPT: ``` Settings > Apps & Connectors > Create MCP server URL: https://cotlet.dev/mcp/v1/connect Authentication: OAuth ``` Cursor: ``` // ~/.cursor/mcp.json { "mcpServers": { "cotlet-mode-analytics": { "url": "https://cotlet.dev/mcp/v1", "headers": { "Authorization": "Bearer ${env:COTLET_API_KEY}" } } } } ``` Codex: ``` # ~/.codex/config.toml [mcp_servers.cotlet-mode-analytics] url = "https://cotlet.dev/mcp/v1" bearer_token_env_var = "COTLET_API_KEY" ``` n8n: ``` MCP Client Tool (inside an AI Agent) Transport: HTTP Streamable URL: https://cotlet.dev/mcp/v1 Auth: Bearer, Tool: mode_analytics_read ``` Make, Zapier: ``` Make: MCP Client > Call a tool Zapier: MCP Client by Zapier > Run Tool Server URL: https://cotlet.dev/mcp/v1 Token: Tool: mode_analytics_write ``` ## How to use the Mode REST API ### Create your Cotlet API key Sign in to your Mode account in its Cotlet Cloud Browser and enable the app for agents. Editing and scheduling a report need edit access to it in Mode. Create a Cotlet API key with access to Mode and its read operations. Store it as `COTLET_API_KEY` in your environment or automation platform's credential store. You do not create a Mode token. ### Make your first Mode API request cURL: list_reports: ``` curl "https://cotlet.dev/api/v1/mode-analytics/reports?workspace=acme-analytics&collection=Growth" \ -H "Authorization: Bearer $COTLET_API_KEY" ``` ### Read reports and continue the list A successful REST call puts the tool output in `result`. This illustrative response excerpt omits call IDs, messages and credit details. Illustrative response excerpt: ``` { "status": "success", "app": "mode-analytics", "tool": "list_reports", "result": { "reports": [ { "token": "a1b2c3d4e5f6", "title": "Weekly signups by channel", "description": "Signups per channel, last 8 weeks", "collection": "Growth", "last_edited": "2026-11-03", "latest_run": "succeeded" }, { "token": "b7c8d9e0f1a2", "title": "Trial to paid conversion", "description": "", "collection": "Growth", "last_edited": "2026-09-18", "latest_run": "succeeded" } ], "next_cursor": null } } ``` Read `result.reports` and pass `result.next_cursor` unchanged as `cursor` until it is empty. Keep the report `token` in your workflow so later runs update the same report. Run results come back as column names and rows. When a result is cut at your `limit`, the response says so with `truncated`. ### Mode workflows for agents and automations | Tool | Connect through | Example workflow | |---|---|---| | n8n | HTTP Request | Call `run_report` on a schedule, then `get_run_results`, and write the rows to a sheet or database. | | Python or Node.js | REST API | Page through `list_report_runs` for each report and collect failed runs with their error text. | | Make | HTTP > Make a request | Call `list_schedules` and post a weekly list of what each report delivers and where. | Send `Authorization: Bearer ` in request headers. You configure the schedule, destination and record comparisons. Cotlet reads and changes Mode; your workflow steps write to your chosen destination. These HTTP workflows do not require a native Cotlet connector or a prebuilt template. The [API and MCP reference](https://cotlet.dev/integrations/mode-analytics-api-mcp-server.md#tools) lists operations and inputs. The [REST API guide](https://cotlet.dev/docs/api.md) explains authentication, errors and approvals. ## Mode API endpoints and MCP tools ### Collections and reports Reports are found by Collection or by words in the title. No tool deletes a report; archive and unarchive are both here. - **List collections** (`list_collections`, read): Lists the Collections of a Workspace that your account can open. - **List reports** (`list_reports`, read): Lists the reports in a Collection or finds reports by words in the title. - **Get report** (`get_report`, read): Reads one report: title, description, Collection, creator and its queries. - **Get query** (`get_query`, read): Reads the SQL of one query in a report. - **Update report** (`update_report`, write): Changes the title or the description of a report. - **Archive report** (`archive_report`, write): Archives a report so it leaves its Collection. - **Unarchive report** (`unarchive_report`, write): Brings an archived report back. ### Runs, results and query edits A run uses your own data source. Results can be cut at a row limit, and the answer says when they were. - **List report runs** (`list_report_runs`, read): Lists the runs of a report, with the state of each. - **Get run results** (`get_run_results`, read): Reads the result table of one query in a report run. - **Run report** (`run_report`, write, asks first): Starts a new run of a report and waits for it to finish. - **Update query** (`update_query`, write, asks first): Changes the name or the SQL of one query in a report. ### Schedules and sharing Slack needs Mode connected to your Slack, and a private channel needs the @Mode bot added. Email recipients must be Workspace members or in a claimed domain unless external sharing is on. - **List schedules** (`list_schedules`, read): Lists the schedules of a report with their delivery settings. - **Create schedule** (`create_schedule`, write, asks first): Adds a schedule to a report that runs it and delivers the results. - **Share report** (`share_report`, write, asks first): Sends a report once to a Slack channel or to email addresses. Inputs, REST path and example response of every tool: https://cotlet.dev/integrations/mode-analytics-api-mcp-server#tools ## Who can see my Mode session, and how do I revoke it? - **What we store.** Your signed-in Mode profile, encrypted with AES-256-GCM, in the EU. Not the password. - **What your agent gets.** The 14 Mode tools. Never the cookie. - **What the session sees.** Your Workspace: the reports, queries and schedules you can open. - **What no tool touches.** Data sources, members, billing, API keys, password and two-factor. - **If Mode asks to verify.** A new device may need a code. You type it in, we never do. - **How to cut access.** Disable for agents or reset the browser in the console, or sign out in Mode. Our site scores A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory ([live results](https://cotlet.dev/security.md)). There is no SOC 2 report or third-party pentest yet. ## Whose permissions does the agent use? Mode's own Member API keys follow each user's access, and an Admin has to switch them on first (Mode Help: API tokens, checked 6 Nov 2026). Cotlet works in your signed-in Mode session, so it follows your access the same way and needs no key. > Schedules and Slack or email sharing follow your Mode plan. Mode's plan page lists them under Pro, not Studio (checked 6 Nov 2026). How your Mode access carries over: - Your own Mode account, signed in by you - Edit access to a report is needed to change or schedule it - One Cloud Browser with its own cookies for your Workspace - Query edits, runs, schedules and shares wait for your OK - No tool deletes a report or a query ## What happens when Mode changes? - **12 h** between tests of the Mode tools - **$0** for a call to a Mode tool paused for repair When Mode moves a button or renames a field, the fix happens on our side and your prompts keep working. [status.cotlet.dev](https://status.cotlet.dev) watches the site, console and API every 3 minutes. ## Approvals, undo and mistakes 1. **Reads the report.** Title, queries and the state of the latest run. 2. **Waits for your OK.** The run or schedule shows up in your Cotlet console first. 3. **Does it in Mode.** Starts the run, saves the query or sets the schedule. 4. **Reports the result.** Run state and time, or the old SQL, or where it delivers. | Action | Undo | |---|---| | Run a report | No, but the run is kept in the report's run history | | Edit a query | Put the old SQL back; the tool returns it | | Change a title or description | Change it back; the tool returns the old text | | Archive a report | Unarchive it with one call | | Create a schedule | Delete the schedule in Mode | | Share to Slack or email | No, the post or email is out | 4 of 14 tools ask first: run_report, update_query, create_schedule and share_report. Reads, archiving and title changes reach no one, so they run at once. Switch the wait off per tool for a scheduled run. > A schedule keeps running until the report or the schedule is deleted. MCP call: ``` { "name": "run_report", "arguments": { "report": "a1b2c3d4e5f6", "parameters": { "weeks": 8 } } } ``` REST: ``` curl -X POST https://cotlet.dev/api/v1/mode-analytics/report/run \ -H "Authorization: Bearer $COTLET_API_KEY" \ -H "Content-Type: application/json" \ -d '{"report":"a1b2c3d4e5f6","parameters":{"weeks":8}}' ``` Tool output: ``` { "run": "r9p8o7i6u5y4", "state": "succeeded", "started": "2026-11-05T09:12:03Z", "finished": "2026-11-05T09:12:31Z" } ``` Scripts and cron jobs reach the same tools over REST with the same key and price. A failed call costs nothing. The tools table lists the REST path of each tool. ## How much does the Mode MCP server cost? **About $16 a month** for one analyst refreshing a report every workday, 2,800 credits. Your Mode plan is billed by Mode as before. | Job | Calls | Credits | |---|---|---| | Refresh a report and read the numbers, workdays | 3 × 20 | 600 | | Check failed scheduled runs, weekly | 3 × 4 | 120 | | Find the report that answers a question | 5 × 8 | 400 | | New Slack digest schedule | 2 × 3 | 60 | | Archive old reports, monthly | 12 × 1 | 120 | | Cloud Browser, 30 days | | 1,500 | | Total | | 2,800 | - Free 7-day trial, no card - 10 credits per successful call, MCP or REST - 50 credits a day for the Cloud Browser - No Mode API token to create or rotate The month is our example: about 130 calls, with one report refreshed on 20 workdays. We found no public figure for a typical Mode workspace. Dollars at the $29 pack rate. ## Mode MCP server on GitHub, the Mode API or hosted: which to use | Option | What it does | Where it stops | |---|---|---| | [nataliemona/mode_mcp](https://github.com/nataliemona/mode_mcp) | Python MCP server on the Mode API, 15 tools: browse, read results, create and edit reports and queries, archive. MIT licence. | Runs on your computer with a token and secret. No run, schedule or share tool. 0 stars, last commit 16 Oct 2026. | | [Pipedream Mode MCP](https://mcp.pipedream.com/app/mode) | A hosted server on Pipedream Connect. | Its page showed no list of Mode tools when we checked. | | [Mode REST API](https://mode.com/developer/api-reference/introduction/) | Official. Reports, queries, runs, exports, schedules and subscriptions, with JSON or CSV results. | You write and host the code. Mode's plan page lists API access under Pro. No one-off share to Slack or email. | | [Mode webhooks](https://mode.com/help/articles/webhooks/) | Official. Posts to your URL when a report is created or a run starts or finishes. | The payload is the event name and a link to the run. | If you have a developer and want one narrow job, the Mode API or the GitHub server is free to use. Cotlet adds what they leave to you: no API key to create, a connector that works in the ChatGPT and Claude apps, hosting around the clock, one account for many apps, and run, schedule and share tools that ask before they act. ## Who runs Cotlet Take Group sp. z o.o. runs Cotlet. It is a software company registered in Poland, EU (VAT PL6342984273), working since 2019, founded by Bart Krawczyk (Co-founder, CTO) and Jake Slugocki (Co-founder, SEO, sales and marketing). Write to contact@cotlet.dev with questions about the Mode tools. ## Mode Analytics MCP: questions ### How do I connect Mode Analytics to ChatGPT or Claude? Sign up at cotlet.dev, log in to Mode Analytics once in its Cloud Browser and add Cotlet to ChatGPT or Claude, following the steps in your console. No API key is needed. ChatGPT and Claude then work in your Mode Analytics account through Cotlet, in their phone apps too. ### What can ChatGPT do in Mode Analytics? With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in Mode Analytics: refresh a report and read the numbers; send a report to Slack every Monday; find the report that answers a question. You ask in plain words, and anything that reaches other people waits for your OK first. ### Can I use the Mode API without an AI agent? Yes. Call Cotlet's REST API from a script or an HTTP step in n8n, Make or Zapier with your Cotlet key. MCP is the alternative for AI agents; you do not need to connect an agent to use REST. ### How do I get access? Create a free account at https://cotlet.dev, open Mode under Integrations in the console and sign in to Mode in its Cloud Browser. The trial starts with your first app, no card asked. ### Do I need a paid Mode plan or an API token? No token is needed, because Cotlet works in your own signed-in Mode account. Mode requires a paid plan for its own API. Its plan comparison lists schedules and Slack and email sharing under Pro, and the Studio column lists no API access, so those tools follow your plan. Mode: Compare plans, checked 5 Nov 2026. ### Who can schedule a report or share it to Slack? Anyone with edit access to the report can schedule it. Sharing to Slack needs Mode connected to your Slack workspace, and a private channel needs the @Mode bot added first. Without the access, the call fails and nothing is sent. Mode Help: Report scheduling and sharing, checked 5 Nov 2026. ### What happens when a scheduled report fails? Mode emails the report creator, the schedule creator and the last editor on every failed run until the error is fixed or the schedule is deleted. Your agent can read the failed run with list_report_runs and the SQL with get_query. Mode Help: Report scheduling and sharing, checked 5 Nov 2026. ### Does Mode have webhooks? Yes. Mode posts to a URL you choose when a report is created or a run starts or finishes, with the event name and a link to the run (Mode Help: Webhooks, checked 6 Nov 2026). Cotlet does not receive them; run your agent on a schedule or point the webhook at your own workflow. ### Can the agent delete a report? No. It can archive a report and bring it back with unarchive_report. No tool deletes a report or a query. ### Is the MCP server different from the REST API? Only the door is different. Both expose the same 14 tools, inputs and answers, with one API key and one price. Agents use MCP; scripts and HTTP steps use REST. ### Is Cotlet affiliated with Mode? No. Cotlet is independent and not affiliated with Mode Analytics, Inc. or ThoughtSpot. --- Give your AI agents your signed-in browser. **Product:** [Integrations](https://cotlet.dev/integrations.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Pricing](https://cotlet.dev/pricing.md) · [Security](https://cotlet.dev/security.md) **Resources:** [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [GitHub](https://github.com/cotletdev/cotlet) **Solutions:** [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md) **Company:** [About](https://cotlet.dev/about.md) · [AI info: company facts](https://cotlet.dev/ai-info.md) · [Contact](https://cotlet.dev/contact.md) **Legal:** [Terms of service](https://cotlet.dev/terms) · [Privacy policy](https://cotlet.dev/privacy) · [Refund policy](https://cotlet.dev/refunds) · [Acceptable use](https://cotlet.dev/acceptable-use) · [Cookie policy](https://cotlet.dev/cookies) · [DPA](https://cotlet.dev/dpa) · [Subprocessors](https://cotlet.dev/subprocessors) **Elsewhere:** [Status page](https://status.cotlet.dev) · [Cotlet on GitHub](https://github.com/cotletdev) · [Cotlet on X](https://x.com/cotletdev) · [Cotlet on LinkedIn](https://www.linkedin.com/company/cotletdev) · [Cotlet on Product Hunt](https://www.producthunt.com/products/cotlet) · [Cotlet on Crunchbase](https://www.crunchbase.com/organization/cotlet) · [Cotlet on SaaSHub](https://www.saashub.com/cotlet) Cotlet.dev is built by Bart Krawczyk and Jake Slugocki, the founders of Take Group sp. z o.o., ul. Wincentego Janasa 4, 40-855 Katowice, Poland. KRS 0000871398, NIP 6342984273, VAT EU: PL6342984273. [About us](https://cotlet.dev/about.md) Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners.