エージェントを強化
公開元自身の URL です。PlugMCP のエンドポイントではありません。
キーとログ付きでコピーをホスト。
https://api.flowcastle.ai/api/mcp上の Claude ボタンを押すと、名前と URL が入力された状態で Claude が開きます。確定の操作は Claude 側で行います。
claude mcp add --transport http ai.flowcastle-flowcastle https://api.flowcastle.ai/api/mcpRun in a terminal.
{ "mcpServers": { "ai.flowcastle-flowcastle": { "command": "npx", "args": [ "-y", "mcp-remote", "https://api.flowcastle.ai/api/mcp" ] } }}claude_desktop_config.json
リモート URL か、手元のマシンのコマンドか 2 つのインストール方法の違い
PlugMCP で実行
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
起動公開元より
Ready-to-use Telegram bot templates and an MCP server — build, edit, and deploy Telegram bots from Claude Code, Codex, Cursor, or any MCP-capable AI agent. No SDK boilerplate: describe the bot, and your agent assembles the flow.
Build, edit, and deploy Telegram bots on FlowCastle's hosted visual flow platform.
FlowCastle is a visual workflow builder for Telegram bots and web chat: flows, triggers, conditions, AI steps, payments (Stripe / YooKassa / Telegram Stars), broadcasts, drip sequences, and integrations (Gmail, Google Sheets, Notion, OpenAI, …) — with a REST API and an MCP server, so bot development works straight from your AI coding agent. Every block an agent creates through MCP is the same block you can drag, wire, and edit visually.
This repo is for developers. It contains:
FlowCastle exposes an MCP server over Streamable HTTP:
POST https://api.flowcastle.ai/api/mcp
Authorization: Bearer <your-application-api-key> # starts with app_
Get a key: sign up → create an application → API page → MCP tab.
Claude Code
export FLOWCASTLE_MCP_TOKEN='<your-application-api-key>'
claude mcp add --transport http flowcastle https://api.flowcastle.ai/api/mcp \
--header "Authorization: Bearer $FLOWCASTLE_MCP_TOKEN"
Codex
codex mcp add flowcastle \
--url https://api.flowcastle.ai/api/mcp \
--bearer-token-env-var FLOWCASTLE_MCP_TOKEN
Cursor / any MCP client (JSON config)
{
"mcpServers": {
"flowcastle": {
"type": "http",
"url": "https://api.flowcastle.ai/api/mcp",
"headers": {
"Authorization": "Bearer <your-application-api-key>"
}
}
}
}
Then just ask your agent things like:
"Look at my FlowCastle workspace and add a lead-qualification flow: greet on /start, ask three button questions, save answers to contact variables, and notify me."
The agent reads your workspace with get_workspace_summary / get_flow_context, drafts a batch of flow-builder actions, checks it with validate_actions, and applies it with apply_actions. See mcp/README.md for the full tool reference.
Each JSON file in templates/ is a complete bot: metadata (title, summary, use-cases, suggested variables, required modules) plus a schemaExample.actions array — an ordered batch of create_flow / create_block / create_link / create_variable operations in the exact format apply_actions accepts.
Three ways to use them:
search_flow_examples / get_flow_example and apply one (optionally customized) to your workspaceFull index and format description: templates/README.md.
Application-scoped REST API for contacts, contact variables, goal events, flow sends, and broadcasts:
https://api.flowcastle.ai/api/public/v1Auth uses the same app_… application key (Authorization: Bearer or X-API-Key).
Step-by-step builds on the FlowCastle blog:
Found a bug in a template, or built a flow worth sharing? Open an issue or PR — templates are plain JSON, and validate_actions (via MCP) will tell you if a batch is well-formed.
The contents of this repository are licensed under the MIT License.
Build, edit, and deploy Telegram bots on FlowCastle's hosted visual flow platform.
{ "mcpServers": { "ai.flowcastle-flowcastle": { "url": "https://api.flowcastle.ai/api/mcp", "headers": {} } }}60 個のツール
よくある質問
| Update application-level settings (name, active state, default language, language for everyone else, incoming-message behavior, the member notice when AI credits run out). Requires the manage_settings permission in that application. Only the fields you pass are changed; omitted fields keep their cur |
| import_website_knowledge | Crawl a website into a knowledge base so an AI_TOOL_ROUTER can answer from it. Creates a new base (named after the host) unless knowledgeBaseId is given. Honours robots.txt, skips junk and duplicate pages, keeps blog posts by default, and caps at maxPages. Returns at once with a job to poll via get_ |
| get_knowledge_base_document | Return the FULL text of one knowledge-base document, with contentSha256 — the hash edit_knowledge_base_text_document quotes as expectedSha256. Read-only. get_workspace_summary and get_application_context show each document only as a preview (truncated: true when cut), so read the document here befor |
| get_website_import | Status of a website import started by import_website_knowledge or an import_website_into_knowledge_base action: stage, progress, counters, warnings and the pages that were not imported. Read-only. Poll until status is DONE, DONE_WITH_ERRORS or FAILED. |
| list_watched_groups | List the group/channel chats a telegram_mtproto userbot monitors. Read-only. The watched list is the single source of truth for which chats the userbot processes: messages from unlisted group/channel chats are dropped (fail closed) and their contacts never materialize; DMs always pass. botId may be |
| list_telegram_operations | Discover supported Telegram MTProto account operations, input schemas, permissions and limits. Requires manage_broadcasts. All current operations read public data; this catalog does not connect to Telegram. botId may be omitted when the application has exactly one userbot. |
| execute_telegram_operation | Submit one supported read operation on the connected telegram_mtproto account. Call list_telegram_operations for the input schema. Returns a requestId; poll get_telegram_operation until completed, error or timed_out. Requires manage_broadcasts. Nothing is sent, joined, marked as read, viewed or clic |
| get_telegram_operation | Read a Telegram operation status and result using its requestId and the same applicationId/botId used for submission. Requires manage_broadcasts for the owning application. Poll every two seconds. Results expire one hour after their last update. timed_out means no result arrived within 60 seconds; a |
| set_watched_groups | Replace a telegram_mtproto userbot's watched-groups list — the chats it monitors. Requires the manage_settings permission. SET semantics: send the COMPLETE desired list every time (call list_watched_groups first and include existing entries you want to keep — omitting one removes it). Each entry nee |
| sync_dialog_contacts | Import a telegram_mtproto userbot's existing chats as contacts — DM partners, groups, and channels — so everything the account already talks to becomes a contact send_message can target without waiting for each chat to message first. Importing does not allow sending: send_message to these contacts i |
| get_workspace_summary | Return a compact application, flow, sequence, operation, and bot summary — the cheapest way to orient in a workspace. Read-only, no side effects. Deliberately omits variables and full flow graphs: use get_variable_context for variables, get_flow_context for a flow's topology, and get_application_con |
| get_variable_context | Search variable definitions by scope and keyword, or read one variable by id. Read-only. Returns { variables, total, returned, truncated } — compare returned against total to detect a cut-off result set and re-call with a higher limit. Values are withheld unless includeValues is true; in a list each |
| get_application_context | Return the full application-level automation context in one read-only call: every flow (with folders), connected bots, variables, sequences, and operations. This is the broad orientation call — prefer get_workspace_summary when you only need names and counts, since this response grows with workspace |
| get_module_catalog | Return a compact index of both installed and available marketplace modules, with each module's key, versions, description, actions, and triggers. Read-only. Start here when you need a capability the core action kinds do not cover; then call get_module_details for the exact input fields of one module |
| get_module_details | Return everything needed to use one module: action input fields and their types, trigger configuration, manual setup fields (credentials an operator must fill in the dashboard), and references to already-installed actions. Read-only. Call get_module_catalog first to obtain moduleKey, and call this a |
| install_module | Install an exact marketplace module version into an application and create any missing installed-template actions. Requires the manage_automation permission. Call get_module_catalog first to select the module and version, then get_module_details after installation to inspect setup requirements and i |
| search_flows | Find every flow and block whose contents contain a keyword. Read-only. Searches message text and its translations, button labels and URLs, action names and configs, action input/output field paths and values, condition operands, trigger commands and payloads, custom-code files, and flow names and de |
| get_flow_context | Return one flow's graph topology: its blocks in reading order from the start block, a short summary per block, and where each block and each menu button leads (links[].to, menu.buttons[].to). Read-only. Deliberately omits block data, action configs and the ids of buttons, actions, links and conditio |
| get_block_details | Return the complete contents of one block: block data, action configs, HTTP request bodies, custom-code files, triggers, menu payloads, and media paths. Read-only. This is the heaviest read in the API — call get_flow_context first to find the block you need rather than walking a flow block by block. |
| get_action_schema | Read-only, needs no API key. The action-authoring contract apply_actions batches are validated against. With NO arguments, returns an INDEX of block types, actions, action kinds and topics with descriptions and sizes. Then request only what this bot uses. Detail responses include essential rules and |
| get_design_guidelines | Return the flow-design rules that validation does NOT enforce: when to split a branch into its own flow, how navigation and menus must be wired, and worked examples. Read-only, needs no API key. Called with NO arguments it returns a compact INDEX: the short rules every batch needs, in full, plus eve |
| get_funnel_analytics | Return the measured conversion funnels of the workspace's ENTRY flows over the last 14 days, busiest first: how many new contacts entered, which blocks they reached, the share who stop at each block, which buttons lead nowhere (pressed then silence), and how many recorded a goal. `dropoff` names the |
| get_flow_analytics | Measure how NAMED flows are actually used over the last 14 days: how many contacts entered each one, where inside it they stop (per block, with the stop RATE), how many were answered by a human agent afterwards, and how many hit an error. Unlike get_funnel_analytics this works for ANY flow — includi |
| get_survey_results | Read what customers ANSWERED in this workspace's surveys. A survey is any flow marked isSurvey: its choice questions record which option each contact tapped, and its free-text questions store the reply the contact typed. Called with NO flowId it lists every survey flow with how many people it reache |
| search_flow_examples | Search the library of reusable flow examples covering common business cases (lead capture, onboarding, payments, reminders). Read-only, needs no API key. Returns summaries to choose by — id, title, summary, useWhen, tags, requiredModules, hasSchemaExample — with no flow body; pass an id to get_flow_ |
| get_flow_example | Return one reusable flow example by id, optionally with a complete action batch you can adapt and pass to apply_actions. Read-only, needs no API key. Call search_flow_examples first to find the id. |
| validate_actions | Dry-run validation of a proposed batch of flow-builder actions. Mutates nothing and is safe to repeat. OPTIONAL: apply_actions runs this exact validation itself and applies nothing when invalid, so calling validate_actions first is redundant — use it only to check a draft you do not intend to apply |
| apply_actions | Validate and apply a batch of flow-builder actions — the single write path for editing flows, blocks, variables, broadcasts, sequences, and folders. Call this directly; a separate validate_actions call beforehand is unnecessary. Broadcasts have no dedicated tool and are managed here: create_broadcas |
| deploy_application | Publish the workspace to its bots — the API equivalent of the dashboard's Deploy button. This is the step that makes edits live. apply_actions writes to the DRAFT graph. Until this runs the connected bots keep serving the previously published version, so a change that looks applied has no effect for |
| run_flow_autotest | Runs deterministic behavioural tests against flows that are ALREADY applied (compiles them to an AST and simulates a user). Call after apply_actions to verify a build; read `summary` and the failed checks, patch with apply_actions, re-run. Mutates nothing. The smoke layer runs on its own with no inp |
| send_message | Send a message to ONE contact right now, outside any flow. For reaching many contacts use a broadcast instead. Target the contact with contactId (globally unique — preferred), or with platformId (the platform-side id, e.g. the Telegram user id). platformId is NOT globally unique: it is unique only p |
| send_flow_to_contacts | Run an EXISTING interactive flow for each listed contact right now, outside any trigger — as if each of them had just triggered it. Use it when the WHOLE message is the flow — its first block's text, media and buttons are what the recipient sees. To send your own custom text with buttons that run a |
| read_messages | Read the message transcript: what users sent the bot and what the bot sent back, newest first. Source is the runtime's own message ledger, written by the bot as it handled each turn — inbound messages are recorded before any routing decision, so messages that matched no trigger are here too. Filter |
| list_contacts | List and search contacts in the application, paginated, newest first. Read-only. Filters combine as AND; search matches name, username, email, phone, and platformId; `tags` / `tagIds` keep only contacts carrying at least one of those tags (UTM attribution tags are named "utm: <slug>" — discover them |
| list_bot_chats | List the groups and channels the application's bots were added to, newest first: title, kind, the numeric chatId a flow uses to address the chat, when the bot was added, and the bot's status and rights there (is it an administrator, can it invite or remove members). Read-only. A chat appears once th |
| list_contact_tags | List the contact tags in use in the application (or one bot) with how many contacts carry each, most-used first. Read-only. This is the attribution view: UTM tags ("utm: <slug>", set by ?start=utm--<slug> deep links, one per ad or campaign) show how many contacts each source brought in; other tags a |
| get_contact | Return one contact's full profile plus every contact-variable value stored for them. Read-only. Values may hold personal data; variables of type SECRET are always redacted. Call list_contacts first to find the contactId. |
| get_contact_activity | Return one contact's engagement history: goals they achieved and buttons they clicked, newest first, plus all-time goal totals. Read-only. This is the per-contact companion to get_broadcast_analytics (which is aggregate). Clicks are inline/menu button presses inside the bot — typed replies, commands |
| list_event_contacts | The reverse lookup: which contacts triggered one analytics event — achieved a goal (kind GOAL + goalKey), clicked a button (BUTTON_CLICK + blockId, optionally buttonId/buttonIndex), were sent a block (BLOCK_SENT + blockId), or received a broadcast (BROADCAST_DELIVERED + broadcastId). Read-only, pagi |
| create_contact | Create a contact manually — for imports or externally-sourced audiences; contacts who message a bot are created automatically. Requires the manage_broadcasts permission. platformId must be unique within the bot (duplicate fails with 409); botId may be omitted only when the application has exactly on |
| update_contact | Update a contact's profile fields and/or contact-variable values. Requires the manage_broadcasts permission. Only the fields you pass are changed — omitted fields keep their current value — so the call is idempotent. The variables map takes variable NAMES (or full folder paths when a name is ambiguo |
| list_broadcasts | List broadcasts in the application with status, schedule, and delivery counts. Read-only. Filters combine as AND. Note that delivery counts report messages attempted, not confirmed deliveries. recipientCount is the number of delivery rows once the broadcast has started sending. Before that it is a l |
| get_broadcast_details | Return full details for a single broadcast: status, schedule, recurrence rule, linked flow, and delivery breakdown by status. recipientCount is the number of delivery rows once the broadcast has started sending. Before that it is a live count of the audience only when the audience has no filter. nul |
| get_broadcast_analytics | Return engagement analytics for a broadcast: delivery breakdown by status plus per-message-block sent and clicked counts for its flow, over an optional date window. Read-only. Sent counts reflect messages attempted, not confirmed deliveries. |
| list_releases | List the application's releases, newest first. A release is a frozen copy of everything the editor held when it was published (flows, steps, menus, actions, variables), stored with the rows' own ids. Each entry has its number, when and how it was made (DASHBOARD, MCP, AI_REPUBLISH, BOT_CREATE, or RE |
| restore_release | Put an earlier release back into the editor: every flow, step, menu, action and variable returns exactly as it was, under the same ids, so running conversations, scheduled steps and buttons users already received keep working. Nothing is lost: the current editor state is saved first as a RESTORE_SAF |
| list_pulse_items | List Pulse items — the workspace attention queue. Two kinds: `attention` is an observed problem a detector found (failing flows, a failed broadcast, an unsubscribe spike), `recommendation` is a proposed improvement. Read-only. Defaults to open items, ordered by severity then due time, the same order |
| get_pulse_item | Return one Pulse item in full: the measured evidence, the ids of the conversations and execution-log rows behind it, and the change Apply would build if the item carries one. Read-only. Call list_pulse_items first to get the itemId. Note `resolutionPolicy`: an `automatic` item closes itself when its |
| update_pulse_item | Change one Pulse item's state. Every action changes the queue for the WHOLE workspace — an item belongs to the workspace, not to whoever called the tool, so dismissing a recommendation hides it from every member and records who decided that. `acknowledge` closes an attention item as seen, with no re |
| list_follow_up_tasks | List follow-up tasks — reminders for a person to get back to a contact. Read-only, ordered by due time so overdue work comes first. A follow-up sends nothing by itself. Scopes: `mine` is the open work assigned to the key's owner and needs a personal key; `unassigned` is unowned open work; `team` is |
| create_follow_up_task | Create a follow-up reminder for a person to get back to a contact. For work the team owes (checking a database, fixing a bug, a refund), use create_task instead. Creates persistent state and is NOT idempotent: calling it twice creates two reminders. Nothing is sent when it comes due — it is a to-do, |
| update_follow_up_task | Close, reopen, snooze, or reschedule one follow-up task. Completing it records that a person handled the reminder — it does not message the contact. Snoozing moves the due time too, so the task reappears when the snooze ends. |
| list_tasks | List CRM tasks — work the team owes, like checking payment records, fixing a bug or sending a refund. Read-only. Tasks live in CRM → Tasks. A task may stand alone or be linked to contacts. While leads are on for the workspace, linking parks the contact's open lead until the task is done (parkLeads, |
| create_task | Create a CRM task, on its own or linked to contacts. Creates persistent state and is NOT idempotent. Tasks live in CRM → Tasks. A task may stand alone or be linked to contacts. While leads are on for the workspace, linking parks the contact's open lead until the task is done (parkLeads, default true |
| update_task | Change one CRM task: its fields, its status, or which contacts it is linked to, in one call. Tasks live in CRM → Tasks. A task may stand alone or be linked to contacts. While leads are on for the workspace, linking parks the contact's open lead until the task is done (parkLeads, default true), and m |
| delete_task | Delete one CRM task. Leads parked on it come back to Waiting on us. The task disappears from CRM → Tasks; to finish a task instead, use update_task with status "done". |
| query_flow_logs | Read the bot execution log (flow_execution_log) — the record of what the runtime actually did, and the only place that separates "the action ran" from "the action produced output". Read-only; requires the view_logs permission. Two modes: without groupBy it returns the newest matching rows, with grou |
| get_tribute_setup | Read the Tribute one-time payment setup of an application: whether a Tribute account is connected, the notification link and whether the owner confirmed it, the products set up here, the number contact variables a purchase can add to, and nextSteps (what is still missing, in order; empty means ready |
このページで Cursor、Claude Desktop、Claude Code、VS Code 用の http 設定をコピーできます。PlugMCP のプロキシではなく、公開元のインストール方法を使います。
このレコードに必須の環境変数は記載されていません。
FlowCastle には HTTP で接続します。
最終チェックは 2026-11-15 です。 Build, edit, and deploy Telegram bots on FlowCastle's hosted visual flow platform.
