[Cotlet](https://cotlet.dev/index.md) · [Integrations](https://cotlet.dev/integrations.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Use cases](https://cotlet.dev/use-cases.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) # Lichess API and MCP server > Lichess has a full, free REST API with personal and OAuth tokens, but no official MCP server (checked 17 Oct 2026). The API covers teams, Arena and Swiss tournaments, studies, broadcasts, challenges and game export, so the gap is a hosted, maintained MCP with no token to create, scope or revoke. Free, open-source chess server run by a non-profit: games, Arena and Swiss tournaments, teams, studies and broadcasts of over-the-board events. ## What is the Lichess API? Cotlet's Lichess API exposes 15 endpoints for your own Lichess account: get my profile, list teams of a user, list team join requests, list Arena tournaments, get Arena results, list studies of a user, export games of a user, list broadcasts of a user, accept a team join request, decline a team join request, send a team update, create an Arena tournament, import a PGN into a study, create a broadcast tournament and create a broadcast round. The get_account endpoint returns return the signed-in Lichess profile: username, title, ratings per game type and account dates. Each endpoint takes simple JSON inputs like username, team_id or name and works both as an operation of the lichess_read or lichess_write MCP tool for agents and as a REST call for scripts. - **Category:** [Creators & communities](https://cotlet.dev/integrations/category/creators-communities.md) - **Endpoints:** 15 (8 read, 7 write) - **Updated:** 2026-10-22 Lichess has a full, free REST API with personal and OAuth tokens, but no official MCP server (checked 17 Oct 2026). Cotlet is a hosted MCP server and REST API for Lichess with 15 endpoints (8 read, 7 write): you sign in once in your own cloud browser, your AI agent does the work. ## Does Lichess have an official API? Lichess has a full, free REST API with personal and OAuth tokens, but no official MCP server (checked 17 Oct 2026). The API covers teams, Arena and Swiss tournaments, studies, broadcasts, challenges and game export, so the gap is a hosted, maintained MCP with no token to create, scope or revoke. | Task | Lichess official | Cotlet | |---|---|---| | Read your profile and list your teams | Yes: API; a token with the right scope, no MCP server | Yes | | List and accept or decline team join requests | Yes: API; needs a team leader token (team:read to list, team:lead to decide) | Yes | | Send an update to all team members | Yes: API; team leader with the Updates permission | Yes | | Create an Arena tournament | Yes: API; up to 12 public or 24 private tournaments a day | Yes | | Read Arena tournament results | Yes: API; streamed as ndjson, no sign-in needed | Yes | | Export your games as PGN or JSON | Yes: API; throttled at 60 games per second for your own games | Yes | | Import a PGN into a study | Yes: API; a study holds at most 64 chapters | Yes | | Create a broadcast and its rounds | Yes: API; a token with the study:write scope | Yes | Sources: [Lichess API reference](https://lichess.org/api), [Lichess API documentation source (GitHub)](https://github.com/lichess-org/api), [Lichess: How to use Lichess Broadcasts](https://lichess.org/broadcast/help), [Lichess: Fair Play](https://lichess.org/page/fair-play) ## For AI agents ```text Lichess has a full, free REST API with personal and OAuth tokens, but no official MCP server (checked 17 Oct 2026). The API covers teams, Arena and Swiss tournaments, studies, broadcasts, challenges and game export, so the gap is a hosted, maintained MCP with no token to create, scope or revoke. Cotlet provides a hosted MCP server and REST API for Lichess: 15 tools (8 read, 7 write). Access Sign up at https://cotlet.dev/app/signup?app=lichess, then request the app and create API keys in the Cotlet console. MCP server https://cotlet.dev/mcp/v1 MCP tools lichess_read, lichess_write, reads and writes apart; call one with {"operation": "", "arguments": {...}} REST base https://cotlet.dev/api/v1/lichess, each operation at its own route, e.g. POST /api/v1/lichess/teams/{team_id}/update Auth Authorization: Bearer . Listing endpoints and schemas needs no key; calling an endpoint needs one. Over MCP the input schemas come with sign-in. Operations get_account, list_user_teams, list_team_join_requests, list_arena_tournaments, get_arena_results, list_studies, export_user_games, list_broadcasts, accept_team_join_request, decline_team_join_request, send_team_update, create_arena_tournament, import_pgn_to_study, create_broadcast, create_broadcast_round Confirm accept_team_join_request, decline_team_join_request, send_team_update, create_arena_tournament, import_pgn_to_study, create_broadcast, create_broadcast_round (by default the user approves each call; the user can switch this off per tool, e.g. for scheduled automations) Markdown https://cotlet.dev/integrations/lichess-api-mcp-server.md How access works: 1. The user signs up at https://cotlet.dev/app/signup?app=lichess, requests Lichess in the Cotlet console and creates an API key there. 2. The user signs in to Lichess once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables Lichess for agents. An agent cannot do this step. 3. The API key goes into the MCP client or the REST call as a bearer token. Fits: people who want a hosted Lichess server that someone else maintains, including non-developers. Developers who prefer to run and fix code on their own computer can use an open-source Lichess MCP server instead. Policy: Cotlet never stores passwords, never solves CAPTCHAs, never bypasses MFA. Company: legal details in the Terms of service at https://cotlet.dev/terms. Contact contact@cotlet.dev. Sign-in: the user signs in to Lichess in their own Cloud Browser, a Chrome Cotlet runs for them in the EU; password saving is off, the profile is AES-256-GCM encrypted, and agents get Lichess only after the user enables it. Calls are requests from that browser's IP with its cookies, each listed in the user's Background activity. Disable for agents, signing out in the browser or Reset browser cuts access. Cotlet is run by Take Group sp. z o.o. (EU VAT PL6342984273). API key: holds no Lichess login or cookies, only asks Cotlet to run a tool. Each key is scoped to chosen apps and tools, read only or read and write. Actions that reach other people wait for the user's approval by default, so a leaked key cannot post or message as the user. Every call is in the activity log; deleting the key ends access at once. Terms: the user stays responsible for following Lichess's terms; Cotlet is not affiliated with Lichess. ``` ## What can an AI agent do in Lichess? Cotlet is best for chess club organisers, team leaders and coaches who need tournaments, team updates, broadcasts and study imports handled by an agent without running or fixing a server. - **[Schedule a weekly Arena tournament](https://cotlet.dev/integrations/lichess-api-mcp-server/schedule-weekly-arena-tournament.md)** (runs: weekly): "Every Monday, create a public 3+0 rated Arena for my club next Friday at 19:00, 60 minutes long, named "Friday Blitz Night". Skip it if one with that name is already scheduled." → `list_arena_tournaments`, `create_arena_tournament` - **[Run a broadcast of an over-the-board event](https://cotlet.dev/integrations/lichess-api-mcp-server/run-a-chess-broadcast.md)** (runs: weekly): "Create a private Lichess broadcast for our club championship, add Round 1 fed from the PGN URL below, and give me the link to share." → `list_broadcasts`, `create_broadcast`, `create_broadcast_round` - **Accept or decline team join requests** (runs: daily): "Go through pending join requests for my team riverside-chess. Accept anyone whose message mentions our club or a local school, decline obvious spam, and leave the rest for me with a one-line reason." → `list_team_join_requests`, `accept_team_join_request`, `decline_team_join_request` - **Send a weekly update to your team** (runs: weekly): "Every Friday at 12:00, send my team riverside-chess an update with tonight's tournament link and the three best results from last week." → `list_arena_tournaments`, `get_arena_results`, `send_team_update` - **Back up your Lichess games** (runs: weekly): "Export my rated blitz and rapid games since last Sunday as PGN with clocks and evaluations, and tell me how many there are and my record." → `export_user_games` - **Load game collections into a study**: "Import the PGN below into my study "Club Games 2026" as new chapters, then list the study's chapter count." → `list_studies`, `import_pgn_to_study` ## Can Lichess automations run on a schedule in n8n, Make or Zapier? Yes. Cotlet does not replace your automation platform: it gives it a Lichess connection it does not have, with the same API key as your agent. Write actions ask for your OK by default; switch that off in your dashboard for the tools you choose, for example to schedule a weekly arena tournament, and the schedule runs on its own. Cotlet runs in the cloud, so it keeps going while your computer is off. | Where | How to connect | How to schedule | |---|---|---| | Your AI agent | Add https://cotlet.dev/mcp/v1 with your API key. | A scheduled agent run, for example a Claude Code routine. | | n8n | MCP Client node with https://cotlet.dev/mcp/v1, or an HTTP Request node with the endpoint's method and URL, such as GET https://cotlet.dev/api/v1/lichess/arena-tournaments. | Schedule Trigger node. | | Make | HTTP module: the endpoint's method and URL with an Authorization: Bearer header, and a JSON body for POST, PUT and PATCH. | Scenario schedule. | | Zapier | Webhooks by Zapier, Custom Request: the same method, URL, header and body. | Schedule by Zapier trigger. | | Your own script | GET https://cotlet.dev/api/v1/lichess/arena-tournaments with your API key. | cron or GitHub Actions. | ## Tools **For AI agents:** Every endpoint and its schema is public. The 15 endpoints on this page, with parameters and example responses, can be listed without an account. Calling one returns 401 without an API key and 403 while the key has no access to Lichess. ### get_account Return the signed-in Lichess profile: username, title, ratings per game type and account dates. Access: read. REST: `GET /api/v1/lichess/account`. MCP: `lichess_read → get_account`. No parameters. Returns the username, an optional title, one rating per game type (bullet, blitz, rapid, classical, correspondence), the account creation date and the count of games. Call it first to learn which account the agent works as. It reads only and changes nothing. Example response: ```json { "username": "club_captain", "title": null, "created_at": "2019-03-14T10:22:00Z", "ratings": { "bullet": 1710, "blitz": 1824, "rapid": 1790, "classical": 1755, "correspondence": 1600 }, "games_played": 6412 } ``` ### list_user_teams List the teams a user belongs to, with member counts and which ones they lead. Access: read. REST: `GET /api/v1/lichess/user-teams`. MCP: `lichess_read → list_user_teams`. | Parameter | Type | Required | Description | |---|---|---|---| | `username` | string | no | Lichess username. Defaults to the signed-in account. | Returns each team with its ID, name, member count and the leaders, which tells the agent which teams the account can manage. Other team tools take the team_id from here. It reads only. Example response: ```json { "teams": [ { "team_id": "riverside-chess", "name": "Riverside Chess Club", "members": 148, "leaders": [ "club_captain", "treasurer_anna" ] }, { "team_id": "weekend-blitz", "name": "Weekend Blitz", "members": 2310, "leaders": [ "blitz_host" ] } ] } ``` ### list_team_join_requests List pending requests to join a team you lead, with each applicant's message and profile. Access: read. REST: `GET /api/v1/lichess/team-join-requests`. MCP: `lichess_read → list_team_join_requests`. | Parameter | Type | Required | Description | |---|---|---|---| | `team_id` | string | yes | Team ID from list_user_teams, e.g. 'coders' for lichess.org/team/coders. | | `declined` | boolean | no | Return the declined requests instead of the pending ones. Default false. | Returns each request with the applicant username, the message they wrote, their ratings and account age. Only a leader of the team can read the requests. It reads only and does not change the queue. Example response: ```json { "requests": [ { "username": "maya_plays", "message": "Hi, I live in Riverside and play in the Tuesday school club.", "rating_blitz": 1432, "account_created": "2024-08-02" }, { "username": "bonus_link_77", "message": "Visit my site for free chess lessons", "rating_blitz": 1500, "account_created": "2026-10-16" } ], "total": 2 } ``` ### list_arena_tournaments List recently active, running and upcoming Arena tournaments from the Lichess schedule. Access: read. REST: `GET /api/v1/lichess/arena-tournaments`. MCP: `lichess_read → list_arena_tournaments`. | Parameter | Type | Required | Description | |---|---|---|---| | `created_by` | string | no | Only tournaments created by this username. | Returns each tournament with its ID, name, creator, clock, length in minutes, rated flag, variant, player count and start time, grouped as upcoming, started and finished. Use it to avoid creating a duplicate. It reads only. Example response: ```json { "upcoming": [ { "tournament_id": "Qx7pLm2a", "name": "Friday Blitz Night", "created_by": "club_captain", "clock": "3+0", "minutes": 60, "rated": true, "variant": "standard", "players": 12, "starts_at": "2026-10-23T19:00:00Z" } ], "started": [], "finished": [] } ``` ### get_arena_results Return the final standings of an Arena tournament: rank, score, rating and performance per player. Access: read. REST: `GET /api/v1/lichess/tournaments/{tournament_id}/arena-results`. MCP: `lichess_read → get_arena_results`. | Parameter | Type | Required | Description | |---|---|---|---| | `tournament_id` | string | yes | Arena tournament ID from list_arena_tournaments. | | `max_players` | integer | no | Return at most this many players. Default all. | Returns players sorted by rank, best first, each with username, score, rating and performance. Results of a running tournament can shift while they are read, so use it on a finished one. It reads only. Example response: ```json { "tournament_id": "Qx7pLm2a", "players": [ { "rank": 1, "username": "rook_and_roll", "score": 46, "rating": 1902, "performance": 1988 }, { "rank": 2, "username": "maya_plays", "score": 41, "rating": 1432, "performance": 1655 }, { "rank": 3, "username": "club_captain", "score": 38, "rating": 1824, "performance": 1790 } ] } ``` ### list_studies List the studies of a user with their IDs, names and update dates. Access: read. REST: `GET /api/v1/lichess/studies`. MCP: `lichess_read → list_studies`. | Parameter | Type | Required | Description | |---|---|---|---| | `username` | string | no | Lichess username. Defaults to the signed-in account, which also returns private and unlisted studies. | Returns each study's ID, name, creation date and last update, most recent first. For the signed-in account it includes private and unlisted studies; for another user only public ones. It reads only. Example response: ```json { "studies": [ { "study_id": "Wk3bPzQa", "name": "Club Games 2026", "created_at": "2026-01-09T18:00:00Z", "updated_at": "2026-10-11T20:41:00Z" }, { "study_id": "Hn8eLr2c", "name": "Opening Repertoire: London System", "created_at": "2025-11-22T09:15:00Z", "updated_at": "2026-09-02T07:30:00Z" } ] } ``` ### export_user_games Export the games of a user as PGN or JSON, newest first, filtered by date, game type, color and opponent. Access: read. REST: `GET /api/v1/lichess/user-games/export`. MCP: `lichess_read → export_user_games`. | Parameter | Type | Required | Description | |---|---|---|---| | `username` | string | yes | Lichess username, e.g. 'club_captain'. | | `since` | string | no | Only games played since this ISO date. | | `until` | string | no | Only games played until this ISO date. | | `max` | integer | no | Return at most this many games. Default all, which can be very long. | | `perf_type` | string | no | Comma list of speeds or variants, e.g. blitz,rapid,classical. | | `rated` | boolean | no | Only rated (true) or only casual (false) games. | | `color` | string | no | Only games as this color: white or black. | | `vs` | string | no | Only games against this opponent. | | `format` | string | no | pgn or json. Default json. | | `include_clocks` | boolean | no | Add clock times to each move. Default false. | | `include_evals` | boolean | no | Add analysis evaluations when the game was analysed. Default false. | Returns the games newest first, each with ID, players, result, speed, rated flag, opening name and date, plus the PGN when format is pgn. Lichess throttles the stream, at 60 games per second for your own games, so set max for long histories. It reads finished games only and never touches a live game. Example response: ```json { "count": 2, "games": [ { "game_id": "q8Zr1TnD", "played_at": "2026-10-15T20:12:00Z", "speed": "blitz", "rated": true, "white": "club_captain", "black": "rook_and_roll", "winner": "black", "status": "resign", "opening": "Sicilian Defense: Najdorf Variation" }, { "game_id": "b4Hs9MwE", "played_at": "2026-10-14T19:48:00Z", "speed": "rapid", "rated": true, "white": "maya_plays", "black": "club_captain", "winner": "black", "status": "mate", "opening": "Queen's Gambit Declined" } ] } ``` ### list_broadcasts List the broadcasts a user created, with their rounds and start dates. Access: read. REST: `GET /api/v1/lichess/broadcasts`. MCP: `lichess_read → list_broadcasts`. | Parameter | Type | Required | Description | |---|---|---|---| | `username` | string | no | Lichess username. Defaults to the signed-in account, which also returns private and unlisted broadcasts. | | `page` | integer | no | Page number, starting at 1. | Returns broadcasts newest first, each with its ID, name, visibility and rounds with start dates. Use it to find an existing broadcast before adding a round. It reads only. Example response: ```json { "page": 1, "broadcasts": [ { "broadcast_id": "Zp4tNc6h", "name": "Riverside Chess Club Championship 2026", "visibility": "private", "rounds": [ { "round_id": "Kf3nQ8vD", "name": "Round 1", "starts_at": "2026-10-24T10:00:00Z" } ] } ] } ``` ### accept_team_join_request Accept one person's request to join a team you lead. Access: write, asks the user first. REST: `POST /api/v1/lichess/teams/{team_id}/join-request/accept`. MCP: `lichess_write → accept_team_join_request`. | Parameter | Type | Required | Description | |---|---|---|---| | `team_id` | string | yes | Team ID from list_user_teams, e.g. 'coders' for lichess.org/team/coders. | | `username` | string | yes | Applicant username from list_team_join_requests. | Adds the applicant to the team and returns ok. Needs a team leader role. The applicant becomes a member of the team, so it reaches another person. By default you confirm each call; you can switch that off for this tool. Example response: ```json { "ok": true, "team_id": "riverside-chess", "username": "maya_plays", "members": 149 } ``` ### decline_team_join_request Decline one person's request to join a team you lead. Access: write, asks the user first. REST: `POST /api/v1/lichess/teams/{team_id}/join-request/decline`. MCP: `lichess_write → decline_team_join_request`. | Parameter | Type | Required | Description | |---|---|---|---| | `team_id` | string | yes | Team ID from list_user_teams, e.g. 'coders' for lichess.org/team/coders. | | `username` | string | yes | Applicant username from list_team_join_requests. | Removes the request from the pending list and moves it to the declined list, which list_team_join_requests returns with declined set to true. Needs a team leader role. The applicant is turned away, so it reaches another person. By default you confirm each call; you can switch that off for this tool. Example response: ```json { "ok": true, "team_id": "riverside-chess", "username": "bonus_link_77", "status": "declined" } ``` ### send_team_update Send a message to all members of a team you lead. Access: write, asks the user first. REST: `POST /api/v1/lichess/teams/{team_id}/update`. MCP: `lichess_write → send_team_update`. | Parameter | Type | Required | Description | |---|---|---|---| | `team_id` | string | yes | Team ID from list_user_teams, e.g. 'coders' for lichess.org/team/coders. | | `message` | string | yes | The update text to send to every member. | Posts the update to all members and returns ok. You must be a team leader with the Updates permission. It reaches every member of the team at once and cannot be recalled. By default you confirm each call; you can switch that off for this tool. Example response: ```json { "ok": true, "team_id": "riverside-chess", "recipients": 148 } ``` ### create_arena_tournament Create a public or private Arena tournament with a clock, length, start time and entry rules. Access: write, asks the user first. REST: `POST /api/v1/lichess/arena-tournaments`. MCP: `lichess_write → create_arena_tournament`. | Parameter | Type | Required | Description | |---|---|---|---| | `name` | string | no | Tournament name, 2 to 30 characters. Empty gives a random Grandmaster name. | | `clock_time` | number | yes | Initial time in minutes, e.g. 3. | | `clock_increment` | integer | yes | Increment in seconds, e.g. 0. | | `minutes` | integer | yes | Length of the tournament in minutes, e.g. 60. | | `start_date` | string | no | ISO start time. Overrides wait_minutes. | | `wait_minutes` | integer | no | Minutes to wait before it starts, counted from now. | | `visibility` | string | no | public or private. Default public. | | `rated` | boolean | no | Games are rated and change ratings. Default true. | | `variant` | string | no | Variant key, e.g. standard. Default standard. | | `berserkable` | boolean | no | Players can Berserk. Only allowed if clock_increment is at most twice clock_time. | | `password` | string | no | Password players must enter. | | `min_rating` | integer | no | Minimum rating to join. | | `min_rated_games` | integer | no | Minimum number of rated games to join. | | `description` | string | no | Text shown to players on the tournament page. | Creates the tournament and returns its ID, URL and start time. Lichess allows up to 12 public or 24 private tournaments a day per account and rejects rated 15-second and 0+1 variant tournaments. A public tournament is visible to everyone on Lichess. By default you confirm each call; you can switch that off for this tool. Example response: ```json { "tournament_id": "Qx7pLm2a", "name": "Friday Blitz Night", "url": "https://lichess.org/tournament/Qx7pLm2a", "clock": "3+0", "minutes": 60, "rated": true, "starts_at": "2026-10-23T19:00:00Z", "created_today": 1 } ``` ### import_pgn_to_study Add a PGN as new chapters to a study you own or can edit. Access: write, asks the user first. REST: `POST /api/v1/lichess/studies/{study_id}/pgn-to-studies`. MCP: `lichess_write → import_pgn_to_study`. | Parameter | Type | Required | Description | |---|---|---|---| | `study_id` | string | yes | Study ID from list_studies. | | `pgn` | string | yes | PGN text. Several games separated by two blank lines become several chapters. | | `name` | string | no | Chapter name, 1 to 100 characters. Ignored when the PGN holds several games. | | `orientation` | string | no | white or black. Detected when empty. | | `mode` | string | no | practice, conceal or gamebook. Default normal analysis. | Creates one chapter per game and returns the chapter IDs and names. A study holds at most 64 chapters, so a larger import fails. Study members, and anyone who can view the study, see the new chapters. By default you confirm each call; you can switch that off for this tool. Example response: ```json { "study_id": "Wk3bPzQa", "chapters_added": 2, "chapters": [ { "chapter_id": "c1Rt8Yup", "name": "Round 1: Becker vs Silva" }, { "chapter_id": "d2Ws9Zvq", "name": "Round 1: Ortiz vs Okafor" } ], "total_chapters": 14 } ``` ### create_broadcast Create a broadcast for an over-the-board event, to which rounds are added next. Access: write, asks the user first. REST: `POST /api/v1/lichess/broadcasts`. MCP: `lichess_write → create_broadcast`. | Parameter | Type | Required | Description | |---|---|---|---| | `name` | string | yes | Tournament name. | | `visibility` | string | no | public, unlisted or private. Default public. Public does not list it on the main Broadcasts page. | | `description` | string | no | Long description in Markdown, shown in the broadcast overview. | | `show_scores` | boolean | no | Show players' scores from the broadcast games. | | `show_rating_diffs` | boolean | no | Show estimated rating changes from the broadcast games. | Creates the broadcast and returns its ID and URL. Visibility decides who can see it: Public, Unlisted (only from the link) or Private (only invited members). A public one is visible to everyone, so it reaches other people. By default you confirm each call; you can switch that off for this tool. Example response: ```json { "broadcast_id": "Zp4tNc6h", "name": "Riverside Chess Club Championship 2026", "visibility": "private", "url": "https://lichess.org/broadcast/riverside-chess-club-championship-2026/Zp4tNc6h", "rounds": [] } ``` ### create_broadcast_round Add a round to a broadcast, fed from a PGN URL, Lichess game IDs or Lichess usernames. Access: write, asks the user first. REST: `POST /api/v1/lichess/broadcasts/{broadcast_id}/round`. MCP: `lichess_write → create_broadcast_round`. | Parameter | Type | Required | Description | |---|---|---|---| | `broadcast_id` | string | yes | Broadcast ID from list_broadcasts or create_broadcast. | | `name` | string | yes | Round name, e.g. Round 1. | | `source` | string | yes | single_pgn_url, multiple_pgn_urls, lichess_game_ids or lichess_usernames. Use exactly one. | | `pgn_urls` | string[] | no | PGN URL, or several, for the two PGN sources. | | `game_ids` | string[] | no | Lichess game IDs for lichess_game_ids. | | `usernames` | string[] | no | Lichess usernames for lichess_usernames. | | `starts_at` | string | no | ISO start time. Read in the time zone set on the broadcast. | Creates the round and returns its ID and URL. The round must have one source type; with none, it can only be fed by pushing PGN. The round appears on the broadcast page for everyone who can view the broadcast. By default you confirm each call; you can switch that off for this tool. Example response: ```json { "round_id": "Kf3nQ8vD", "broadcast_id": "Zp4tNc6h", "name": "Round 1", "source": "single_pgn_url", "starts_at": "2026-10-24T10:00:00Z", "url": "https://lichess.org/broadcast/riverside-chess-club-championship-2026/round-1/Kf3nQ8vD" } ``` ## How do I connect Lichess to Claude Code, Codex or Cursor? Connecting Lichess takes three steps: sign up, sign in to Lichess once in your Cloud Browser and enable it for agents, then add one MCP server or call the REST API with the same key. ### Connect Lichess to your agent. 1. **Create an account** Sign up and add Lichess in the console. Your API key is there too. 2. **Sign in to Lichess in your Cloud Browser** Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to Lichess there yourself, the way you always do, then press Enable for agents, read only or read and write. We never save your password, and your agent keeps working even when your computer is off. 3. **Add Cotlet to your agent** Paste the snippet for your client. The same server and key serve every app you connect, so you do this once. Claude Code: ``` claude mcp add --transport http cotlet \ https://cotlet.dev/mcp/v1 \ --header "Authorization: Bearer $COTLET_API_KEY" ``` Cursor: ``` { "mcpServers": { "cotlet": { "url": "https://cotlet.dev/mcp/v1", "headers": { "Authorization": "Bearer ${COTLET_API_KEY}" } } } } ``` Codex: ``` # ~/.codex/config.toml [mcp_servers.cotlet] url = "https://cotlet.dev/mcp/v1" bearer_token_env_var = "COTLET_API_KEY" ``` 4. **Ask your agent** Ask in plain words. Your agent finds the Lichess tools on the server and calls them for you; anything that reaches other people waits for your OK unless you switch that off for a tool. ``` Every Monday, create a public 3+0 rated Arena for my club next Friday at 19:00, 60 minutes long, named "Friday Blitz Night". Skip it if one with that name is already scheduled. ``` ### Call Lichess from your scripts. 1. **Export your API key** Your scripts use the same API key as your agent. Keep it in an environment variable, never in your code. ``` export COTLET_API_KEY="cotlet_..." ``` 2. **Call a tool** Every tool is an endpoint under /api/v1/lichess with its own method and path, listed with the endpoints above. Path parameters go in the URL; the other parameters go in the query for GET and DELETE and in a JSON body otherwise. ``` curl -X POST https://cotlet.dev/api/v1/lichess/teams/riverside-chess/update \ -H "Authorization: Bearer $COTLET_API_KEY" \ -H "Content-Type: application/json" \ -d '{"message":"Friday Blitz Night starts at 19:00 UTC: https://lichess.org/tournament/Qx7pLm2a. Top three last week: rook_and_roll, maya_plays, club_captain."}' ``` 3. **Read the result** You get plain JSON back, ready for your script. A failed call costs nothing. ``` { "ok": true, "team_id": "riverside-chess", "recipients": 148 } ``` ## Why use Cotlet for Lichess? **Built for agents** - One MCP server for every app you connect. - The same tools as a REST API for scripts and cron jobs. - Works with Claude Code, Codex and Cursor. **Your login stays yours** - You sign in to Lichess yourself, in your own Cloud Browser. We never save your password; the profile is encrypted with AES-256-GCM, the cipher 1Password uses. - A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory. - The model never sees a login. - No stored passwords, no CAPTCHA solving, no MFA bypass. **You stay in control** - Scope each API key: its apps, its tools, read only or read and write. - Anything that reaches other people waits for your OK, so a leaked key cannot post or message as you. - Every background request listed in your Background activity. Disable for agents in one click. **Kept working for you** - We test every integration every 6 hours. - When Lichess changes, the tool pauses until we fix it. - Failed calls cost nothing. ## Is it safe to connect Lichess to Cotlet? Yes. You sign in to Lichess yourself, in your own Cloud Browser, and we never save your password. Your agents only get Lichess once you enable it, and every background request is listed. The browser profile is stored encrypted with AES-256-GCM, the same cipher 1Password uses for its vaults and Apple for iCloud Keychain. Independent public scanners grade cotlet.dev A+ and find it clean; click a result to rerun it yourself. - **A+ on Qualys SSL Labs**: Encryption in transit: TLS setup and certificates, on all four server addresses. [Live result](https://www.ssllabs.com/ssltest/analyze.html?d=cotlet.dev) - **A+ on securityheaders.com**: Browser protections sent with every page, all six headers present. [Live result](https://securityheaders.com/?q=cotlet.dev&followRedirects=on) - **A+ on Mozilla Observatory**: Mozilla's web security baseline: score 120 of 100, 12 of 12 tests passed. [Live result](https://developer.mozilla.org/en-US/observatory/analyze?host=cotlet.dev) - **Clean on Sucuri SiteCheck**: No malware, spam or defacement, and not on any of 9 blocklists, Google Safe Browsing included. [Live result](https://sitecheck.sucuri.net/results/cotlet.dev) [How Cotlet protects your access](https://cotlet.dev/security.md) ### Common concerns **Who runs Cotlet?** Cotlet is run by Take Group, a Polish software company working since 2019. Take Group runs about 3,200 websites on its own systems and has its own DevOps team for infrastructure security. We built and used integrations like this inside the company for years before opening them as Cotlet. **Is this an official Lichess integration?** No, Cotlet is independent of Lichess. Lichess's own API is too limited for this work. Cotlet works through your own Lichess account, the way you use Lichess in the browser, so you need no partner approval and no developer setup. **What about client data and GDPR?** Cotlet is run from the EU and follows the GDPR. Cloud Browsers run in Finland, a Tier 1 country in the ITU Global Cybersecurity Index 2024. Data passes through a call and is not kept after it. **Can I start with read only?** Yes. Enable the app for agents as read only, or make the API key read only, and anything that reaches other people waits for your OK unless you switch that off per tool. **Is it reliable?** Every Cotlet service is checked every 3 minutes from Europe, North America, Asia and Australia. The live results and any outage are public at status.cotlet.dev. **How do I stop?** Press Disable for agents next to Lichess in your console: your agents lose access at once and you stay signed in. Signing out of Lichess in the browser works too, and Reset browser deletes the whole profile. ## Is there a Lichess MCP server on GitHub? Yes. Community Lichess MCP servers exist on GitHub, usually maintained by one person. You install one yourself, give it a Lichess API token, and fix it when something changes. Cotlet hosts the same kind of server for you, signs in as you once, and our team keeps it working. The Lichess API is open and easy to script, so Cotlet adds the most when you want agents to use it without running anything. | | GitHub MCP server | Cotlet | |---|---|---| | Setup | Clone the repo, create a personal API token with the right scopes, add the server to each MCP client | Sign up, sign in to Lichess once, add one MCP server or API key | | When Lichess changes | It breaks until you or the maintainer fix it | Our team tests it daily and fixes it for you; failed calls are free | | Your Lichess access | A token in a file on your computer, readable by any program you run, valid until you revoke it | Signed in inside your own Cloud Browser in the EU, profile encrypted, only for the apps you enable, disabled for agents in one click | | When access expires | Tools fail until you create a new token or sign in again by hand | Your Cloud Browser keeps you signed in; if Lichess logs you out, your agent gets a link to sign in again | | Upkeep | You update, monitor and debug it yourself | Nothing to host or update | | Where it runs | Your computer, while it is on | Hosted: Claude Code, Codex, Cursor, n8n and scripts, also on a schedule | | Price | Free, paid for with your time | Free 7-day trial, then pay-as-you-go credit packs, no subscription | ### Which one fits you **Pick Cotlet if** - you are not a developer, or you do not want to maintain a server - you need it to keep working when Lichess changes, without checking it yourself - your agent or a script should run it on a schedule, also while your computer is off **Pick an open-source server if** - you are comfortable installing, updating and fixing it yourself - you want your sign-in to stay on your own computer - you only need it now and then, from one MCP client ## How much does the Lichess API cost? Free 7-day trial with 2,000 credits, no card needed. After that, the Lichess API is pay as you go with no limit on apps: Credit packs from $29 for 5,000 credits, one-time, no subscription. A successful call uses 20 to 30 credits (25 for most tools, about $0.10 to $0.15), your Cloud Browser uses 50 credits a day while it has an app enabled for agents, however many apps that is, and an agent driving the browser itself uses 5 credits a minute. Credit packs stay valid for 12 months and stack, so unused credits carry over. | Credits | Price, one time | Calls at 25 credits | Per 1,000 credits | |---|---|---|---| | 5,000 | $29 | 200 | $5.80 | | 15,000 | $79 | 600 | $5.27 | | 32,000 | $149 | 1,280 | $4.66 | | 60,000 | $249 | 2,400 | $4.15 | Only successful calls use credits; failed calls and timeouts cost nothing. At a balance of 0 calls pause, never a surprise charge. Authenticate with the `Authorization: Bearer` header. [See full pricing](https://cotlet.dev/pricing.md) ## How Cotlet holds your access Cotlet hosts MCP servers and REST APIs for apps with no usable API. Your agent works in your own Lichess account. - **Company details:** Cotlet is run by Take Group sp. z o.o., a company registered in Poland. Its full address and registration numbers are in the Terms of service. [Terms of service](https://cotlet.dev/terms) - **Your sign-in:** You sign in to Lichess yourself, in your own Cloud Browser: a Chrome we run for you in the EU, one per app. We never save your password (password saving is off), the profile is stored encrypted with AES-256-GCM, and your agents get Lichess only after you enable it. When Lichess signs you out, your agent gives you a link to sign in again. [Security](https://cotlet.dev/security.md) - **Revoking access:** Press Disable for agents next to Lichess, sign out of Lichess in your Cloud Browser, or reset the browser. Every background request is listed in your Background activity. Actions that reach other people wait for your OK unless you switch that off per tool. - **What we never do:** Store passwords, solve CAPTCHAs or bypass MFA. - **Lichess's terms:** You use your own Lichess account and stay responsible for following Lichess's terms. Cotlet is independent and not affiliated with Lichess. [Terms](https://cotlet.dev/terms) - **Contact:** Questions about the company, security or an app: [contact@cotlet.dev](mailto:contact@cotlet.dev) ## Frequently asked questions **How do I get access?** Sign up free, open Lichess in the console and press Request access. Then you create your API key and connect Lichess there. **Do I need to be technical?** No. You sign in to Lichess once in your Cloud Browser, a normal Chrome you open from the console, and paste one command into your agent, or one URL into n8n. Your agent can walk you through it. There is no server to install, update or fix. **Is it safe to connect Lichess to Cotlet?** Yes. You sign in to Lichess yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Lichess once you enable it, every background request is listed, and the browser profile is stored encrypted with AES-256-GCM, the cipher 1Password uses for its vaults. The AI model never sees a login, posts and messages wait for your OK, and Disable for agents cuts access in one click. Independent scanners grade cotlet.dev A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory; live results are on https://cotlet.dev/security. **Is a hosted server safer than a local one? My Lichess sign-in would leave my computer.** On Cotlet you sign in inside your own Cloud Browser, which only you open, and its profile is stored encrypted with AES-256-GCM in the EU. Agents get only the apps you enable, and every background request is listed. A local server keeps your Lichess cookie in a plain file on your computer, readable by any program you run, and stops when your computer is off. **Why does Cotlet send requests instead of clicking in my browser?** To be fast, Cotlet doesn't click through Lichess's pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. Lichess sees the same browser and IP you signed in with, and every request is listed in your Background activity. **What if someone gets my Cotlet API key?** The key holds no Lichess login or cookies, it only asks Cotlet to run a tool. It can call only the apps and tools you gave it, and a read-only key changes nothing. Anything that reaches other people, like posts, comments or messages, waits for your OK in the dashboard by default, so a leaked key cannot post or message as you. When you switch approval off for a scheduled job, give that job its own key limited to that one tool. Every call is in your activity log, and deleting the key ends access at once. **Why a signed-in browser and not OAuth, like other integration platforms?** Lichess offers no OAuth token you can simply grant for these tools: its official API leaves them out or needs a developer app, a plan or an approval first (see the official API section above). That is why Cotlet sets the limits itself: per key, per tool, with your approval before anything reaches other people. Cotlet is run by Take Group sp. z o.o., an EU company (VAT PL6342984273). **Can my agent play or suggest moves in my Lichess games?** No. Cotlet has no tool that joins a game, makes a move or analyses a live position. Lichess forbids external help during a game and allows moves only through its own site or its official Board and Bot APIs, so these tools stay on teams, tournaments, studies, broadcasts and finished games. **Which Lichess role do the team tools need?** Listing join requests needs a team leader. Accepting and declining need the team leader role, and sending an update needs a leader with the Updates permission. A member who is not a leader can still use the tournament, study and export tools. **Is there a rate limit?** Yes. Lichess rate limits all API requests, asks clients to make one request at a time and answers 429 when a limit is hit, usually clearing after a minute. Cotlet calls are made one at a time. **Can my agent post or send messages in Lichess without asking me?** No. Every call to accept_team_join_request, decline_team_join_request, send_team_update, create_arena_tournament, import_pgn_to_study, create_broadcast or create_broadcast_round waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals. **Can I use the Lichess API in n8n?** Yes. Add https://cotlet.dev/mcp/v1 with your API key in n8n's MCP Client node, or call its endpoints under https://cotlet.dev/api/v1/lichess from the HTTP Request node. --- Give your AI agents your signed-in browser. **Product:** [Integrations](https://cotlet.dev/integrations.md) · [Use cases](https://cotlet.dev/use-cases.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 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. ## For AI agents: sign your user up Is your user asking you to sign them up for Cotlet? You can do it for them, no account or key needed. 1. Read the fields and their allowed values: GET https://cotlet.dev/api/v1/access-requests 2. Ask the user for each value: email, apps, what you will do with them. If they leave the password to you, generate a strong one and show it to them. 3. Show the user what you will send, then POST it as JSON to https://cotlet.dev/api/v1/access-requests. One call creates the account and sends the access request; we email the user when access is granted.